system

Abstract

Provide a system. [Solution] a means of collecting audio feedback from users; a means for acquiring data from a plurality of sensors mounted on the vehicle; a means for analyzing the collected voice feedback and sensor data to determine the driver's driving state; A means for suggesting transition to an automated driving mode based on the driver's driving state; A means for transmitting the analysis results to the generative AI and generating information related to safe driving; a means for presenting the generated information on safe driving to a driver; A system that includes a means to generate communication messages with pedestrians and transmit them outside the vehicle during autonomous driving.

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] The present invention relates to an automated driving system, and in particular to a system that evaluates a driver's driving skill and fatigue level in real time and suggests an appropriate transition to automated driving mode. Conventional automated driving systems lack the means to appropriately assess a driver's fatigue level and driving skill, posing challenges in ensuring safe driving and improving social acceptance. Furthermore, the provision of information regarding safe driving is limited, and communication with pedestrians during automated driving in urban areas is also insufficient. Therefore, the present invention aims to solve these challenges. [Means for solving the problem]

[0005] The present invention provides the following means. First, it provides a means for collecting voice feedback from the user, which allows the driver's subjective state to be obtained in real time. Second, it provides a means for acquiring data from multiple sensors installed in the vehicle, including biometric data such as heart rate and driving time. Third, it provides a means for analyzing the collected voice feedback and sensor data to determine the driver's driving state, which allows accurate determination of whether the driver is fatigued. Fourth, it provides a means for suggesting a transition to autonomous driving mode based on the driver's driving state, which ensures safe driving. Fifth, it provides a means for transmitting the analysis results to a generative AI and generating information regarding safe driving. Sixth, it provides a means for presenting the generated information regarding safe driving to the driver, thereby providing appropriate driving advice to the driver. Finally, it provides a means for generating communication messages with pedestrians during autonomous driving and transmitting them outside the vehicle, which improves the social acceptability of autonomous vehicles.

[0006] "Means of collecting voice feedback from users" refers to the function of capturing voice data from drivers and collecting feedback in real time.

[0007] "Multiple sensors installed in the vehicle" refers to various sensors installed inside and outside the vehicle to measure the driver's biometric information and the vehicle's operating status.

[0008] "Means for analyzing and determining the driver's driving state" refers to the function of using algorithms and AI to evaluate the driver's state based on collected voice feedback and sensor data.

[0009] "Means for proposing a transition to automated driving mode based on the driver's driving state" refers to a function for recommending a switch from manual driving to automated driving based on the determined driving state.

[0010] "Generative AI" refers to artificial intelligence that analyzes collected data and generates appropriate advice and recommendations for safe driving.

[0011] "Driving safety information" refers to driving advice and recommendations provided to ensure driver and vehicle safety.

[0012] "Means for generating and transmitting pedestrian communication messages outside the vehicle" refers to the ability of an autonomous vehicle to generate messages to communicate safely and effectively with people around it and transmit them to the outside through audio or display. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[0035] System Configuration

[0036] The system mainly consists of the following components:

[0037] User device (in-vehicle device or smartphone)

[0038] server

[0039] Multiple sensors installed in the vehicle

[0040] DETAILED DESCRIPTION OF THE INVENTION

[0041] Collecting voice feedback from users

[0042] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," this feedback is recorded as text data on the device.

[0043] Collecting data from sensors

[0044] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[0045] Analysis of driver's driving state

[0046] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0047] Proposal for transition to autonomous driving mode

[0048] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0049] Providing information on safe driving

[0050] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates information such as "Keep the recommended speed at 60 km / h and make sure to check for safety," which is then sent to the user's device and displayed to the driver.

[0051] Communication with pedestrians during autonomous driving

[0052] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[0053] The user device will announce this message to the outside via the vehicle's speakers and display.

[0054] Specific examples

[0055] Consider the following scenario as a concrete example: A driver begins to feel fatigued after driving for a long period of time. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." A sensor measures a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "Please maintain a recommended speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and gains the understanding of pedestrians.

[0056] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[0060] Specifically, the terminal converts voice feedback such as "I'm tired" into text data and records this as "user feedback."

[0061] Step 2:

[0062] The device collects data in real time from multiple sensors installed in the vehicle.

[0063] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[0064] Step 3:

[0065] The device sends the collected sensor data and user feedback to the server.

[0066] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[0067] Step 4:

[0068] The server analyzes the received data and determines the driver's driving condition.

[0069] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[0070] Step 5:

[0071] The server sends the analysis results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[0072] Specifically, if the server determines that the driver is in a "fatigue state," it generates a message stating, "We recommend switching to autonomous driving mode," and sends it to the device.

[0073] Step 6:

[0074] The user terminal receives the message from the server and displays it to the driver.

[0075] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[0076] Step 7:

[0077] The server sends the sensor data to the generative AI, which generates information about safe driving.

[0078] Specifically, it generates safe driving information such as "Keep the recommended speed at 60 km / h and make sure to check for safety."

[0079] Step 8:

[0080] The user terminal presents the generated safe driving information to the driver.

[0081] Specifically, the device will display the message, "Please maintain a recommended speed of 60 km / h and ensure safety."

[0082] Step 9:

[0083] The server generates the communication messages with pedestrians required during autonomous driving.

[0084] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[0085] Step 10:

[0086] The user terminal transmits the generated communication message to the pedestrian.

[0087] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[0088] Example 1

[0089] 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."

[0090] Advances in autonomous driving technology are expected to reduce driver burden and prevent accidents, but current systems have difficulty properly assessing the driver's driving state in real time and taking the necessary action immediately. Furthermore, there is a lack of communication with pedestrians, leaving challenges in improving safety and ensuring social acceptance. There is a need to solve these problems and provide safer, more effective autonomous driving systems.

[0091] 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.

[0092] In this invention, the server includes a means for collecting voice feedback from the user in real time, a means for acquiring data in real time from multiple sensors mounted on the vehicle, and a means for analyzing and determining the driver's driving state based on the collected voice feedback and sensor data. This makes it possible to appropriately evaluate the driver's driving state in real time, suggest transitioning to autonomous driving mode, provide safe driving information, and smoothly communicate with pedestrians.

[0093] "Voice feedback from the user" refers to feedback entered by the user through an in-car terminal or smartphone, and is a means of obtaining the driver's condition and emotions in real time.

[0094] "Multiple sensors" refers to a diverse group of sensors installed in the vehicle, such as heart rate sensors, driving time measurement sensors, and road condition sensors, which are devices that collect driver biometric information and road environment information in real time.

[0095] "Voice recognition function" is a technology that converts voice data into text data and is used to accurately analyze the driver's voice feedback.

[0096] "Means for analyzing and judging the driver's driving condition" refers to the system's function of analyzing the driver's driving situation based on collected voice feedback and sensor data, and evaluating and judging that condition.

[0097] "Means for suggesting transition to autonomous driving mode" refers to the system's function of providing a message to the driver to recommend switching to autonomous driving mode based on the analysis results.

[0098] A "generative AI model" is an artificial intelligence model that generates appropriate safe driving information based on analysis results, and provides safe driving instructions and advice using prompt text as input.

[0099] "Information about safe driving" is information generated by a generative AI model to support safe driving, such as recommended driving speeds for drivers and methods for ensuring safety.

[0100] "Communication messages with pedestrians during autonomous driving" are messages generated by autonomous vehicles to enable smooth interaction with pedestrians, including messages explaining the vehicle's behavior and warning pedestrians.

[0101] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[0102] System Configuration

[0103] The system mainly consists of the following components:

[0104] User device (in-vehicle device or smartphone)

[0105] server

[0106] Multiple sensors installed in the vehicle

[0107] Collecting voice feedback from users

[0108] The user device uses a voice recognition function (e.g., Google (registered trademark) Assistant or Amazon Alexa) to collect the driver's voice feedback in real time. For example, if a driver feels tired after driving for a long time and says, "I'm tired," the voice data is sent to the device and converted into text data by the voice recognition function. This text data is then sent directly to the server.

[0109] Collecting data from sensors

[0110] The vehicle is equipped with multiple sensors, including a heart rate sensor, a driving time measurement sensor, and a road condition sensor. These sensors collect data in real time and send it to a server via the user's device. For example, the heart rate sensor measures the driver's heart rate as 120 bpm, and the driving time measurement sensor measures the driving time as 3 hours.

[0111] Analysis of driver's driving state

[0112] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, based on voice feedback such as "I'm tired," a heart rate of 120 bpm, and driving time of more than three hours, the server will determine the driver's condition as "fatigue." To do this, it uses data processing algorithms and machine learning models.

[0113] Proposal for transition to autonomous driving mode

[0114] The user device will suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the message "We recommend switching to autonomous driving mode" will be displayed on the user device. This is an important step to maintain safety and comfort.

[0115] Providing information on safe driving

[0116] The server sends the analysis results to a generative AI model (such as OpenAI's (registered trademark) GPT model) to generate information about safe driving. Safe driving information is obtained by inputting a specific prompt into the generative AI model. For example, the prompt could be, "Please generate appropriate safe driving information if your heart rate is 120 bpm and your driving time is more than three hours." Based on this prompt, the generative AI model generates information such as, "Keep the recommended speed at 60 km / h and ensure thorough safety checks." This information is sent to the user's device via the server and presented to the driver.

[0117] Communication with pedestrians during autonomous driving

[0118] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[0119] Specific examples

[0120] As a concrete example, consider the following scenario: A driver feels fatigued after driving for a long time and utters, "I'm tired." This feedback is converted to text on the user's device and sent to the server. At the same time, the heart rate sensor measures a heart rate of 120 bpm and the driving time sensor measures three hours of driving time. These data are sent to the server, and analysis results indicate a "fatigue state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." The generative AI model also receives a prompt: "If your heart rate is 120 bpm and you have been driving for more than three hours, please generate appropriate safe driving information." This information is then displayed on the user's device. The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[0121] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] Collecting voice feedback from users

[0125] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," the voice data is input into the device. The device converts this voice data into text data and sends it to the server.

[0126] Input: Driver's voice feedback (e.g., "I'm tired")

[0127] Output: Converted text data (e.g. "Tired")

[0128] Specific operation: The driver says, "I'm tired." The user device uses its voice recognition function to convert the speech into text and send it to the server.

[0129] Step 2:

[0130] Collecting data from sensors

[0131] Multiple sensors installed in the vehicle collect real-time data such as heart rate, driving time, and road conditions, and this sensor data is sent to a server via the user's device.

[0132] Input: Data from heart rate sensors, driving time sensors, and road condition sensors

[0133] Output: Sensor data (e.g. heart rate 120 bpm, driving time 3 hours)

[0134] Specific operation: The heart rate sensor measures the driver's heart rate, and the driving time measurement sensor measures the driving time and sends the data to the user's device. The user's device then sends this data to the server.

[0135] Step 3:

[0136] Analysis of driver's driving state

[0137] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0138] Input: Audio feedback and sensor data sent from the user device

[0139] Output: Driver's driving state (e.g., "fatigue state")

[0140] Specific operation: The server analyzes the voice feedback and sensor data and obtains a judgment result of "fatigue state."

[0141] Step 4:

[0142] Proposal for transition to autonomous driving mode

[0143] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0144] Input: Driving state analysis results from the server (e.g., "fatigue state")

[0145] Output: Message (e.g. "We recommend switching to Autopilot mode")

[0146] Specific operation: The user device receives the analysis results from the server and displays a message suggesting switching to autonomous driving mode.

[0147] Step 5:

[0148] Providing information on safe driving

[0149] The server sends the analysis results to the generation AI model, which generates information about safe driving. The prompt sentence "Please generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is 3 hours or more" is input to the generation AI model. The generated information is sent to the user's device via the server and presented to the driver.

[0150] Input: Prompt sentence based on the analysis results (e.g., "Generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is more than 3 hours.")

[0151] Output: Safe driving information (e.g., "Keep the recommended speed at 60km / h and be sure to check for safety")

[0152] Specific operation: The server generates a prompt sentence and sends it to the generative AI model. When the generative AI model returns safe driving information, it is sent from the server to the user's device.

[0153] Step 6:

[0154] Communication with pedestrians during autonomous driving

[0155] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[0156] Input: Data based on vehicle position and situation (e.g., data on approaching a pedestrian crossing)

[0157] Output: Communication message (e.g. "Vehicle waiting to pass. Please wait.")

[0158] Specific operation: The server generates a message based on the vehicle's status data and announces it to the outside via the vehicle's speakers and display via the user's terminal.

[0159] Through the above processing, the system can appropriately evaluate the driver's driving condition in real time and immediately take necessary measures to improve the safety of both the driver and pedestrians.

[0160] (Application example 1)

[0161] 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."

[0162] Conventional autonomous vehicle systems are unable to accurately grasp the driver's driving condition or fatigue level, resulting in insufficient provision of appropriate advice for continuing safe driving or suggestions for switching to autonomous driving mode. Furthermore, there is a lack of means for achieving smooth communication with pedestrians in urban areas. To resolve these issues, there is a need for dynamic monitoring of driving conditions and real-time responses based on immediate analysis results.

[0163] 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.

[0164] In this invention, the server includes: means for collecting voice feedback from the user; means for acquiring data from multiple sensors installed in the vehicle; means for analyzing the collected voice feedback and sensor data to determine the driver's driving state; means for proposing transition to autonomous driving mode based on the driver's driving state; means for transmitting the analysis results to a generative AI model and generating information on safe driving; means for presenting the generated information on safe driving to the driver; means for generating a communication message for the pedestrian when the vehicle approaches a pedestrian and transmitting it to an external device; and means for monitoring the driving state in real time based on sensor data and displaying safe driving information on an in-vehicle terminal or head-mounted display when necessary. This allows the driver's state to be grasped in real time, and it is possible to propose transition to autonomous driving mode at the appropriate time and generate safe driving advice. It also enables smooth communication with pedestrians.

[0165] "Audio feedback" refers to information collected by the system based on the audio produced by the user.

[0166] "Sensors" are various measuring devices installed in vehicles that collect data such as heart rate, driving time, and road conditions.

[0167] A "generative AI model" is an artificial intelligence that generates information about safe driving based on a given prompt.

[0168] "Driver's driving state" refers to the driver's fatigue and stress level, which is obtained by analyzing collected voice feedback and sensor data.

[0169] "Autonomous driving mode" refers to a mode in which the system operates the vehicle on behalf of the driver.

[0170] "Communication messages" are messages that a vehicle transmits to pedestrians during autonomous driving, and are generated for safety and information purposes.

[0171] An "in-vehicle terminal" is an electronic device installed in a vehicle, and is a terminal for collecting voice feedback, displaying safe driving information, and the like.

[0172] A "head-mounted display" is an electronic device worn by the driver that displays information directly into their field of vision.

[0173] "Real-time" refers to the time concept in which systems and equipment instantly collect, analyze, and respond to information.

[0174] This invention is a system that evaluates the driving status of a driver of an autonomous vehicle in real time, and if necessary, suggests switching to autonomous driving mode, provides safe driving information, and also enables smooth communication with pedestrians. This system mainly includes the following components.

[0175] User Device

[0176] The user terminal is a device with voice recognition capabilities installed in the vehicle (e.g., an in-vehicle terminal or smartphone) that collects voice feedback from the driver in real time. This terminal converts the driver's utterances into text data and sends it to a server.

[0177] Multiple sensors installed in the vehicle

[0178] The sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. These sensors collect the driver's biometric information and driving environment data in real time and send it to a server via the user's terminal.

[0179] server

[0180] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. For example, if the driver says "I'm tired," has a high heart rate, and has been driving for a long time, the server will determine that the driver is fatigued.

[0181] Proposal for transition to autonomous driving mode

[0182] If the server analyzes the driver's driving condition and finds that the driver is fatigued or stressed, it will display a message on the user's device stating, "We recommend switching to autonomous driving mode."

[0183] Generate safe driving information

[0184] The server sends the analysis results to a generative AI model, which generates optimal advice on safe driving. For example, it generates information such as "Keep the recommended speed at 50 km / h and thoroughly check for safety" and displays it on the user's device. GPT-3 (registered trademark) and other AI models are used as generative models.

[0185] Communication with pedestrians

[0186] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message to inform the pedestrian, such as "A vehicle is waiting to pass. Please wait," and plays the message over the vehicle's speaker.

[0187] Real-time monitoring of sensor data

[0188] User terminals and head-mounted displays monitor driving conditions in real time based on sensor data and display safe driving information when necessary.

[0189] Specific examples

[0190] As a concrete example, a driver begins to feel fatigued after driving for a long period of time. The driver says, "I'm tired," and sensors measure a heart rate of 130 bpm and four hours of continuous driving. The server collects and analyzes this data and determines that the driver is fatigued. As a result, the device displays a message saying, "We recommend switching to autonomous driving mode," and at the same time, the generative AI model provides safe driving information such as, "Please maintain a recommended speed of 50 km / h and thoroughly check for safety." Then, when the vehicle approaches a pedestrian, a message is generated saying, "The vehicle is waiting to pass. Please wait," and this is announced through the vehicle's speaker.

[0191] Prompt Sentence Examples

[0192] "Provide safe driving advice to fatigued drivers."

[0193] "What is the best driving advice for tired drivers?"

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] The user's device collects the user's voice in real time. The collected voice feedback is converted into text data using a voice recognition function. The input is the user's voice feedback, and the output is text data. Specifically, the system captures voice using the vehicle's microphone and converts it into text using a voice recognition library (e.g., Google Speech-to-Text).

[0197] Step 2:

[0198] Sensors installed in the vehicle collect real-time data such as the driver's heart rate, driving time, and road conditions. The input is biometric information and driving environment data from each sensor, and the output is sensor data. Specifically, the system acquires data from the heart rate sensor and GPS and sends it to the user's device.

[0199] Step 3:

[0200] The user device sends collected voice feedback and sensor data to the server. The input is text data and sensor data, and the output is data transmission to the server. Specifically, data is sent from the device to the server using an HTTP request.

[0201] Step 4:

[0202] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. The input is the text data and sensor data sent to the server, and the output is the result of the driving state assessment. Specifically, the data is analyzed using a Python library (e.g., Pandas, NumPy) to determine the driving state as "fatigued" or "normal."

[0203] Step 5:

[0204] The server sends prompts to the generative AI model based on the driving state, generating information about safe driving. The input is the driving state assessment result, and the output is the generated safe driving advice. Specifically, the prompt sentence "Please tell me the best driving advice for a tired driver" is input to the generative AI model (e.g., GPT-3), which generates appropriate advice.

[0205] Step 6:

[0206] The generated safe driving information is sent to the user terminal and presented to the driver. The input is the generated safe driving advice, and the output is the display on the user terminal. Specifically, data is sent from the server to the user terminal, and a message is displayed on the terminal's display.

[0207] Step 7:

[0208] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message for the pedestrian. The input is vehicle position data and pedestrian detection data, and the output is the generated message. Specifically, the generative AI model generates the message "A vehicle is waiting to pass. Please wait."

[0209] Step 8:

[0210] The generated message is communicated to pedestrians through the in-car speaker or external display. The input is the generated message, and the output is the transmission of the message to pedestrians. The specific operation is to announce or display the message on the in-car speaker or external display.

[0211] 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.

[0212] The system based on this invention combines autonomous driving technology with an emotion engine that recognizes the user's emotions to more accurately evaluate the driver's driving state and suggest switching to autonomous driving mode as necessary. Furthermore, by taking the driver's emotional state into consideration when providing safe driving information, it is possible to provide appropriate and effective advice.

[0213] System Configuration

[0214] The system mainly consists of the following components:

[0215] User device (in-vehicle device or smartphone)

[0216] server

[0217] Multiple sensors installed in the vehicle

[0218] Emotion engine that recognizes user emotions

[0219] DETAILED DESCRIPTION OF THE INVENTION

[0220] Collecting voice feedback from users

[0221] The user device uses voice recognition to collect real-time voice feedback from the driver. For example, if the driver says, "I'm tired," this feedback is recorded as text data on the device. Data for recognizing emotions from the voice is also collected in parallel.

[0222] Collecting data from sensors

[0223] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[0224] Analysis of driver's driving state

[0225] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0226] Emotion recognition with emotion engine

[0227] The server uses an emotion engine to recognize emotions from the user's voice feedback, for example, assessing whether the driver is stressed or anxious through voice analysis.

[0228] Proposal for transition to autonomous driving mode

[0229] The user device will suggest switching to autonomous driving mode based on the driver's driving and emotional state analyzed by the server. Specifically, if the driver is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0230] Providing information on safe driving

[0231] The server sends the analysis results to the generative AI, which generates information on safe driving. For example, taking into account the driver's emotional state, the AI ​​generates information such as, "You seem tired. Please keep your speed at 60 km / h and make sure to check for safety." This information is then sent to the user's device and displayed to the driver.

[0232] Communication with pedestrians during autonomous driving

[0233] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[0234] The user device will announce this message to the outside via the vehicle's speakers and display.

[0235] Specific examples

[0236] Consider the following scenario as a concrete example: After driving for a long period of time, the driver begins to feel fatigued and stressed. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." Sensors measure a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state" and, based on the driver's voice, that they are feeling stressed. In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "You appear tired. Please maintain a speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[0237] In this way, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving condition and emotional state and taking necessary measures in real time.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[0241] Specifically, the device converts voice feedback such as "I'm tired" into text data and records it as "user feedback." In addition, the voice data is also saved and sent to the emotion engine.

[0242] Step 2:

[0243] The device collects data in real time from multiple sensors installed in the vehicle.

[0244] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[0245] Step 3:

[0246] The device sends the collected sensor data and user feedback to the server.

[0247] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[0248] Step 4:

[0249] The server analyzes the received data and determines the driver's driving condition.

[0250] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[0251] Step 5:

[0252] The server uses an emotion engine to recognize emotions from the user's voice.

[0253] Specifically, voice analysis technology is used to assess whether a driver is feeling stressed or anxious based on the voice saying "I'm tired."

[0254] Step 6:

[0255] The server sends the analysis results and emotion recognition results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[0256] Specifically, if the driver is determined to be in a "fatigued" and "stressed" state, a message stating "We recommend switching to autonomous driving mode" is generated and sent to the device.

[0257] Step 7:

[0258] The user terminal receives the message from the server and displays it to the driver.

[0259] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[0260] Step 8:

[0261] The server sends the sensor data and emotion recognition results to the generative AI, which then generates information about safe driving.

[0262] Specifically, safe driving information is generated such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety."

[0263] Step 9:

[0264] The user terminal presents the generated safe driving information to the driver.

[0265] Specifically, the device will display the message, "You appear to be tired. Please maintain a speed of 60 km / h and ensure safety."

[0266] Step 10:

[0267] The server generates the communication messages with pedestrians required during autonomous driving.

[0268] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[0269] Step 11:

[0270] The user terminal transmits the generated communication message to the pedestrian.

[0271] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[0272] Example 2

[0273] 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."

[0274] Conventional autonomous driving technology does not fully consider the driver's driving condition or emotional state, and therefore has the problem of not responding appropriately when the driver is fatigued or stressed. This can lead to reduced safety and increased driver burden, which is a problem.

[0275] 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.

[0276] In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors mounted on the vehicle, means for analyzing the collected voice feedback and sensor data to determine the driver's driving state and emotional state, means for proposing transition to autonomous driving mode based on the driver's driving state and emotional state, means for transmitting the analysis results to generative artificial intelligence and generating information on safe driving, means for presenting the generated information on safe driving to the driver, and means for generating communication messages with pedestrians during autonomous driving and transmitting them to outside the vehicle. This makes it possible to analyze the driver's driving state and emotional state in real time and provide appropriate autonomous driving suggestions and safe driving information.

[0277] "Voice feedback" refers to opinions or status reports provided by the user through voice.

[0278] A "sensor" is a device installed in a vehicle that detects and measures heart rate, driving time, road conditions, etc.

[0279] "Driving condition" refers to the state of a driver's physical and mental driving ability.

[0280] "Emotional state" indicates the driver's current emotions and stress level.

[0281] "Autonomous driving mode" refers to a driving mode in which the vehicle is automatically controlled and driven without driver intervention.

[0282] "Generative AI" refers to an AI technology that generates appropriate countermeasures and information based on analysis results.

[0283] "Safe driving information" refers to information that provides drivers with advice and recommended driving behaviors that they need to continue driving safely.

[0284] "Communication messages" are messages generated by autonomous vehicles to facilitate communication with pedestrians and other road users.

[0285] MODE FOR CARRYING OUT THE INVENTION

[0286] The system based on the present invention analyzes the driving and emotional state of the user and provides appropriate transition to autonomous driving mode and safe driving information. This system is composed of the following elements.

[0287] System Components

[0288] 1. User device: An in-vehicle device or smartphone is used. It is equipped with voice recognition functionality and is responsible for collecting voice feedback from the user.

[0289] 2. Server: Analyzes collected data and plays a central role in generating countermeasures and information using generative artificial intelligence.

[0290] 3. Sensors: Multiple sensors installed in the vehicle (heart rate sensors, driving time measurement sensors, road condition sensors, etc.) are used.

[0291] 4. Emotion engine: Used to analyze the user's emotional state.

[0292] Data collection and analysis

[0293] The user device uses voice recognition to collect the user's voice feedback in real time and convert it into text data. For example, imagine a situation where the user says "I'm tired." At the same time, data is also obtained from the voice data to analyze emotions.

[0294] The sensors collect real-time data such as heart rate, driving time, and road conditions, and transmit the data to a server via the user's device.

[0295] Data analysis and recommendations

[0296] The server analyzes the voice feedback and sensor data collected in real time to determine the driver's driving and emotional state. For example, if the voice feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigued."

[0297] Next, an emotion engine is used to analyze the user's emotional state from their voice data to determine whether they are stressed or not.

[0298] Providing information and suggesting autonomous driving modes

[0299] Based on the results of the analysis, the user's device will suggest switching to autonomous driving mode. For example, if the user is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0300] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, the server provides the generative AI with the following prompt:

[0301] "Generate a response when a driver expresses fatigue, their heart rate is over 120 bpm, and they've been driving for more than three hours."

[0302] "Please provide suggestions to drivers on how to drive safely if they are feeling fatigued."

[0303] The generated information is displayed on the user's device in the form of, for example, "You seem tired. Please maintain a speed of 60 km / h and make sure to check for safety."

[0304] Communication with pedestrians during autonomous driving

[0305] The server generates communication messages for pedestrians during autonomous driving. When the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the user's terminal using the vehicle's speakers and display.

[0306] In this way, the system comprehensively evaluates the user's driving and emotional state and provides appropriate responses in real time, thereby enhancing safety and comfort.

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] Detailed explanation of the processing steps

[0309] Step 1:

[0310] The user provides vocal feedback.

[0311] Specific operation: The user says "I'm tired." The device collects the voice feedback in real time and converts it into text data. At the same time, it performs preprocessing to analyze emotions from the voice data.

[0312] Input: User's voice feedback

[0313] Data processing: Preprocessing for speech-to-text conversion and sentiment analysis

[0314] Output: Preprocessing results of text data and emotion data

[0315] Step 2:

[0316] The terminal collects data in real time from multiple sensors installed in the vehicle.

[0317] Specific operation: The heart rate sensor measures 120 bpm, and the driving time sensor records the driving time for 3 hours. This data is collected on the user's device and sent to the server.

[0318] Input: Data from heart rate sensor and driving time measurement sensor

[0319] Data processing: Real-time data collection, data aggregation and transmission to the server

[0320] Output: Collected sensor data (heart rate and driving time)

[0321] Step 3:

[0322] The server receives and analyzes the audio feedback and sensor data.

[0323] Specific operation: The server analyzes the preprocessing results of the text data and emotion data, and integrates the heart rate data and driving time data. For example, if the text data is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigue state."

[0324] Input: Text data of voice feedback and collected sensor data

[0325] Data processing: Analysis of text data and sensor data

[0326] Output: Driver's driving condition (fatigue state)

[0327] Step 4:

[0328] The server uses an emotion engine to analyze the user's emotional state.

[0329] Specific operation: The server inputs the results of preprocessing the voice data into the emotion engine and analyzes emotional states such as stress and anxiety.

[0330] Input: Preprocessed audio data

[0331] Data processing: Emotion analysis using an emotion engine

[0332] Output: User's emotional state (e.g., stress state)

[0333] Step 5:

[0334] Based on the results of the analysis by the server, the device will suggest switching to autonomous driving mode.

[0335] Specific operation: If the driver is determined to be "fatigued" and "stressed," the device will display a message stating "We recommend switching to autonomous driving mode."

[0336] Input: Driver's driving and emotional state analyzed by the server

[0337] Output: Message proposing to switch to autonomous driving mode

[0338] Step 6:

[0339] The server sends the analysis results to the generative artificial intelligence, which generates information about safe driving.

[0340] Specific operation: The server inputs a prompt to the AI: "What to do if the driver says they are tired, their heart rate is over 120 bpm, and they have been driving for more than three hours." Based on this input, the AI ​​generates safe driving information such as, "Keep the speed at 60 km / h and make sure to check for safety."

[0341] Input: Prompt sentences based on the driver's driving and emotional state

[0342] Data Computation: Generating safe driving information using generative AI models

[0343] Output: Safe driving information

[0344] Step 7:

[0345] The terminal presents the generated safe driving information to the user.

[0346] Specific operation: The generated safe driving information is sent to the terminal, and the user is shown a message saying, "You seem tired. Please maintain a speed of 60 km / h and be thorough in checking for safety."

[0347] Input: Generated safe driving information

[0348] Output: Safe driving information presented to the user

[0349] Step 8:

[0350] The server generates communication messages with pedestrians during autonomous driving.

[0351] Specific operation: When a vehicle approaches a crosswalk, a message is generated stating "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the terminal using the in-car speaker or display.

[0352] Input: Vehicle position data and road condition data

[0353] Data calculation: Generating appropriate communication messages to pedestrians

[0354] Output: Communication message to pedestrians

[0355] (Application example 2)

[0356] 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."

[0357] As autonomous driving technology advances, there is a demand for improved safety that takes into account driver fatigue and emotional state. However, conventional autonomous driving systems are unable to consider the driver's emotional state, making it difficult to suggest transitioning to autonomous driving mode at the optimal time. This has resulted in a lack of systems that can reduce driver fatigue and stress and support safe driving.

[0358] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors installed in the vehicle, means for analyzing the collected voice feedback and sensor data and determining the driver's driving state, means for suggesting transition to autonomous driving mode based on the driver's driving state, means for transmitting the analysis results to a generative AI and generating information on safe driving, means for presenting the generated information on safe driving to the driver, means for generating communication messages with pedestrians during autonomous driving and transmitting them to the outside of the vehicle, means for recognizing the driver's voice feedback and emotional state in real time via a smartphone terminal, and means for providing appropriate advice to the driver based on the emotion recognition results. This enables appropriate suggestions for autonomous driving mode taking the driver's emotional state into consideration and support for safe driving.

[0359] "User voice feedback" refers to voice information provided by the driver through a device such as an in-car terminal or smartphone.

[0360] "Multiple sensors installed in a vehicle" refers to various sensors (e.g., heart rate sensors, driving time measurement sensors, road condition sensors, etc.) installed to grasp the situation inside and outside the vehicle.

[0361] "Collected audio feedback and sensor data" refers to the driver's audio feedback and data acquired by multiple sensors.

[0362] "Means for determining the driver's driving state" refers to a method or technology for evaluating and determining the driver's driving state (e.g., fatigue, decreased attention, etc.) based on collected voice feedback and sensor data.

[0363] "Means for proposing transition to automated driving mode" refers to a method or technology that recommends or notifies the driver to switch to automated driving mode based on the determined driving state of the driver.

[0364] "Generative AI" refers to a system or technology that uses artificial intelligence to automatically generate specific information (in this case, information about safe driving) from analysis results.

[0365] "Information regarding safe driving" refers to advice and warnings to assist drivers in safe driving (for example, recommended speeds, safety check methods, etc.).

[0366] The "means for recognizing driver's voice feedback and emotional state in real time via a smartphone device" refers to a technology that uses a smartphone device to receive the driver's voice input in real time, analyzes it, and recognizes the driver's emotional state.

[0367] "Means for generating communication messages with pedestrians during autonomous driving and transmitting them outside the vehicle" refers to technology that creates messages for smooth communication with pedestrians during autonomous driving and transmits them to pedestrians through appropriate means (for example, on-board speakers or displays).

[0368] MODE FOR CARRYING OUT THE INVENTION

[0369] The system based on the present invention combines autonomous driving technology with an emotion recognition engine to evaluate the driving condition and emotional state of the driver, and then transitions to autonomous driving mode and provides advice on safe driving. Specific embodiments are described below.

[0370] System Configuration

[0371] The system consists of the following main components:

[0372] 1. User device (smartphone or in-car device)

[0373] 2. Server

[0374] 3. Multiple sensors installed on the vehicle

[0375] 4. Emotion Recognition Engine

[0376] User Device

[0377] The user device is a smartphone or in-car device equipped with a voice recognition function. Speech recognition is performed using the speech_recognition library and the Google Speech Recognition API, which allows the driver's voice feedback to be collected in real time.

[0378] server

[0379] The server has the following features:

[0380] Analysis of collected audio feedback and sensor data

[0381] Determining the driver's driving and emotional state

[0382] Generating safe driving information using generative AI

[0383] Drive suggests transitioning to autonomous driving mode based on driving and emotional state

[0384] Generating communication messages with pedestrians during autonomous driving

[0385] Multiple sensors installed in the vehicle

[0386] The vehicle is equipped with sensors such as a heart rate sensor, a driving time measurement sensor, and a road condition sensor, which collect data in real time and transmit it to a server via the user's terminal.

[0387] Emotion Recognition Engine

[0388] The emotion recognition engine analyzes voice feedback from the user and recognizes the driver's emotional state (e.g., stress, anxiety, fatigue, etc.), and provides appropriate advice to the driver.

[0389] Specific operation example

[0390] For example, suppose a driver begins to feel fatigued or stressed after driving for a long period of time. At this point, the driver provides verbal feedback to the device, saying, "I'm tired." Sensors installed in the vehicle measure a heart rate of 120 bpm and driving time of three hours. This data is sent to the server in real time, and the server determines the driver's state as "fatigued."

[0391] Next, the emotion recognition engine analyzes the voice data and determines that the driver is feeling stressed. Based on this, the server notifies the user's device, "We recommend switching to autonomous driving mode." The generative AI also generates safe driving information to the driver, such as "You seem tired. Please maintain a speed of 60 km / h and thoroughly check for safety." After that, the system switches to autonomous driving mode, and when the vehicle approaches a pedestrian crossing, a message is generated and announced to pedestrians, saying, "A vehicle is waiting to pass. Please wait."

[0392] The above procedure makes it possible to provide safe driving assistance that takes into account the driver's driving condition and emotional state.

[0393] Prompt Sentence Examples

[0394] To illustrate, consider the following scenario:

[0395] User: While driving, say "I'm tired"

[0396] System: Emotion analysis determines "fatigue state" and notifies "We recommend switching to autonomous driving mode"

[0397] In this way, the system of the present invention provides appropriate responses based on the driver's real-time emotional and driving state, thereby improving safety.

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] The user device collects the driver's voice feedback. Specifically, it uses the speech_recognition library and the Google Speech Recognition API to obtain voice input as text data. This process takes voice data as input and obtains text data as output.

[0401] Step 2:

[0402] Multiple sensors installed in the vehicle collect data such as heart rate, driving time, and road conditions in real time and send it to a server via the user's terminal. The input is real-time data obtained from the sensors, and the output is data sent to the server.

[0403] Step 3:

[0404] The server analyzes the collected voice feedback and sensor data to determine the driver's driving state. Here, the voice data is analyzed using an emotion recognition engine to identify the driver's emotional state. The server also uses sensor data to determine the driver's "fatigue level" and other driving conditions based on heart rate and driving time. The input is the voice feedback and sensor data, and the output is the analysis results.

[0405] Step 4:

[0406] The server suggests switching to autonomous driving mode based on the driver's driving condition and emotional state. For example, if the driver is "fatigued" and "stressed," it generates a message saying "We recommend switching to autonomous driving mode" and sends it to the user's device. The input is the analysis result (driving condition and emotional state), and the output is a suggestion message.

[0407] Step 5:

[0408] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates specific advice such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety." The input is the analysis results, and the output is the generated safe driving information.

[0409] Step 6:

[0410] The user device presents the generated safe driving information to the driver. The device communicates the information to the driver using a screen display or audio output. The input is the safe driving information, and the output is a notification or display to the driver.

[0411] Step 7:

[0412] The server generates communication messages for pedestrians during autonomous driving and transmits them outside the vehicle. For example, when approaching a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait," and transmits it through the vehicle's speaker and display. The input is the vehicle's location and situation, and the output is a message to pedestrians.

[0413] The above processing steps realize an automated driving assistance system that takes into account the driver's driving state and emotional state.

[0414] 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.

[0415] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0416] 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.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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."

[0430] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[0431] System Configuration

[0432] The system mainly consists of the following components:

[0433] User device (in-vehicle device or smartphone)

[0434] server

[0435] Multiple sensors installed in the vehicle

[0436] DETAILED DESCRIPTION OF THE INVENTION

[0437] Collecting voice feedback from users

[0438] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," this feedback is recorded as text data on the device.

[0439] Collecting data from sensors

[0440] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[0441] Analysis of driver's driving state

[0442] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0443] Proposal for transition to autonomous driving mode

[0444] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0445] Providing information about safe driving

[0446] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates information such as "Keep the recommended speed at 60 km / h and make sure to check for safety," which is then sent to the user's device and displayed to the driver.

[0447] Communication with pedestrians during autonomous driving

[0448] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[0449] The user device will announce this message to the outside via the vehicle's speakers and display.

[0450] Specific examples

[0451] Consider the following scenario as a concrete example: A driver begins to feel fatigued after driving for a long period of time. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." A sensor measures a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "Please maintain a recommended speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and gains the understanding of pedestrians.

[0452] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[0453] The processing flow will be explained below.

[0454] Step 1:

[0455] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[0456] Specifically, the terminal converts voice feedback such as "I'm tired" into text data and records this as "user feedback."

[0457] Step 2:

[0458] The device collects data in real time from multiple sensors installed in the vehicle.

[0459] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[0460] Step 3:

[0461] The device sends the collected sensor data and user feedback to the server.

[0462] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[0463] Step 4:

[0464] The server analyzes the received data and determines the driver's driving condition.

[0465] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[0466] Step 5:

[0467] The server sends the analysis results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[0468] Specifically, if the server determines that the driver is in a "fatigue state," it generates a message stating, "We recommend switching to autonomous driving mode," and sends it to the device.

[0469] Step 6:

[0470] The user terminal receives the message from the server and displays it to the driver.

[0471] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[0472] Step 7:

[0473] The server sends the sensor data to the generative AI, which generates information about safe driving.

[0474] Specifically, it generates safe driving information such as "Keep the recommended speed at 60 km / h and make sure to check for safety."

[0475] Step 8:

[0476] The user terminal presents the generated safe driving information to the driver.

[0477] Specifically, the device will display the message, "Please maintain a recommended speed of 60 km / h and ensure safety."

[0478] Step 9:

[0479] The server generates the communication messages with pedestrians required during autonomous driving.

[0480] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[0481] Step 10:

[0482] The user terminal transmits the generated communication message to the pedestrian.

[0483] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[0484] Example 1

[0485] 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."

[0486] Advances in autonomous driving technology are expected to reduce driver burden and prevent accidents, but current systems have difficulty properly assessing the driver's driving state in real time and taking the necessary action immediately. Furthermore, there is a lack of communication with pedestrians, leaving challenges in improving safety and ensuring social acceptance. There is a need to solve these problems and provide safer, more effective autonomous driving systems.

[0487] 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.

[0488] In this invention, the server includes a means for collecting voice feedback from the user in real time, a means for acquiring data in real time from multiple sensors mounted on the vehicle, and a means for analyzing and determining the driver's driving state based on the collected voice feedback and sensor data. This makes it possible to appropriately evaluate the driver's driving state in real time, suggest transitioning to autonomous driving mode, provide safe driving information, and smoothly communicate with pedestrians.

[0489] "Voice feedback from the user" refers to feedback entered by the user through an in-car terminal or smartphone, and is a means of obtaining the driver's condition and emotions in real time.

[0490] "Multiple sensors" refers to a diverse group of sensors installed in the vehicle, such as heart rate sensors, driving time measurement sensors, and road condition sensors, which are devices that collect driver biometric information and road environment information in real time.

[0491] "Voice recognition function" is a technology that converts voice data into text data and is used to accurately analyze the driver's voice feedback.

[0492] "Means for analyzing and judging the driver's driving condition" refers to the system's function of analyzing the driver's driving situation based on collected voice feedback and sensor data, and evaluating and judging that condition.

[0493] "Means for suggesting transition to autonomous driving mode" refers to the system's function of providing a message to the driver to recommend switching to autonomous driving mode based on the analysis results.

[0494] A "generative AI model" is an artificial intelligence model that generates appropriate safe driving information based on analysis results, and provides safe driving instructions and advice using prompt text as input.

[0495] "Information about safe driving" is information generated by a generative AI model to support safe driving, such as recommended driving speeds for drivers and methods for ensuring safety.

[0496] "Communication messages with pedestrians during autonomous driving" are messages generated by autonomous vehicles to enable smooth interactions with pedestrians, including messages explaining the vehicle's behavior and warning pedestrians.

[0497] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[0498] System Configuration

[0499] The system mainly consists of the following components:

[0500] User device (in-vehicle device or smartphone)

[0501] server

[0502] Multiple sensors installed in the vehicle

[0503] Collecting voice feedback from users

[0504] The user device uses a voice recognition function (such as Google Assistant or Amazon Alexa) to collect the driver's voice feedback in real time. For example, if a driver feels tired after driving for a long time and says "I'm tired," the voice data is sent to the device and converted into text data by the voice recognition function. This text data is then sent directly to the server.

[0505] Collecting data from sensors

[0506] The vehicle is equipped with multiple sensors, including a heart rate sensor, a driving time measurement sensor, and a road condition sensor. These sensors collect data in real time and send it to a server via the user's device. For example, the heart rate sensor measures the driver's heart rate as 120 bpm, and the driving time measurement sensor measures the driving time as 3 hours.

[0507] Analysis of driver's driving state

[0508] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, based on voice feedback such as "I'm tired," a heart rate of 120 bpm, and driving time of more than three hours, the server will determine the driver's condition as "fatigue." To do this, it uses data processing algorithms and machine learning models.

[0509] Proposal for transition to autonomous driving mode

[0510] The user device will suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the message "We recommend switching to autonomous driving mode" will be displayed on the user device. This is an important step to maintain safety and comfort.

[0511] Providing information about safe driving

[0512] The server sends the analysis results to a generative AI model (such as OpenAI's GPT model) to generate information about safe driving. Safe driving information is obtained by inputting specific prompts into the generative AI model. For example, the prompt might read, "Please generate appropriate safe driving information if your heart rate is 120 bpm and your driving time is more than three hours." Based on this prompt, the generative AI model generates information such as, "Keep the recommended speed at 60 km / h and ensure thorough safety checks." This information is sent to the user's device via the server and presented to the driver.

[0513] Communication with pedestrians during autonomous driving

[0514] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[0515] Specific examples

[0516] As a concrete example, consider the following scenario. A driver feels tired after driving for a long time and utters, "I'm tired." This feedback is converted to text on the user's device and sent to the server. At the same time, the heart rate sensor measures a heart rate of 120 bpm and the driving time sensor measures three hours of driving time. These data are sent to the server, and analysis results indicate a "fatigue state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." The generative AI model also receives a prompt: "If your heart rate is 120 bpm and you have been driving for more than three hours, please generate appropriate safe driving information." This information is then displayed on the user's device. The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[0517] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[0518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0519] Step 1:

[0520] Collecting voice feedback from users

[0521] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," the voice data is input into the device. The device converts this voice data into text data and sends it to the server.

[0522] Input: Driver's voice feedback (e.g., "I'm tired")

[0523] Output: Converted text data (e.g. "Tired")

[0524] Specific operation: The driver says, "I'm tired." The user device uses its voice recognition function to convert the speech into text and send it to the server.

[0525] Step 2:

[0526] Collecting data from sensors

[0527] Multiple sensors installed in the vehicle collect real-time data such as heart rate, driving time, and road conditions, and this sensor data is sent to a server via the user's device.

[0528] Input: Data from heart rate sensors, driving time sensors, and road condition sensors

[0529] Output: Sensor data (e.g. heart rate 120 bpm, driving time 3 hours)

[0530] Specific operation: The heart rate sensor measures the driver's heart rate, and the driving time measurement sensor measures the driving time and sends the data to the user's device. The user's device then sends this data to the server.

[0531] Step 3:

[0532] Analysis of driver's driving state

[0533] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0534] Input: Audio feedback and sensor data sent from the user device

[0535] Output: Driver's driving state (e.g., "fatigue state")

[0536] Specific operation: The server analyzes the voice feedback and sensor data and obtains a judgment result of "fatigue state."

[0537] Step 4:

[0538] Proposal for transition to autonomous driving mode

[0539] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0540] Input: Driving state analysis results from the server (e.g., "fatigue state")

[0541] Output: Message (e.g. "We recommend switching to Autopilot mode")

[0542] Specific operation: The user device receives the analysis results from the server and displays a message suggesting switching to autonomous driving mode.

[0543] Step 5:

[0544] Providing information about safe driving

[0545] The server sends the analysis results to the generation AI model, which generates information about safe driving. The prompt sentence "Please generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is 3 hours or more" is input to the generation AI model. The generated information is sent to the user's device via the server and presented to the driver.

[0546] Input: Prompt sentence based on the analysis results (e.g., "Generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is more than 3 hours.")

[0547] Output: Safe driving information (e.g., "Keep the recommended speed at 60km / h and be sure to check for safety")

[0548] Specific operation: The server generates a prompt sentence and sends it to the generative AI model. When the generative AI model returns safe driving information, it is sent from the server to the user's device.

[0549] Step 6:

[0550] Communication with pedestrians during autonomous driving

[0551] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[0552] Input: Data based on vehicle position and situation (e.g., data on approaching a pedestrian crossing)

[0553] Output: Communication message (e.g. "Vehicle waiting to pass. Please wait.")

[0554] Specific operation: The server generates a message based on the vehicle's status data and announces it to the outside via the vehicle's speakers and display via the user's terminal.

[0555] Through the above processing, the system can appropriately evaluate the driver's driving condition in real time and immediately take necessary measures to improve the safety of both the driver and pedestrians.

[0556] (Application example 1)

[0557] 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."

[0558] Conventional autonomous vehicle systems are unable to accurately grasp the driver's driving condition or fatigue level, resulting in insufficient provision of appropriate advice for continuing safe driving or suggestions for switching to autonomous driving mode. Furthermore, there is a lack of means for achieving smooth communication with pedestrians in urban areas. To resolve these issues, there is a need for dynamic monitoring of driving conditions and real-time responses based on immediate analysis results.

[0559] 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.

[0560] In this invention, the server includes: means for collecting voice feedback from the user; means for acquiring data from multiple sensors installed in the vehicle; means for analyzing the collected voice feedback and sensor data to determine the driver's driving state; means for proposing transition to autonomous driving mode based on the driver's driving state; means for transmitting the analysis results to a generative AI model and generating information on safe driving; means for presenting the generated information on safe driving to the driver; means for generating a communication message for the pedestrian when the vehicle approaches a pedestrian and transmitting it to an external device; and means for monitoring the driving state in real time based on sensor data and displaying safe driving information on an in-vehicle terminal or head-mounted display when necessary. This allows the driver's state to be grasped in real time, and it is possible to propose transition to autonomous driving mode at the appropriate time and generate safe driving advice. It also enables smooth communication with pedestrians.

[0561] "Audio feedback" refers to information collected by the system based on the audio produced by the user.

[0562] "Sensors" are various measuring devices installed in vehicles that collect data such as heart rate, driving time, and road conditions.

[0563] A "generative AI model" is an artificial intelligence that generates information about safe driving based on a given prompt.

[0564] "Driver's driving state" refers to the driver's fatigue and stress level, which is obtained by analyzing collected voice feedback and sensor data.

[0565] "Autonomous driving mode" refers to a mode in which the system operates the vehicle on behalf of the driver.

[0566] "Communication messages" are messages that a vehicle transmits to pedestrians during autonomous driving, and are generated for safety and information purposes.

[0567] An "in-vehicle terminal" is an electronic device installed in a vehicle, and is a terminal for collecting voice feedback, displaying safe driving information, and the like.

[0568] A "head-mounted display" is an electronic device worn by the driver that displays information directly into their field of vision.

[0569] "Real-time" refers to the time concept in which systems and equipment instantly collect, analyze, and respond to information.

[0570] This invention is a system that evaluates the driving status of a driver of an autonomous vehicle in real time, and if necessary, suggests switching to autonomous driving mode, provides safe driving information, and also enables smooth communication with pedestrians. This system mainly includes the following components.

[0571] User Device

[0572] The user terminal is a device with voice recognition capabilities installed in the vehicle (e.g., an in-vehicle terminal or smartphone) that collects voice feedback from the driver in real time. This terminal converts the driver's utterances into text data and sends it to a server.

[0573] Multiple sensors installed in the vehicle

[0574] The sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. These sensors collect the driver's biometric information and driving environment data in real time and send it to a server via the user's terminal.

[0575] server

[0576] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. For example, if the driver says "I'm tired," has a high heart rate, and has been driving for a long time, the server will determine that the driver is fatigued.

[0577] Proposal for transition to autonomous driving mode

[0578] If the server analyzes the driver's driving condition and finds that the driver is fatigued or stressed, it will display a message on the user's device stating, "We recommend switching to autonomous driving mode."

[0579] Generate safe driving information

[0580] The server sends the analysis results to a generative AI model, which generates optimal advice on safe driving. For example, it generates information such as "Keep the recommended speed at 50 km / h and thoroughly check for safety" and displays it on the user's device. GPT-3 and other models are used as generative AI models.

[0581] Communication with pedestrians

[0582] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message to inform the pedestrian, such as "A vehicle is waiting to pass. Please wait," and plays the message over the vehicle's speaker.

[0583] Real-time monitoring of sensor data

[0584] User devices and head-mounted displays monitor driving conditions in real time based on sensor data and display safe driving information when necessary.

[0585] Specific examples

[0586] As a concrete example, a driver begins to feel fatigued after driving for a long period of time. The driver says, "I'm tired," and sensors measure a heart rate of 130 bpm and four hours of continuous driving. The server collects and analyzes this data and determines that the driver is fatigued. As a result, the device displays a message saying, "We recommend switching to autonomous driving mode," and at the same time, the generative AI model provides safe driving information such as, "Please maintain a recommended speed of 50 km / h and thoroughly check for safety." Then, when the vehicle approaches a pedestrian, a message is generated saying, "The vehicle is waiting to pass. Please wait," and this is announced through the vehicle's speaker.

[0587] Prompt Sentence Examples

[0588] "Provide safe driving advice to fatigued drivers."

[0589] "What is the best driving advice for tired drivers?"

[0590] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0591] Step 1:

[0592] The user's device collects the user's voice in real time. The collected voice feedback is converted into text data using a voice recognition function. The input is the user's voice feedback, and the output is text data. Specifically, the system captures voice using the vehicle's microphone and converts it into text using a voice recognition library (e.g., Google Speech-to-Text).

[0593] Step 2:

[0594] Sensors installed in the vehicle collect real-time data such as the driver's heart rate, driving time, and road conditions. The input is biometric information and driving environment data from each sensor, and the output is sensor data. Specifically, the system acquires data from the heart rate sensor and GPS and sends it to the user's device.

[0595] Step 3:

[0596] The user device sends collected voice feedback and sensor data to the server. The input is text data and sensor data, and the output is data transmission to the server. Specifically, data is sent from the device to the server using an HTTP request.

[0597] Step 4:

[0598] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. The input is the text data and sensor data sent to the server, and the output is the result of the driving state assessment. Specifically, the data is analyzed using a Python library (e.g., Pandas, NumPy) to determine the driving state as "fatigued" or "normal."

[0599] Step 5:

[0600] The server sends prompts to the generative AI model based on the driving state, generating information about safe driving. The input is the driving state assessment result, and the output is the generated safe driving advice. Specifically, the prompt sentence "Please tell me the best driving advice for a tired driver" is input to the generative AI model (e.g., GPT-3), which generates appropriate advice.

[0601] Step 6:

[0602] The generated safe driving information is sent to the user terminal and presented to the driver. The input is the generated safe driving advice, and the output is the display on the user terminal. Specifically, data is sent from the server to the user terminal, and a message is displayed on the terminal's display.

[0603] Step 7:

[0604] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message for the pedestrian. The input is vehicle position data and pedestrian detection data, and the output is the generated message. Specifically, the generative AI model generates the message "A vehicle is waiting to pass. Please wait."

[0605] Step 8:

[0606] The generated message is communicated to pedestrians through the in-car speaker or external display. The input is the generated message, and the output is the transmission of the message to pedestrians. The specific operation is to announce or display the message on the in-car speaker or external display.

[0607] 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.

[0608] The system based on this invention combines autonomous driving technology with an emotion engine that recognizes the user's emotions to more accurately evaluate the driver's driving state and suggest switching to autonomous driving mode as necessary. Furthermore, by taking the driver's emotional state into consideration when providing safe driving information, it is possible to provide appropriate and effective advice.

[0609] System Configuration

[0610] The system mainly consists of the following components:

[0611] User device (in-vehicle device or smartphone)

[0612] server

[0613] Multiple sensors installed in the vehicle

[0614] Emotion engine that recognizes user emotions

[0615] DETAILED DESCRIPTION OF THE INVENTION

[0616] Collecting voice feedback from users

[0617] The user device uses voice recognition to collect real-time voice feedback from the driver. For example, if the driver says, "I'm tired," this feedback is recorded as text data on the device. Data for recognizing emotions from the voice is also collected in parallel.

[0618] Collecting data from sensors

[0619] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[0620] Analysis of driver's driving state

[0621] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0622] Emotion recognition with emotion engine

[0623] The server uses an emotion engine to recognize emotions from the user's voice feedback, for example, assessing whether the driver is stressed or anxious through voice analysis.

[0624] Proposal for transition to autonomous driving mode

[0625] The user device will suggest switching to autonomous driving mode based on the driver's driving and emotional state analyzed by the server. Specifically, if the driver is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0626] Providing information on safe driving

[0627] The server sends the analysis results to the generative AI, which generates information on safe driving. For example, taking into account the driver's emotional state, the AI ​​generates information such as, "You seem tired. Please keep your speed at 60 km / h and make sure to check for safety." This information is then sent to the user's device and displayed to the driver.

[0628] Communication with pedestrians during autonomous driving

[0629] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[0630] The user device will announce this message to the outside via the vehicle's speakers and display.

[0631] Specific examples

[0632] Consider the following scenario as a concrete example: After driving for a long period of time, the driver begins to feel fatigued and stressed. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." Sensors measure a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state" and, based on the driver's voice, that they are feeling stressed. In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "You appear tired. Please maintain a speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[0633] In this way, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving condition and emotional state and taking necessary measures in real time.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[0637] Specifically, the device converts voice feedback such as "I'm tired" into text data and records it as "user feedback." In addition, the voice data is also saved and sent to the emotion engine.

[0638] Step 2:

[0639] The device collects data in real time from multiple sensors installed in the vehicle.

[0640] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[0641] Step 3:

[0642] The device sends the collected sensor data and user feedback to the server.

[0643] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[0644] Step 4:

[0645] The server analyzes the received data and determines the driver's driving condition.

[0646] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[0647] Step 5:

[0648] The server uses an emotion engine to recognize emotions from the user's voice.

[0649] Specifically, voice analysis technology is used to assess whether a driver is feeling stressed or anxious based on the voice saying "I'm tired."

[0650] Step 6:

[0651] The server sends the analysis results and emotion recognition results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[0652] Specifically, if the driver is determined to be in a "fatigued" and "stressed" state, a message stating "We recommend switching to autonomous driving mode" is generated and sent to the device.

[0653] Step 7:

[0654] The user terminal receives the message from the server and displays it to the driver.

[0655] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[0656] Step 8:

[0657] The server sends the sensor data and emotion recognition results to the generative AI, which then generates information about safe driving.

[0658] Specifically, safe driving information is generated such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety."

[0659] Step 9:

[0660] The user terminal presents the generated safe driving information to the driver.

[0661] Specifically, the device will display the message, "You appear to be tired. Please maintain a speed of 60 km / h and ensure safety."

[0662] Step 10:

[0663] The server generates the communication messages with pedestrians required during autonomous driving.

[0664] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[0665] Step 11:

[0666] The user terminal transmits the generated communication message to the pedestrian.

[0667] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[0668] Example 2

[0669] 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."

[0670] Conventional autonomous driving technology does not fully consider the driver's driving condition or emotional state, and therefore has the problem of not responding appropriately when the driver is fatigued or stressed. This can lead to reduced safety and increased driver burden, which is a problem.

[0671] 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.

[0672] In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors mounted on the vehicle, means for analyzing the collected voice feedback and sensor data to determine the driver's driving state and emotional state, means for proposing transition to autonomous driving mode based on the driver's driving state and emotional state, means for transmitting the analysis results to generative artificial intelligence and generating information on safe driving, means for presenting the generated information on safe driving to the driver, and means for generating communication messages with pedestrians during autonomous driving and transmitting them to outside the vehicle. This makes it possible to analyze the driver's driving state and emotional state in real time and provide appropriate autonomous driving suggestions and safe driving information.

[0673] "Voice feedback" refers to opinions or status reports provided by the user through voice.

[0674] A "sensor" is a device installed in a vehicle that detects and measures heart rate, driving time, road conditions, etc.

[0675] "Driving condition" refers to the state of a driver's physical and mental driving ability.

[0676] "Emotional state" indicates the driver's current emotions and stress level.

[0677] "Autonomous driving mode" refers to a driving mode in which the vehicle is automatically controlled and driven without driver intervention.

[0678] "Generative AI" refers to an AI technology that generates appropriate countermeasures and information based on analysis results.

[0679] "Safe driving information" refers to information that provides drivers with advice and recommended driving behaviors that they need to continue driving safely.

[0680] "Communication messages" are messages generated by autonomous vehicles to facilitate communication with pedestrians and other road users.

[0681] MODE FOR CARRYING OUT THE INVENTION

[0682] The system based on the present invention analyzes the driving and emotional state of the user and provides appropriate transition to autonomous driving mode and safe driving information. This system is composed of the following elements.

[0683] System Components

[0684] 1. User device: An in-vehicle device or smartphone is used. It is equipped with voice recognition functionality and is responsible for collecting voice feedback from the user.

[0685] 2. Server: Analyzes collected data and plays a central role in generating countermeasures and information using generative artificial intelligence.

[0686] 3. Sensors: Multiple sensors installed in the vehicle (heart rate sensors, driving time measurement sensors, road condition sensors, etc.) are used.

[0687] 4. Emotion engine: Used to analyze the user's emotional state.

[0688] Data collection and analysis

[0689] The user device uses voice recognition to collect the user's voice feedback in real time and convert it into text data. For example, imagine a situation where the user says "I'm tired." At the same time, data is also obtained from the voice data to analyze emotions.

[0690] The sensors collect real-time data such as heart rate, driving time, and road conditions, and transmit the data to a server via the user's device.

[0691] Data analysis and recommendations

[0692] The server analyzes the voice feedback and sensor data collected in real time to determine the driver's driving and emotional state. For example, if the voice feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigued."

[0693] Next, an emotion engine is used to analyze the user's emotional state from their voice data to determine whether they are stressed or not.

[0694] Providing information and suggesting autonomous driving modes

[0695] Based on the results of the analysis, the user's device will suggest switching to autonomous driving mode. For example, if the user is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0696] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, the server provides the generative AI with the following prompt:

[0697] "Generate a response when a driver expresses fatigue, their heart rate is over 120 bpm, and they've been driving for more than three hours."

[0698] "Please provide suggestions to drivers on how to drive safely if they are feeling fatigued."

[0699] The generated information is displayed on the user's device in the form of, for example, "You seem tired. Please maintain a speed of 60 km / h and make sure to check for safety."

[0700] Communication with pedestrians during autonomous driving

[0701] The server generates communication messages for pedestrians during autonomous driving. When the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the user's terminal using the vehicle's speakers and display.

[0702] In this way, the system comprehensively evaluates the user's driving and emotional state and provides appropriate responses in real time, thereby enhancing safety and comfort.

[0703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0704] Detailed explanation of the processing steps

[0705] Step 1:

[0706] The user provides vocal feedback.

[0707] Specific operation: The user says "I'm tired." The device collects the voice feedback in real time and converts it into text data. At the same time, it performs preprocessing to analyze emotions from the voice data.

[0708] Input: User's voice feedback

[0709] Data processing: Preprocessing for speech-to-text conversion and sentiment analysis

[0710] Output: Preprocessing results of text data and emotion data

[0711] Step 2:

[0712] The terminal collects data in real time from multiple sensors installed in the vehicle.

[0713] Specific operation: The heart rate sensor measures 120 bpm, and the driving time sensor records the driving time for 3 hours. This data is collected on the user's device and sent to the server.

[0714] Input: Data from heart rate sensor and driving time measurement sensor

[0715] Data processing: Real-time data collection, data aggregation and transmission to the server

[0716] Output: Collected sensor data (heart rate and driving time)

[0717] Step 3:

[0718] The server receives and analyzes the audio feedback and sensor data.

[0719] Specific operation: The server analyzes the preprocessing results of the text data and emotion data, and integrates the heart rate data and driving time data. For example, if the text data is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigue state."

[0720] Input: Text data of voice feedback and collected sensor data

[0721] Data processing: Analysis of text data and sensor data

[0722] Output: Driver's driving condition (fatigue state)

[0723] Step 4:

[0724] The server uses an emotion engine to analyze the user's emotional state.

[0725] Specific operation: The server inputs the results of preprocessing the voice data into the emotion engine and analyzes emotional states such as stress and anxiety.

[0726] Input: Preprocessed audio data

[0727] Data processing: Emotion analysis using an emotion engine

[0728] Output: User's emotional state (e.g., stress state)

[0729] Step 5:

[0730] Based on the results of the analysis by the server, the device will suggest switching to autonomous driving mode.

[0731] Specific operation: If the driver is determined to be "fatigued" and "stressed," the device will display a message stating "We recommend switching to autonomous driving mode."

[0732] Input: Driver's driving and emotional state analyzed by the server

[0733] Output: Message proposing to switch to autonomous driving mode

[0734] Step 6:

[0735] The server sends the analysis results to the generative artificial intelligence, which generates information about safe driving.

[0736] Specific operation: The server inputs a prompt to the AI: "What to do if the driver says they are tired, their heart rate is over 120 bpm, and they have been driving for more than three hours." Based on this input, the AI ​​generates safe driving information such as, "Keep the speed at 60 km / h and make sure to check for safety."

[0737] Input: Prompt sentences based on the driver's driving and emotional state

[0738] Data Computation: Generating safe driving information using generative AI models

[0739] Output: Safe driving information

[0740] Step 7:

[0741] The terminal presents the generated safe driving information to the user.

[0742] Specific operation: The generated safe driving information is sent to the terminal, and the user is shown a message saying, "You seem tired. Please maintain a speed of 60 km / h and be thorough in checking for safety."

[0743] Input: Generated safe driving information

[0744] Output: Safe driving information presented to the user

[0745] Step 8:

[0746] The server generates communication messages with pedestrians during autonomous driving.

[0747] Specific operation: When a vehicle approaches a crosswalk, a message is generated stating "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the terminal using the in-car speaker or display.

[0748] Input: Vehicle position data and road condition data

[0749] Data calculation: Generating appropriate communication messages to pedestrians

[0750] Output: Communication message to pedestrians

[0751] (Application example 2)

[0752] 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."

[0753] As autonomous driving technology advances, there is a demand for improved safety that takes into account driver fatigue and emotional state. However, conventional autonomous driving systems are unable to consider the driver's emotional state, making it difficult to suggest transitioning to autonomous driving mode at the optimal time. This has resulted in a lack of systems that can reduce driver fatigue and stress and support safe driving.

[0754] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors installed in the vehicle, means for analyzing the collected voice feedback and sensor data and determining the driver's driving state, means for suggesting transition to autonomous driving mode based on the driver's driving state, means for transmitting the analysis results to a generative AI and generating information on safe driving, means for presenting the generated information on safe driving to the driver, means for generating communication messages with pedestrians during autonomous driving and transmitting them to the outside of the vehicle, means for recognizing the driver's voice feedback and emotional state in real time via a smartphone terminal, and means for providing appropriate advice to the driver based on the emotion recognition results. This enables appropriate suggestions for autonomous driving mode taking the driver's emotional state into consideration and support for safe driving.

[0755] "User voice feedback" refers to voice information provided by the driver through a device such as an in-car terminal or smartphone.

[0756] "Multiple sensors installed in a vehicle" refers to various sensors (e.g., heart rate sensors, driving time measurement sensors, road condition sensors, etc.) installed to grasp the situation inside and outside the vehicle.

[0757] "Collected audio feedback and sensor data" refers to the driver's audio feedback and data acquired by multiple sensors.

[0758] "Means for determining the driver's driving state" refers to a method or technology for evaluating and determining the driver's driving state (e.g., fatigue, decreased attention, etc.) based on collected voice feedback and sensor data.

[0759] "Means for proposing transition to automated driving mode" refers to a method or technology that recommends or notifies the driver to switch to automated driving mode based on the determined driving state of the driver.

[0760] "Generative AI" refers to a system or technology that uses artificial intelligence to automatically generate specific information (in this case, information about safe driving) from analysis results.

[0761] "Information regarding safe driving" refers to advice and warnings to assist drivers in safe driving (for example, recommended speeds, safety check methods, etc.).

[0762] The "means for recognizing driver's voice feedback and emotional state in real time via a smartphone device" refers to a technology that uses a smartphone device to receive the driver's voice input in real time, analyzes it, and recognizes the driver's emotional state.

[0763] "Means for generating communication messages with pedestrians during autonomous driving and transmitting them outside the vehicle" refers to technology that creates messages for smooth communication with pedestrians during autonomous driving and transmits them to pedestrians through appropriate means (for example, on-board speakers or displays).

[0764] MODE FOR CARRYING OUT THE INVENTION

[0765] The system based on the present invention combines autonomous driving technology with an emotion recognition engine to evaluate the driving condition and emotional state of the driver, and then transitions to autonomous driving mode and provides advice on safe driving. Specific embodiments are described below.

[0766] System Configuration

[0767] The system consists of the following main components:

[0768] 1. User device (smartphone or in-car device)

[0769] 2. Server

[0770] 3. Multiple sensors installed on the vehicle

[0771] 4. Emotion Recognition Engine

[0772] User Device

[0773] The user device is a smartphone or in-car device equipped with a voice recognition function. Speech recognition is performed using the speech_recognition library and the Google Speech Recognition API, which allows the driver's voice feedback to be collected in real time.

[0774] server

[0775] The server has the following features:

[0776] Analysis of collected audio feedback and sensor data

[0777] Determining the driver's driving and emotional state

[0778] Generating safe driving information using generative AI

[0779] Drive suggests transitioning to autonomous driving mode based on driving and emotional state

[0780] Generating communication messages with pedestrians during autonomous driving

[0781] Multiple sensors installed in the vehicle

[0782] The vehicle is equipped with sensors such as a heart rate sensor, a driving time measurement sensor, and a road condition sensor, which collect data in real time and transmit it to a server via the user's terminal.

[0783] Emotion Recognition Engine

[0784] The emotion recognition engine analyzes voice feedback from the user and recognizes the driver's emotional state (e.g., stress, anxiety, fatigue, etc.), and provides appropriate advice to the driver.

[0785] Specific operation example

[0786] For example, suppose a driver begins to feel fatigued or stressed after driving for a long period of time. At this point, the driver provides verbal feedback to the device, saying, "I'm tired." Sensors installed in the vehicle measure a heart rate of 120 bpm and driving time of three hours. This data is sent to the server in real time, and the server determines the driver's state as "fatigued."

[0787] Next, the emotion recognition engine analyzes the voice data and determines that the driver is feeling stressed. Based on this, the server notifies the user's device, "We recommend switching to autonomous driving mode." The generative AI also generates safe driving information to the driver, such as "You seem tired. Please maintain a speed of 60 km / h and thoroughly check for safety." After that, the system switches to autonomous driving mode, and when the vehicle approaches a pedestrian crossing, a message is generated and announced to pedestrians, saying, "A vehicle is waiting to pass. Please wait."

[0788] The above procedure makes it possible to provide safe driving assistance that takes into account the driver's driving condition and emotional state.

[0789] Prompt Sentence Examples

[0790] To illustrate, consider the following scenario:

[0791] User: While driving, say "I'm tired"

[0792] System: Emotion analysis determines "fatigue state" and notifies "We recommend switching to autonomous driving mode"

[0793] In this way, the system of the present invention provides appropriate responses based on the driver's real-time emotional and driving state, thereby improving safety.

[0794] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0795] Step 1:

[0796] The user device collects the driver's voice feedback. Specifically, it uses the speech_recognition library and the Google Speech Recognition API to obtain voice input as text data. This process takes voice data as input and obtains text data as output.

[0797] Step 2:

[0798] Multiple sensors installed in the vehicle collect data such as heart rate, driving time, and road conditions in real time and send it to a server via the user's terminal. The input is real-time data obtained from the sensors, and the output is data sent to the server.

[0799] Step 3:

[0800] The server analyzes the collected voice feedback and sensor data to determine the driver's driving state. Here, the voice data is analyzed using an emotion recognition engine to identify the driver's emotional state. The server also uses sensor data to determine the driver's "fatigue level" and other driving conditions based on heart rate and driving time. The input is the voice feedback and sensor data, and the output is the analysis results.

[0801] Step 4:

[0802] The server suggests switching to autonomous driving mode based on the driver's driving condition and emotional state. For example, if the driver is "fatigued" and "stressed," it generates a message saying "We recommend switching to autonomous driving mode" and sends it to the user's device. The input is the analysis result (driving condition and emotional state), and the output is a suggestion message.

[0803] Step 5:

[0804] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates specific advice such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety." The input is the analysis results, and the output is the generated safe driving information.

[0805] Step 6:

[0806] The user device presents the generated safe driving information to the driver. The device communicates the information to the driver using a screen display or audio output. The input is the safe driving information, and the output is a notification or display to the driver.

[0807] Step 7:

[0808] The server generates communication messages for pedestrians during autonomous driving and transmits them outside the vehicle. For example, when approaching a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait," and transmits it through the vehicle's speaker and display. The input is the vehicle's location and situation, and the output is a message to pedestrians.

[0809] The above processing steps realize an automated driving assistance system that takes into account the driver's driving state and emotional state.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] [Third embodiment]

[0814] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0815] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0816] 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).

[0817] 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.

[0818] 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.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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."

[0826] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[0827] System Configuration

[0828] The system mainly consists of the following components:

[0829] User device (in-vehicle device or smartphone)

[0830] server

[0831] Multiple sensors installed in the vehicle

[0832] DETAILED DESCRIPTION OF THE INVENTION

[0833] Collecting voice feedback from users

[0834] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," this feedback is recorded as text data on the device.

[0835] Collecting data from sensors

[0836] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[0837] Analysis of driver's driving state

[0838] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0839] Proposal for transition to autonomous driving mode

[0840] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0841] Providing information about safe driving

[0842] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates information such as "Keep the recommended speed at 60 km / h and make sure to check for safety," which is then sent to the user's device and displayed to the driver.

[0843] Communication with pedestrians during autonomous driving

[0844] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[0845] The user device will announce this message to the outside via the vehicle's speakers and display.

[0846] Specific examples

[0847] Consider the following scenario as a concrete example: A driver begins to feel fatigued after driving for a long period of time. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." A sensor measures a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "Please maintain a recommended speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and gains the understanding of pedestrians.

[0848] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[0849] The processing flow will be explained below.

[0850] Step 1:

[0851] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[0852] Specifically, the terminal converts voice feedback such as "I'm tired" into text data and records this as "user feedback."

[0853] Step 2:

[0854] The device collects data in real time from multiple sensors installed in the vehicle.

[0855] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[0856] Step 3:

[0857] The device sends the collected sensor data and user feedback to the server.

[0858] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[0859] Step 4:

[0860] The server analyzes the received data and determines the driver's driving condition.

[0861] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[0862] Step 5:

[0863] The server sends the analysis results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[0864] Specifically, if the server determines that the driver is in a "fatigue state," it generates a message stating, "We recommend switching to autonomous driving mode," and sends it to the device.

[0865] Step 6:

[0866] The user terminal receives the message from the server and displays it to the driver.

[0867] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[0868] Step 7:

[0869] The server sends the sensor data to the generative AI, which generates information about safe driving.

[0870] Specifically, it generates safe driving information such as "Keep the recommended speed at 60 km / h and make sure to check for safety."

[0871] Step 8:

[0872] The user terminal presents the generated safe driving information to the driver.

[0873] Specifically, the device will display the message, "Please maintain a recommended speed of 60 km / h and ensure safety."

[0874] Step 9:

[0875] The server generates the communication messages with pedestrians required during autonomous driving.

[0876] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[0877] Step 10:

[0878] The user terminal transmits the generated communication message to the pedestrian.

[0879] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[0880] Example 1

[0881] 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."

[0882] Advances in autonomous driving technology are expected to reduce driver burden and prevent accidents, but current systems have difficulty properly assessing the driver's driving state in real time and taking the necessary action immediately. Furthermore, there is a lack of communication with pedestrians, leaving challenges in improving safety and ensuring social acceptance. There is a need to solve these problems and provide safer, more effective autonomous driving systems.

[0883] 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.

[0884] In this invention, the server includes a means for collecting voice feedback from the user in real time, a means for acquiring data in real time from multiple sensors mounted on the vehicle, and a means for analyzing and determining the driver's driving state based on the collected voice feedback and sensor data. This makes it possible to appropriately evaluate the driver's driving state in real time, suggest transitioning to autonomous driving mode, provide safe driving information, and smoothly communicate with pedestrians.

[0885] "Voice feedback from the user" refers to feedback entered by the user through an in-car terminal or smartphone, and is a means of obtaining the driver's condition and emotions in real time.

[0886] "Multiple sensors" refers to a diverse group of sensors installed in the vehicle, such as heart rate sensors, driving time measurement sensors, and road condition sensors, which are devices that collect driver biometric information and road environment information in real time.

[0887] "Voice recognition function" is a technology that converts voice data into text data and is used to accurately analyze the driver's voice feedback.

[0888] "Means for analyzing and judging the driver's driving condition" refers to the system's function of analyzing the driver's driving situation based on collected voice feedback and sensor data, and evaluating and judging that condition.

[0889] "Means for suggesting transition to autonomous driving mode" refers to the system's function of providing a message to the driver to recommend switching to autonomous driving mode based on the analysis results.

[0890] A "generative AI model" is an artificial intelligence model that generates appropriate safe driving information based on analysis results, and provides safe driving instructions and advice using prompt text as input.

[0891] "Information about safe driving" is information generated by a generative AI model to support safe driving, such as recommended driving speeds for drivers and methods for ensuring safety.

[0892] "Communication messages with pedestrians during autonomous driving" are messages generated by autonomous vehicles to enable smooth interactions with pedestrians, including messages explaining the vehicle's behavior and warning pedestrians.

[0893] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[0894] System Configuration

[0895] The system mainly consists of the following components:

[0896] User device (in-vehicle device or smartphone)

[0897] server

[0898] Multiple sensors installed in the vehicle

[0899] Collecting voice feedback from users

[0900] The user device uses a voice recognition function (such as Google Assistant or Amazon Alexa) to collect the driver's voice feedback in real time. For example, if a driver feels tired after driving for a long time and says "I'm tired," the voice data is sent to the device and converted into text data by the voice recognition function. This text data is then sent directly to the server.

[0901] Collecting data from sensors

[0902] The vehicle is equipped with multiple sensors, including a heart rate sensor, a driving time measurement sensor, and a road condition sensor. These sensors collect data in real time and send it to a server via the user's device. For example, the heart rate sensor measures the driver's heart rate as 120 bpm, and the driving time measurement sensor measures the driving time as 3 hours.

[0903] Analysis of driver's driving state

[0904] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, based on voice feedback such as "I'm tired," a heart rate of 120 bpm, and driving time of more than three hours, the server will determine the driver's condition as "fatigue." To do this, it uses data processing algorithms and machine learning models.

[0905] Proposal for transition to autonomous driving mode

[0906] The user device will suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the message "We recommend switching to autonomous driving mode" will be displayed on the user device. This is an important step to maintain safety and comfort.

[0907] Providing information about safe driving

[0908] The server sends the analysis results to a generative AI model (such as OpenAI's GPT model) to generate information about safe driving. Safe driving information is obtained by inputting specific prompts into the generative AI model. For example, the prompt might read, "Please generate appropriate safe driving information if your heart rate is 120 bpm and your driving time is more than three hours." Based on this prompt, the generative AI model generates information such as, "Keep the recommended speed at 60 km / h and ensure thorough safety checks." This information is sent to the user's device via the server and presented to the driver.

[0909] Communication with pedestrians during autonomous driving

[0910] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[0911] Specific examples

[0912] As a concrete example, consider the following scenario. A driver feels tired after driving for a long time and utters, "I'm tired." This feedback is converted to text on the user's device and sent to the server. At the same time, the heart rate sensor measures a heart rate of 120 bpm and the driving time sensor measures three hours of driving time. These data are sent to the server, and analysis results indicate a "fatigue state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." The generative AI model also receives a prompt: "If your heart rate is 120 bpm and you have been driving for more than three hours, please generate appropriate safe driving information." This information is then displayed on the user's device. The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[0913] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[0914] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0915] Step 1:

[0916] Collecting voice feedback from users

[0917] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," the voice data is input into the device. The device converts this voice data into text data and sends it to the server.

[0918] Input: Driver's voice feedback (e.g., "I'm tired")

[0919] Output: Converted text data (e.g. "Tired")

[0920] Specific operation: The driver says, "I'm tired." The user device uses its voice recognition function to convert the speech into text and send it to the server.

[0921] Step 2:

[0922] Collecting data from sensors

[0923] Multiple sensors installed in the vehicle collect real-time data such as heart rate, driving time, and road conditions, and this sensor data is sent to a server via the user's device.

[0924] Input: Data from heart rate sensors, driving time sensors, and road condition sensors

[0925] Output: Sensor data (e.g. heart rate 120 bpm, driving time 3 hours)

[0926] Specific operation: The heart rate sensor measures the driver's heart rate, and the driving time measurement sensor measures the driving time and sends the data to the user's device. The user's device then sends this data to the server.

[0927] Step 3:

[0928] Analysis of driver's driving state

[0929] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[0930] Input: Audio feedback and sensor data sent from the user device

[0931] Output: Driver's driving state (e.g., "fatigue state")

[0932] Specific operation: The server analyzes the voice feedback and sensor data and obtains a judgment result of "fatigue state."

[0933] Step 4:

[0934] Proposal for transition to autonomous driving mode

[0935] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[0936] Input: Driving state analysis results from the server (e.g., "fatigue state")

[0937] Output: Message (e.g. "We recommend switching to Autopilot mode")

[0938] Specific operation: The user device receives the analysis results from the server and displays a message suggesting switching to autonomous driving mode.

[0939] Step 5:

[0940] Providing information about safe driving

[0941] The server sends the analysis results to the generation AI model, which generates information about safe driving. The prompt sentence "Please generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is 3 hours or more" is input to the generation AI model. The generated information is sent to the user's device via the server and presented to the driver.

[0942] Input: Prompt sentence based on the analysis results (e.g., "Generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is more than 3 hours.")

[0943] Output: Safe driving information (e.g., "Keep the recommended speed at 60km / h and be sure to check for safety")

[0944] Specific operation: The server generates a prompt sentence and sends it to the generative AI model. When the generative AI model returns safe driving information, it is sent from the server to the user's device.

[0945] Step 6:

[0946] Communication with pedestrians during autonomous driving

[0947] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[0948] Input: Data based on vehicle position and situation (e.g., data on approaching a pedestrian crossing)

[0949] Output: Communication message (e.g. "Vehicle waiting to pass. Please wait.")

[0950] Specific operation: The server generates a message based on the vehicle's status data and announces it to the outside via the vehicle's speakers and display via the user's terminal.

[0951] Through the above processing, the system can appropriately evaluate the driver's driving condition in real time and immediately take necessary measures to improve the safety of both the driver and pedestrians.

[0952] (Application example 1)

[0953] 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."

[0954] Conventional autonomous vehicle systems are unable to accurately grasp the driver's driving condition or fatigue level, resulting in insufficient provision of appropriate advice for continuing safe driving or suggestions for switching to autonomous driving mode. Furthermore, there is a lack of means for achieving smooth communication with pedestrians in urban areas. To resolve these issues, there is a need for dynamic monitoring of driving conditions and real-time responses based on immediate analysis results.

[0955] 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.

[0956] In this invention, the server includes: means for collecting voice feedback from the user; means for acquiring data from multiple sensors installed in the vehicle; means for analyzing the collected voice feedback and sensor data to determine the driver's driving state; means for proposing transition to autonomous driving mode based on the driver's driving state; means for transmitting the analysis results to a generative AI model and generating information on safe driving; means for presenting the generated information on safe driving to the driver; means for generating a communication message for the pedestrian when the vehicle approaches a pedestrian and transmitting it to an external device; and means for monitoring the driving state in real time based on sensor data and displaying safe driving information on an in-vehicle terminal or head-mounted display when necessary. This allows the driver's state to be grasped in real time, and it is possible to propose transition to autonomous driving mode at the appropriate time and generate safe driving advice. It also enables smooth communication with pedestrians.

[0957] "Audio feedback" refers to information collected by the system based on the audio produced by the user.

[0958] "Sensors" are various measuring devices installed in vehicles that collect data such as heart rate, driving time, and road conditions.

[0959] A "generative AI model" is an artificial intelligence that generates information about safe driving based on a given prompt.

[0960] "Driver's driving state" refers to the driver's fatigue and stress level, which is obtained by analyzing collected voice feedback and sensor data.

[0961] "Autonomous driving mode" refers to a mode in which the system operates the vehicle on behalf of the driver.

[0962] "Communication messages" are messages that a vehicle transmits to pedestrians during autonomous driving, and are generated for safety and information purposes.

[0963] An "in-vehicle terminal" is an electronic device installed in a vehicle, and is a terminal for collecting voice feedback, displaying safe driving information, and the like.

[0964] A "head-mounted display" is an electronic device worn by the driver that displays information directly into their field of vision.

[0965] "Real-time" refers to the time concept in which systems and equipment instantly collect, analyze, and respond to information.

[0966] This invention is a system that evaluates the driving status of a driver of an autonomous vehicle in real time, and if necessary, suggests switching to autonomous driving mode, provides safe driving information, and also enables smooth communication with pedestrians. This system mainly includes the following components.

[0967] User Device

[0968] The user terminal is a device with voice recognition capabilities installed in the vehicle (e.g., an in-vehicle terminal or smartphone) that collects voice feedback from the driver in real time. This terminal converts the driver's utterances into text data and sends it to a server.

[0969] Multiple sensors installed in the vehicle

[0970] The sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. These sensors collect the driver's biometric information and driving environment data in real time and send it to a server via the user's terminal.

[0971] server

[0972] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. For example, if the driver says "I'm tired," has a high heart rate, and has been driving for a long time, the server will determine that the driver is fatigued.

[0973] Proposal for transition to autonomous driving mode

[0974] If the server analyzes the driver's driving condition and finds that the driver is fatigued or stressed, it will display a message on the user's device stating, "We recommend switching to autonomous driving mode."

[0975] Generate safe driving information

[0976] The server sends the analysis results to a generative AI model, which generates optimal advice on safe driving. For example, it generates information such as "Keep the recommended speed at 50 km / h and thoroughly check for safety" and displays it on the user's device. GPT-3 and other models are used as generative AI models.

[0977] Communication with pedestrians

[0978] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message to inform the pedestrian, such as "A vehicle is waiting to pass. Please wait," and plays the message over the vehicle's speaker.

[0979] Real-time monitoring of sensor data

[0980] User devices and head-mounted displays monitor driving conditions in real time based on sensor data and display safe driving information when necessary.

[0981] Specific examples

[0982] As a concrete example, a driver begins to feel fatigued after driving for a long period of time. The driver says, "I'm tired," and sensors measure a heart rate of 130 bpm and four hours of continuous driving. The server collects and analyzes this data and determines that the driver is fatigued. As a result, the device displays a message saying, "We recommend switching to autonomous driving mode," and at the same time, the generative AI model provides safe driving information such as, "Please maintain a recommended speed of 50 km / h and thoroughly check for safety." Then, when the vehicle approaches a pedestrian, a message is generated saying, "The vehicle is waiting to pass. Please wait," and this is announced through the vehicle's speaker.

[0983] Prompt Sentence Examples

[0984] "Provide safe driving advice to fatigued drivers."

[0985] "What is the best driving advice for tired drivers?"

[0986] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0987] Step 1:

[0988] The user's device collects the user's voice in real time. The collected voice feedback is converted into text data using a voice recognition function. The input is the user's voice feedback, and the output is text data. Specifically, the system captures voice using the vehicle's microphone and converts it into text using a voice recognition library (e.g., Google Speech-to-Text).

[0989] Step 2:

[0990] Sensors installed in the vehicle collect real-time data such as the driver's heart rate, driving time, and road conditions. The input is biometric information and driving environment data from each sensor, and the output is sensor data. Specifically, the system acquires data from the heart rate sensor and GPS and sends it to the user's device.

[0991] Step 3:

[0992] The user device sends collected voice feedback and sensor data to the server. The input is text data and sensor data, and the output is data transmission to the server. Specifically, data is sent from the device to the server using an HTTP request.

[0993] Step 4:

[0994] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. The input is the text data and sensor data sent to the server, and the output is the result of the driving state assessment. Specifically, the data is analyzed using a Python library (e.g., Pandas, NumPy) to determine the driving state as "fatigued" or "normal."

[0995] Step 5:

[0996] The server sends prompts to the generative AI model based on the driving state, generating information about safe driving. The input is the driving state assessment result, and the output is the generated safe driving advice. Specifically, the prompt sentence "Please tell me the best driving advice for a tired driver" is input to the generative AI model (e.g., GPT-3), which generates appropriate advice.

[0997] Step 6:

[0998] The generated safe driving information is sent to the user terminal and presented to the driver. The input is the generated safe driving advice, and the output is the display on the user terminal. Specifically, data is sent from the server to the user terminal, and a message is displayed on the terminal's display.

[0999] Step 7:

[1000] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message for the pedestrian. The input is vehicle position data and pedestrian detection data, and the output is the generated message. Specifically, the generative AI model generates the message "A vehicle is waiting to pass. Please wait."

[1001] Step 8:

[1002] The generated message is communicated to pedestrians through the in-car speaker or external display. The input is the generated message, and the output is the transmission of the message to pedestrians. The specific operation is to announce or display the message on the in-car speaker or external display.

[1003] 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.

[1004] The system based on this invention combines autonomous driving technology with an emotion engine that recognizes the user's emotions to more accurately evaluate the driver's driving state and suggest switching to autonomous driving mode as necessary. Furthermore, by taking the driver's emotional state into consideration when providing safe driving information, it is possible to provide appropriate and effective advice.

[1005] System Configuration

[1006] The system mainly consists of the following components:

[1007] User device (in-vehicle device or smartphone)

[1008] server

[1009] Multiple sensors installed in the vehicle

[1010] Emotion engine that recognizes user emotions

[1011] DETAILED DESCRIPTION OF THE INVENTION

[1012] Collecting voice feedback from users

[1013] The user device uses voice recognition to collect real-time voice feedback from the driver. For example, if the driver says, "I'm tired," this feedback is recorded as text data on the device. Data for recognizing emotions from the voice is also collected in parallel.

[1014] Collecting data from sensors

[1015] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[1016] Analysis of driver's driving state

[1017] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[1018] Emotion recognition with emotion engine

[1019] The server uses an emotion engine to recognize emotions from the user's voice feedback, for example, assessing whether the driver is stressed or anxious through voice analysis.

[1020] Proposal for transition to autonomous driving mode

[1021] The user device will suggest switching to autonomous driving mode based on the driver's driving and emotional state analyzed by the server. Specifically, if the driver is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[1022] Providing information about safe driving

[1023] The server sends the analysis results to the generative AI, which generates information on safe driving. For example, taking into account the driver's emotional state, the AI ​​generates information such as, "You seem tired. Please keep your speed at 60 km / h and be careful to check for safety." This information is then sent to the user's device and displayed to the driver.

[1024] Communication with pedestrians during autonomous driving

[1025] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[1026] The user device will announce this message to the outside via the vehicle's speakers and display.

[1027] Specific examples

[1028] Consider the following scenario as a concrete example: After driving for a long period of time, the driver begins to feel fatigued and stressed. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." Sensors measure a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state" and that the driver's voice indicates stress. In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "You appear tired. Please maintain a speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[1029] In this way, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving condition and emotional state and taking necessary measures in real time.

[1030] The processing flow will be explained below.

[1031] Step 1:

[1032] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[1033] Specifically, the device converts voice feedback such as "I'm tired" into text data and records it as "user feedback." In addition, the voice data is also saved and sent to the emotion engine.

[1034] Step 2:

[1035] The device collects data in real time from multiple sensors installed in the vehicle.

[1036] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[1037] Step 3:

[1038] The device sends the collected sensor data and user feedback to the server.

[1039] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[1040] Step 4:

[1041] The server analyzes the received data and determines the driver's driving condition.

[1042] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[1043] Step 5:

[1044] The server uses an emotion engine to recognize emotions from the user's voice.

[1045] Specifically, voice analysis technology is used to assess whether a driver is feeling stressed or anxious based on the voice saying "I'm tired."

[1046] Step 6:

[1047] The server sends the analysis results and emotion recognition results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[1048] Specifically, if the driver is determined to be in a "fatigued" and "stressed" state, a message stating "We recommend switching to autonomous driving mode" is generated and sent to the device.

[1049] Step 7:

[1050] The user terminal receives the message from the server and displays it to the driver.

[1051] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[1052] Step 8:

[1053] The server sends the sensor data and emotion recognition results to the generative AI, which then generates information about safe driving.

[1054] Specifically, safe driving information is generated such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety."

[1055] Step 9:

[1056] The user terminal presents the generated safe driving information to the driver.

[1057] Specifically, the device will display the message, "You appear to be tired. Please maintain a speed of 60 km / h and ensure safety."

[1058] Step 10:

[1059] The server generates the communication messages with pedestrians required during autonomous driving.

[1060] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[1061] Step 11:

[1062] The user terminal transmits the generated communication message to the pedestrian.

[1063] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[1064] Example 2

[1065] 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."

[1066] Conventional autonomous driving technology does not fully consider the driver's driving condition or emotional state, and therefore has the problem of not responding appropriately when the driver is fatigued or stressed. This can lead to reduced safety and increased driver burden, which is a problem.

[1067] 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.

[1068] In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors mounted on the vehicle, means for analyzing the collected voice feedback and sensor data to determine the driver's driving state and emotional state, means for proposing transition to autonomous driving mode based on the driver's driving state and emotional state, means for transmitting the analysis results to generative artificial intelligence and generating information on safe driving, means for presenting the generated information on safe driving to the driver, and means for generating communication messages with pedestrians during autonomous driving and transmitting them to outside the vehicle. This makes it possible to analyze the driver's driving state and emotional state in real time and provide appropriate autonomous driving suggestions and safe driving information.

[1069] "Voice feedback" refers to opinions or status reports provided by the user through voice.

[1070] A "sensor" is a device installed in a vehicle that detects and measures heart rate, driving time, road conditions, etc.

[1071] "Driving condition" refers to the state of a driver's physical and mental driving ability.

[1072] "Emotional state" indicates the driver's current emotions and stress level.

[1073] "Autonomous driving mode" refers to a driving mode in which the vehicle is automatically controlled and driven without driver intervention.

[1074] "Generative AI" refers to an AI technology that generates appropriate countermeasures and information based on analysis results.

[1075] "Safe driving information" refers to information that provides drivers with advice and recommended driving behaviors that they need to continue driving safely.

[1076] "Communication messages" are messages generated by autonomous vehicles to facilitate communication with pedestrians and other road users.

[1077] MODE FOR CARRYING OUT THE INVENTION

[1078] The system based on the present invention analyzes the driving and emotional state of the user, and provides appropriate transition to autonomous driving mode and safe driving information. This system is composed of the following elements.

[1079] System Components

[1080] 1. User device: An in-vehicle device or smartphone is used. It is equipped with voice recognition functionality and is responsible for collecting voice feedback from the user.

[1081] 2. Server: Analyzes collected data and plays a central role in generating countermeasures and information using generative artificial intelligence.

[1082] 3. Sensors: Multiple sensors installed in the vehicle (heart rate sensors, driving time measurement sensors, road condition sensors, etc.) are used.

[1083] 4. Emotion engine: Used to analyze the user's emotional state.

[1084] Data collection and analysis

[1085] The user device uses voice recognition to collect the user's voice feedback in real time and convert it into text data. For example, imagine a situation where the user says, "I'm tired." At the same time, data is also obtained from the voice data to analyze emotions.

[1086] The sensors collect real-time data such as heart rate, driving time, and road conditions, and transmit the data to a server via the user's device.

[1087] Data analysis and recommendations

[1088] The server analyzes the voice feedback and sensor data collected in real time to determine the driver's driving and emotional state. For example, if the voice feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigued."

[1089] Next, an emotion engine is used to analyze the user's emotional state from their voice data to determine whether they are stressed or not.

[1090] Providing information and suggesting autonomous driving modes

[1091] Based on the results of the analysis, the user's device will suggest switching to autonomous driving mode. For example, if the user is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[1092] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, the server provides the generative AI with the following prompt:

[1093] "Generate a response when a driver expresses fatigue, their heart rate is over 120 bpm, and they've been driving for more than three hours."

[1094] "Please provide suggestions to drivers on how to drive safely if they are feeling fatigued."

[1095] The generated information is displayed on the user's device in the form of, for example, "You seem tired. Please maintain a speed of 60 km / h and make sure to check for safety."

[1096] Communication with pedestrians during autonomous driving

[1097] The server generates communication messages for pedestrians during autonomous driving. When the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the user's terminal using the vehicle's speakers and display.

[1098] In this way, the system comprehensively evaluates the user's driving and emotional state and provides appropriate responses in real time, thereby enhancing safety and comfort.

[1099] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1100] Detailed explanation of the processing steps

[1101] Step 1:

[1102] The user provides vocal feedback.

[1103] Specific operation: The user says "I'm tired." The device collects the voice feedback in real time and converts it into text data. At the same time, it performs preprocessing to analyze emotions from the voice data.

[1104] Input: User's voice feedback

[1105] Data processing: Preprocessing for speech-to-text conversion and sentiment analysis

[1106] Output: Preprocessing results of text data and emotion data

[1107] Step 2:

[1108] The terminal collects data in real time from multiple sensors installed in the vehicle.

[1109] Specific operation: The heart rate sensor measures 120 bpm, and the driving time sensor records the driving time for 3 hours. This data is collected on the user's device and sent to the server.

[1110] Input: Data from heart rate sensor and driving time measurement sensor

[1111] Data processing: Real-time data collection, data aggregation and transmission to the server

[1112] Output: Collected sensor data (heart rate and driving time)

[1113] Step 3:

[1114] The server receives and analyzes the audio feedback and sensor data.

[1115] Specific operation: The server analyzes the preprocessing results of the text data and emotion data, and integrates the heart rate data and driving time data. For example, if the text data is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigue state."

[1116] Input: Text data of voice feedback and collected sensor data

[1117] Data processing: Analysis of text data and sensor data

[1118] Output: Driver's driving condition (fatigue state)

[1119] Step 4:

[1120] The server uses an emotion engine to analyze the user's emotional state.

[1121] Specific operation: The server inputs the results of preprocessing the voice data into the emotion engine and analyzes emotional states such as stress and anxiety.

[1122] Input: Preprocessed audio data

[1123] Data processing: Emotion analysis using an emotion engine

[1124] Output: User's emotional state (e.g., stress state)

[1125] Step 5:

[1126] Based on the results of the analysis by the server, the device will suggest switching to autonomous driving mode.

[1127] Specific operation: If the driver is determined to be "fatigued" and "stressed," the device will display a message stating "We recommend switching to autonomous driving mode."

[1128] Input: Driver's driving and emotional state analyzed by the server

[1129] Output: Message proposing to switch to autonomous driving mode

[1130] Step 6:

[1131] The server sends the analysis results to the generative artificial intelligence, which generates information about safe driving.

[1132] Specific operation: The server inputs a prompt to the AI: "What to do if the driver says they are tired, their heart rate is over 120 bpm, and they have been driving for more than three hours." Based on this input, the AI ​​generates safe driving information such as, "Keep the speed at 60 km / h and make sure to check for safety."

[1133] Input: Prompt sentences based on the driver's driving and emotional state

[1134] Data Computation: Generating safe driving information using generative AI models

[1135] Output: Safe driving information

[1136] Step 7:

[1137] The terminal presents the generated safe driving information to the user.

[1138] Specific operation: The generated safe driving information is sent to the terminal, and the user is shown a message saying, "You seem tired. Please maintain a speed of 60 km / h and be thorough in checking for safety."

[1139] Input: Generated safe driving information

[1140] Output: Safe driving information presented to the user

[1141] Step 8:

[1142] The server generates communication messages with pedestrians during autonomous driving.

[1143] Specific operation: When a vehicle approaches a crosswalk, a message is generated stating "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the terminal using the in-car speaker or display.

[1144] Input: Vehicle position data and road condition data

[1145] Data calculation: Generating appropriate communication messages to pedestrians

[1146] Output: Communication message to pedestrians

[1147] (Application example 2)

[1148] 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."

[1149] As autonomous driving technology advances, there is a demand for improved safety that takes into account driver fatigue and emotional state. However, conventional autonomous driving systems are unable to consider the driver's emotional state, making it difficult to suggest transitioning to autonomous driving mode at the optimal time. This has resulted in a lack of systems that can reduce driver fatigue and stress and support safe driving.

[1150] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors installed in the vehicle, means for analyzing the collected voice feedback and sensor data and determining the driver's driving state, means for suggesting transition to autonomous driving mode based on the driver's driving state, means for transmitting the analysis results to a generative AI and generating information on safe driving, means for presenting the generated information on safe driving to the driver, means for generating communication messages with pedestrians during autonomous driving and transmitting them to the outside of the vehicle, means for recognizing the driver's voice feedback and emotional state in real time via a smartphone terminal, and means for providing appropriate advice to the driver based on the emotion recognition results. This enables appropriate suggestions for autonomous driving mode taking the driver's emotional state into consideration and support for safe driving.

[1151] "User voice feedback" refers to voice information provided by the driver through a device such as an in-car terminal or smartphone.

[1152] "Multiple sensors installed in a vehicle" refers to various sensors (e.g., heart rate sensors, driving time measurement sensors, road condition sensors, etc.) installed to grasp the situation inside and outside the vehicle.

[1153] "Collected audio feedback and sensor data" refers to the driver's audio feedback and data acquired by multiple sensors.

[1154] "Means for determining the driver's driving state" refers to a method or technology for evaluating and determining the driver's driving state (e.g., fatigue, decreased attention, etc.) based on collected voice feedback and sensor data.

[1155] "Means for proposing transition to automated driving mode" refers to a method or technology that recommends or notifies the driver to switch to automated driving mode based on the determined driving state of the driver.

[1156] "Generative AI" refers to a system or technology that uses artificial intelligence to automatically generate specific information (in this case, information about safe driving) from analysis results.

[1157] "Information regarding safe driving" refers to advice and warnings to assist drivers in safe driving (for example, recommended speeds, safety check methods, etc.).

[1158] The "means for recognizing driver's voice feedback and emotional state in real time via a smartphone device" refers to a technology that uses a smartphone device to receive the driver's voice input in real time, analyzes it, and recognizes the driver's emotional state.

[1159] "Means for generating communication messages with pedestrians during autonomous driving and transmitting them outside the vehicle" refers to technology that creates messages for smooth communication with pedestrians during autonomous driving and transmits them to pedestrians through appropriate means (for example, on-board speakers or displays).

[1160] MODE FOR CARRYING OUT THE INVENTION

[1161] The system based on the present invention combines autonomous driving technology with an emotion recognition engine to evaluate the driving condition and emotional state of the driver, and then transitions to autonomous driving mode and provides advice on safe driving. Specific embodiments are described below.

[1162] System Configuration

[1163] The system consists of the following main components:

[1164] 1. User device (smartphone or in-car device)

[1165] 2. Server

[1166] 3. Multiple sensors installed on the vehicle

[1167] 4. Emotion Recognition Engine

[1168] User Device

[1169] The user device is a smartphone or in-car device equipped with a voice recognition function. Voice recognition is performed using the speech_recognition library and the Google Speech Recognition API, which allows the driver's voice feedback to be collected in real time.

[1170] server

[1171] The server has the following features:

[1172] Analysis of collected audio feedback and sensor data

[1173] Determining the driver's driving and emotional state

[1174] Generating safe driving information using generative AI

[1175] Drive suggests transitioning to autonomous driving mode based on driving and emotional state

[1176] Generating communication messages with pedestrians during autonomous driving

[1177] Multiple sensors installed in the vehicle

[1178] The vehicle is equipped with sensors such as a heart rate sensor, a driving time measurement sensor, and a road condition sensor, which collect data in real time and transmit it to a server via the user's terminal.

[1179] Emotion Recognition Engine

[1180] The emotion recognition engine analyzes voice feedback from the user and recognizes the driver's emotional state (e.g., stress, anxiety, fatigue, etc.), and provides appropriate advice to the driver.

[1181] Specific operation example

[1182] For example, suppose a driver begins to feel fatigued or stressed after driving for a long period of time. At this point, the driver provides verbal feedback to the device, saying, "I'm tired." Sensors installed in the vehicle measure a heart rate of 120 bpm and driving time of three hours. This data is sent to the server in real time, and the server determines the driver's state as "fatigued."

[1183] Next, the emotion recognition engine analyzes the voice data and determines that the driver is feeling stressed. Based on this, the server notifies the user's device, "We recommend switching to autonomous driving mode." The generative AI also generates safe driving information to the driver, such as "You seem tired. Please maintain a speed of 60 km / h and thoroughly check for safety." After that, the system switches to autonomous driving mode, and when the vehicle approaches a pedestrian crossing, a message is generated and announced to pedestrians, saying, "A vehicle is waiting to pass. Please wait."

[1184] The above procedure makes it possible to provide safe driving assistance that takes into account the driver's driving condition and emotional state.

[1185] Prompt Sentence Examples

[1186] To illustrate, consider the following scenario:

[1187] User: While driving, say "I'm tired"

[1188] System: Emotion analysis determines "fatigue state" and notifies "We recommend switching to autonomous driving mode"

[1189] In this way, the system of the present invention provides appropriate responses based on the driver's real-time emotional and driving state, thereby improving safety.

[1190] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1191] Step 1:

[1192] The user device collects the driver's voice feedback. Specifically, it uses the speech_recognition library and the Google Speech Recognition API to obtain voice input as text data. This process takes voice data as input and obtains text data as output.

[1193] Step 2:

[1194] Multiple sensors installed in the vehicle collect data such as heart rate, driving time, and road conditions in real time and send it to a server via the user's terminal. The input is real-time data obtained from the sensors, and the output is data sent to the server.

[1195] Step 3:

[1196] The server analyzes the collected voice feedback and sensor data to determine the driver's driving state. Here, the voice data is analyzed using an emotion recognition engine to identify the driver's emotional state. The server also uses sensor data to determine the driver's "fatigue level" and other driving conditions based on heart rate and driving time. The input is the voice feedback and sensor data, and the output is the analysis results.

[1197] Step 4:

[1198] The server suggests switching to autonomous driving mode based on the driver's driving condition and emotional state. For example, if the driver is "fatigued" and "stressed," it generates a message saying "We recommend switching to autonomous driving mode" and sends it to the user's device. The input is the analysis result (driving condition and emotional state), and the output is a suggestion message.

[1199] Step 5:

[1200] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates specific advice such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety." The input is the analysis results, and the output is the generated safe driving information.

[1201] Step 6:

[1202] The user device presents the generated safe driving information to the driver. The device communicates the information to the driver using a screen display or audio output. The input is the safe driving information, and the output is a notification or display to the driver.

[1203] Step 7:

[1204] The server generates communication messages for pedestrians during autonomous driving and transmits them outside the vehicle. For example, when approaching a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait," and transmits it through the vehicle's speaker and display. The input is the vehicle's location and situation, and the output is a message to pedestrians.

[1205] The above processing steps realize an automated driving assistance system that takes into account the driver's driving state and emotional state.

[1206] 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.

[1207] 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.

[1208] 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.

[1209] [Fourth embodiment]

[1210] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1211] 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.

[1212] 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).

[1213] 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.

[1214] 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.

[1215] 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).

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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."

[1223] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[1224] System Configuration

[1225] The system mainly consists of the following components:

[1226] User device (in-vehicle device or smartphone)

[1227] server

[1228] Multiple sensors installed in the vehicle

[1229] DETAILED DESCRIPTION OF THE INVENTION

[1230] Collecting voice feedback from users

[1231] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," this feedback is recorded as text data on the device.

[1232] Collecting data from sensors

[1233] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[1234] Analysis of driver's driving state

[1235] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[1236] Proposal for transition to autonomous driving mode

[1237] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[1238] Providing information about safe driving

[1239] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates information such as "Keep the recommended speed at 60 km / h and make sure to check for safety," which is then sent to the user's device and displayed to the driver.

[1240] Communication with pedestrians during autonomous driving

[1241] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[1242] The user device will announce this message to the outside via the vehicle's speakers and display.

[1243] Specific examples

[1244] Consider the following scenario as a concrete example: A driver begins to feel fatigued after driving for a long period of time. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." A sensor measures a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "Please maintain a recommended speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and gains the understanding of pedestrians.

[1245] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[1246] The processing flow will be explained below.

[1247] Step 1:

[1248] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[1249] Specifically, the terminal converts voice feedback such as "I'm tired" into text data and records this as "user feedback."

[1250] Step 2:

[1251] The device collects data in real time from multiple sensors installed in the vehicle.

[1252] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[1253] Step 3:

[1254] The device sends the collected sensor data and user feedback to the server.

[1255] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[1256] Step 4:

[1257] The server analyzes the received data and determines the driver's driving condition.

[1258] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[1259] Step 5:

[1260] The server sends the analysis results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[1261] Specifically, if the server determines that the driver is in a "fatigue state," it generates a message stating, "We recommend switching to autonomous driving mode," and sends it to the device.

[1262] Step 6:

[1263] The user terminal receives the message from the server and displays it to the driver.

[1264] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[1265] Step 7:

[1266] The server sends the sensor data to the generative AI, which generates information about safe driving.

[1267] Specifically, it generates safe driving information such as "Keep the recommended speed at 60 km / h and make sure to check for safety."

[1268] Step 8:

[1269] The user terminal presents the generated safe driving information to the driver.

[1270] Specifically, the device will display the message, "Please maintain a recommended speed of 60 km / h and ensure safety."

[1271] Step 9:

[1272] The server generates the communication messages with pedestrians required during autonomous driving.

[1273] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[1274] Step 10:

[1275] The user terminal transmits the generated communication message to the pedestrian.

[1276] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[1277] Example 1

[1278] 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."

[1279] Advances in autonomous driving technology are expected to reduce driver burden and prevent accidents, but current systems have difficulty properly assessing the driver's driving state in real time and taking the necessary action immediately. Furthermore, there is a lack of communication with pedestrians, leaving challenges in improving safety and ensuring social acceptance. There is a need to solve these problems and provide safer, more effective autonomous driving systems.

[1280] 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.

[1281] In this invention, the server includes a means for collecting voice feedback from the user in real time, a means for acquiring data in real time from multiple sensors mounted on the vehicle, and a means for analyzing and determining the driver's driving state based on the collected voice feedback and sensor data. This makes it possible to appropriately evaluate the driver's driving state in real time, suggest transitioning to autonomous driving mode, provide safe driving information, and smoothly communicate with pedestrians.

[1282] "Voice feedback from the user" refers to feedback entered by the user through an in-car terminal or smartphone, and is a means of obtaining the driver's condition and emotions in real time.

[1283] "Multiple sensors" refers to a diverse group of sensors installed in the vehicle, such as heart rate sensors, driving time measurement sensors, and road condition sensors, which are devices that collect driver biometric information and road environment information in real time.

[1284] "Voice recognition function" is a technology that converts voice data into text data and is used to accurately analyze the driver's voice feedback.

[1285] "Means for analyzing and judging the driver's driving condition" refers to the system's function of analyzing the driver's driving situation based on collected voice feedback and sensor data, and evaluating and judging that condition.

[1286] "Means for suggesting transition to autonomous driving mode" refers to the system's function of providing a message to the driver to recommend switching to autonomous driving mode based on the analysis results.

[1287] A "generative AI model" is an artificial intelligence model that generates appropriate safe driving information based on analysis results, and provides safe driving instructions and advice using prompt text as input.

[1288] "Information about safe driving" is information generated by a generative AI model to support safe driving, such as recommended driving speeds for drivers and methods for ensuring safety.

[1289] "Communication messages with pedestrians during autonomous driving" are messages generated by autonomous vehicles to enable smooth interactions with pedestrians, including messages explaining the vehicle's behavior and warning pedestrians.

[1290] The system based on this invention uses autonomous driving technology to evaluate the driver's driving condition in real time, transitioning to autonomous driving mode as needed, providing safe driving information, and enabling smooth communication with pedestrians in the city.

[1291] System Configuration

[1292] The system mainly consists of the following components:

[1293] User device (in-vehicle device or smartphone)

[1294] server

[1295] Multiple sensors installed in the vehicle

[1296] Collecting voice feedback from users

[1297] The user device uses a voice recognition function (such as Google Assistant or Amazon Alexa) to collect the driver's voice feedback in real time. For example, if a driver feels tired after driving for a long time and says "I'm tired," the voice data is sent to the device and converted into text data by the voice recognition function. This text data is then sent directly to the server.

[1298] Collecting data from sensors

[1299] The vehicle is equipped with multiple sensors, including a heart rate sensor, a driving time measurement sensor, and a road condition sensor. These sensors collect data in real time and send it to a server via the user's device. For example, the heart rate sensor measures the driver's heart rate as 120 bpm, and the driving time measurement sensor measures the driving time as 3 hours.

[1300] Analysis of driver's driving state

[1301] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, based on voice feedback such as "I'm tired," a heart rate of 120 bpm, and driving time of more than three hours, the server will determine the driver's condition as "fatigue." To do this, it uses data processing algorithms and machine learning models.

[1302] Proposal for transition to autonomous driving mode

[1303] The user device will suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the message "We recommend switching to autonomous driving mode" will be displayed on the user device. This is an important step to maintain safety and comfort.

[1304] Providing information about safe driving

[1305] The server sends the analysis results to a generative AI model (such as OpenAI's GPT model) to generate information about safe driving. Safe driving information is obtained by inputting specific prompts into the generative AI model. For example, the prompt might read, "Please generate appropriate safe driving information if your heart rate is 120 bpm and your driving time is more than three hours." Based on this prompt, the generative AI model generates information such as, "Keep the recommended speed at 60 km / h and ensure thorough safety checks." This information is sent to the user's device via the server and presented to the driver.

[1306] Communication with pedestrians during autonomous driving

[1307] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[1308] Specific examples

[1309] As a concrete example, consider the following scenario. A driver feels tired after driving for a long time and utters, "I'm tired." This feedback is converted to text on the user's device and sent to the server. At the same time, the heart rate sensor measures a heart rate of 120 bpm and the driving time sensor measures three hours of driving time. These data are sent to the server, and analysis results indicate a "fatigue state." In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." The generative AI model also receives a prompt: "If your heart rate is 120 bpm and you have been driving for more than three hours, please generate appropriate safe driving information." This information is then displayed on the user's device. The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[1310] As described above, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving state and taking necessary measures in real time.

[1311] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1312] Step 1:

[1313] Collecting voice feedback from users

[1314] The user device uses voice recognition to collect the driver's voice feedback in real time. For example, if the driver says "I'm tired," the voice data is input into the device. The device converts this voice data into text data and sends it to the server.

[1315] Input: Driver's voice feedback (e.g., "I'm tired")

[1316] Output: Converted text data (e.g. "Tired")

[1317] Specific operation: The driver says, "I'm tired." The user device uses its voice recognition function to convert the speech into text and send it to the server.

[1318] Step 2:

[1319] Collecting data from sensors

[1320] Multiple sensors installed in the vehicle collect real-time data such as heart rate, driving time, and road conditions, and this sensor data is sent to a server via the user's device.

[1321] Input: Data from heart rate sensors, driving time sensors, and road condition sensors

[1322] Output: Sensor data (e.g. heart rate 120 bpm, driving time 3 hours)

[1323] Specific operation: The heart rate sensor measures the driver's heart rate, and the driving time measurement sensor measures the driving time and sends the data to the user's device. The user's device then sends this data to the server.

[1324] Step 3:

[1325] Analysis of driver's driving state

[1326] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[1327] Input: Audio feedback and sensor data sent from the user device

[1328] Output: Driver's driving state (e.g., "fatigue state")

[1329] Specific operation: The server analyzes the voice feedback and sensor data and obtains a judgment result of "fatigue state."

[1330] Step 4:

[1331] Proposal for transition to autonomous driving mode

[1332] The user device will then suggest switching to autonomous driving mode based on the driver's driving status analyzed by the server. Specifically, the device will display a message saying, "We recommend switching to autonomous driving mode."

[1333] Input: Driving state analysis results from the server (e.g., "fatigue state")

[1334] Output: Message (e.g. "We recommend switching to Autopilot mode")

[1335] Specific operation: The user device receives the analysis results from the server and displays a message suggesting switching to autonomous driving mode.

[1336] Step 5:

[1337] Providing information about safe driving

[1338] The server sends the analysis results to the generation AI model, which generates information about safe driving. The prompt sentence "Please generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is 3 hours or more" is input to the generation AI model. The generated information is sent to the user's device via the server and presented to the driver.

[1339] Input: Prompt sentence based on the analysis results (e.g., "Generate appropriate safe driving information if the heart rate is 120 bpm and the driving time is more than 3 hours.")

[1340] Output: Safe driving information (e.g., "Keep the recommended speed at 60km / h and be sure to check for safety")

[1341] Specific operation: The server generates a prompt sentence and sends it to the generative AI model. When the generative AI model returns safe driving information, it is sent from the server to the user's device.

[1342] Step 6:

[1343] Communication with pedestrians during autonomous driving

[1344] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the vehicle's speakers and display on the user's device.

[1345] Input: Data based on vehicle position and situation (e.g., data on approaching a pedestrian crossing)

[1346] Output: Communication message (e.g. "Vehicle waiting to pass. Please wait.")

[1347] Specific operation: The server generates a message based on the vehicle's status data and announces it to the outside via the vehicle's speakers and display via the user's terminal.

[1348] Through the above processing, the system can appropriately evaluate the driver's driving condition in real time and immediately take necessary measures to improve the safety of both the driver and pedestrians.

[1349] (Application example 1)

[1350] 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."

[1351] Conventional autonomous vehicle systems are unable to accurately grasp the driver's driving condition or fatigue level, resulting in insufficient provision of appropriate advice for continuing safe driving or suggestions for switching to autonomous driving mode. Furthermore, there is a lack of means for achieving smooth communication with pedestrians in urban areas. To resolve these issues, there is a need for dynamic monitoring of driving conditions and real-time responses based on immediate analysis results.

[1352] 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.

[1353] In this invention, the server includes: means for collecting voice feedback from the user; means for acquiring data from multiple sensors installed in the vehicle; means for analyzing the collected voice feedback and sensor data to determine the driver's driving state; means for proposing transition to autonomous driving mode based on the driver's driving state; means for transmitting the analysis results to a generative AI model and generating information on safe driving; means for presenting the generated information on safe driving to the driver; means for generating a communication message for the pedestrian when the vehicle approaches a pedestrian and transmitting it to an external device; and means for monitoring the driving state in real time based on sensor data and displaying safe driving information on an in-vehicle terminal or head-mounted display when necessary. This allows the driver's state to be grasped in real time, and it is possible to propose transition to autonomous driving mode at the appropriate time and generate safe driving advice. It also enables smooth communication with pedestrians.

[1354] "Audio feedback" refers to information collected by the system based on the audio produced by the user.

[1355] "Sensors" are various measuring devices installed in vehicles that collect data such as heart rate, driving time, and road conditions.

[1356] A "generative AI model" is an artificial intelligence that generates information about safe driving based on a given prompt.

[1357] "Driver's driving state" refers to the driver's fatigue and stress level, which is obtained by analyzing collected voice feedback and sensor data.

[1358] "Autonomous driving mode" refers to a mode in which the system operates the vehicle on behalf of the driver.

[1359] "Communication messages" are messages that a vehicle transmits to pedestrians during autonomous driving, and are generated for safety and information purposes.

[1360] An "in-vehicle terminal" is an electronic device installed in a vehicle, and is a terminal for collecting voice feedback, displaying safe driving information, and the like.

[1361] A "head-mounted display" is an electronic device worn by the driver that displays information directly into their field of vision.

[1362] "Real-time" refers to the time concept in which systems and equipment instantly collect, analyze, and respond to information.

[1363] This invention is a system that evaluates the driving status of a driver of an autonomous vehicle in real time, and if necessary, suggests switching to autonomous driving mode, provides safe driving information, and also enables smooth communication with pedestrians. This system mainly includes the following components.

[1364] User Device

[1365] The user terminal is a device with voice recognition capabilities installed in the vehicle (e.g., an in-vehicle terminal or smartphone) that collects voice feedback from the driver in real time. This terminal converts the driver's utterances into text data and sends it to a server.

[1366] Multiple sensors installed in the vehicle

[1367] The sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. These sensors collect the driver's biometric information and driving environment data in real time and send it to a server via the user's terminal.

[1368] server

[1369] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. For example, if the driver says "I'm tired," has a high heart rate, and has been driving for a long time, the server will determine that the driver is fatigued.

[1370] Proposal for transition to autonomous driving mode

[1371] If the server analyzes the driver's driving condition and finds that the driver is fatigued or stressed, it will display a message on the user's device stating, "We recommend switching to autonomous driving mode."

[1372] Generate safe driving information

[1373] The server sends the analysis results to a generative AI model, which generates optimal advice on safe driving. For example, it generates information such as "Keep the recommended speed at 50 km / h and thoroughly check for safety" and displays it on the user's device. GPT-3 and other models are used as generative AI models.

[1374] Communication with pedestrians

[1375] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message to inform the pedestrian, such as "A vehicle is waiting to pass. Please wait," and plays the message over the vehicle's speaker.

[1376] Real-time monitoring of sensor data

[1377] User devices and head-mounted displays monitor driving conditions in real time based on sensor data and display safe driving information when necessary.

[1378] Specific examples

[1379] As a concrete example, a driver begins to feel fatigued after driving for a long period of time. The driver says, "I'm tired," and sensors measure a heart rate of 130 bpm and four hours of continuous driving. The server collects and analyzes this data and determines that the driver is fatigued. As a result, the device displays a message saying, "We recommend switching to autonomous driving mode," and at the same time, the generative AI model provides safe driving information such as, "Please maintain a recommended speed of 50 km / h and thoroughly check for safety." Then, when the vehicle approaches a pedestrian, a message is generated saying, "The vehicle is waiting to pass. Please wait," and this is announced through the vehicle's speaker.

[1380] Prompt Sentence Examples

[1381] "Provide safe driving advice to fatigued drivers."

[1382] "What is the best driving advice for tired drivers?"

[1383] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1384] Step 1:

[1385] The user's device collects the user's voice in real time. The collected voice feedback is converted into text data using a voice recognition function. The input is the user's voice feedback, and the output is text data. Specifically, the system captures voice using the vehicle's microphone and converts it into text using a voice recognition library (e.g., Google Speech-to-Text).

[1386] Step 2:

[1387] Sensors installed in the vehicle collect real-time data such as the driver's heart rate, driving time, and road conditions. The input is biometric information and driving environment data from each sensor, and the output is sensor data. Specifically, the system acquires data from the heart rate sensor and GPS and sends it to the user's device.

[1388] Step 3:

[1389] The user device sends collected voice feedback and sensor data to the server. The input is text data and sensor data, and the output is data transmission to the server. Specifically, data is sent from the device to the server using an HTTP request.

[1390] Step 4:

[1391] The server analyzes the received voice feedback and sensor data to determine the driver's driving state. The input is the text data and sensor data sent to the server, and the output is the result of the driving state assessment. Specifically, the data is analyzed using a Python library (e.g., Pandas, NumPy) to determine the driving state as "fatigued" or "normal."

[1392] Step 5:

[1393] The server sends prompts to the generative AI model based on the driving state, generating information about safe driving. The input is the driving state assessment result, and the output is the generated safe driving advice. Specifically, the prompt sentence "Please tell me the best driving advice for a tired driver" is input to the generative AI model (e.g., GPT-3), which generates appropriate advice.

[1394] Step 6:

[1395] The generated safe driving information is sent to the user terminal and presented to the driver. The input is the generated safe driving advice, and the output is the display on the user terminal. Specifically, data is sent from the server to the user terminal, and a message is displayed on the terminal's display.

[1396] Step 7:

[1397] When a vehicle approaches a pedestrian, the server uses a generative AI model based on sensor data to generate a message for the pedestrian. The input is vehicle position data and pedestrian detection data, and the output is the generated message. Specifically, the generative AI model generates the message "A vehicle is waiting to pass. Please wait."

[1398] Step 8:

[1399] The generated message is communicated to pedestrians through the in-car speaker or external display. The input is the generated message, and the output is the transmission of the message to pedestrians. The specific operation is to announce or display the message on the in-car speaker or external display.

[1400] 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.

[1401] The system based on this invention combines autonomous driving technology with an emotion engine that recognizes the user's emotions to more accurately evaluate the driver's driving state and suggest switching to autonomous driving mode as necessary. Furthermore, by taking the driver's emotional state into consideration when providing safe driving information, it is possible to provide appropriate and effective advice.

[1402] System Configuration

[1403] The system mainly consists of the following components:

[1404] User device (in-vehicle device or smartphone)

[1405] server

[1406] Multiple sensors installed in the vehicle

[1407] Emotion engine that recognizes user emotions

[1408] DETAILED DESCRIPTION OF THE INVENTION

[1409] Collecting voice feedback from users

[1410] The user device uses voice recognition to collect real-time voice feedback from the driver. For example, if the driver says, "I'm tired," this feedback is recorded as text data on the device. Data for recognizing emotions from the voice is also collected in parallel.

[1411] Collecting data from sensors

[1412] The multiple sensors installed in the vehicle include a heart rate sensor, a driving time measurement sensor, a road condition sensor, etc. Data from these sensors is collected in real time and sent to a server via the user's terminal.

[1413] Analysis of driver's driving state

[1414] The server analyzes the driver's driving condition based on the collected voice feedback and sensor data. For example, if the feedback is "I'm tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's condition as "fatigued."

[1415] Emotion recognition with emotion engine

[1416] The server uses an emotion engine to recognize emotions from the user's voice feedback, for example, assessing whether the driver is stressed or anxious through voice analysis.

[1417] Proposal for transition to autonomous driving mode

[1418] The user device will suggest switching to autonomous driving mode based on the driver's driving and emotional state analyzed by the server. Specifically, if the driver is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[1419] Providing information about safe driving

[1420] The server sends the analysis results to the generative AI, which generates information on safe driving. For example, taking into account the driver's emotional state, the AI ​​generates information such as, "You seem tired. Please keep your speed at 60 km / h and be careful to check for safety." This information is then sent to the user's device and displayed to the driver.

[1421] Communication with pedestrians during autonomous driving

[1422] The server generates communication messages for pedestrians in the city during autonomous driving. For example, when the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait."

[1423] The user device will announce this message to the outside via the vehicle's speakers and display.

[1424] Specific examples

[1425] Consider the following scenario as a concrete example: After driving for a long period of time, the driver begins to feel fatigued and stressed. At this point, the driver verbally provides feedback to the device, saying, "I'm tired." Sensors measure a heart rate of 120 bpm and three hours of driving time. This data is sent to the server, which determines that the driver is in a "fatigued state" and that the driver's voice indicates stress. In response, the user's device displays a message saying, "We recommend switching to autonomous driving mode." At the same time, the generative AI generates and presents safe driving information to the driver, saying, "You appear tired. Please maintain a speed of 60 km / h and thoroughly check for safety." The system then switches to autonomous driving mode, and announces to pedestrians, "A vehicle is waiting to pass. Please wait." This ensures the driver's safety and ensures pedestrians' understanding.

[1426] In this way, the present invention is a system that can improve safety and social acceptance by appropriately evaluating the driver's driving condition and emotional state and taking necessary measures in real time.

[1427] The processing flow will be explained below.

[1428] Step 1:

[1429] The user terminal activates the voice recognition function and collects voice feedback from the driver.

[1430] Specifically, the device converts voice feedback such as "I'm tired" into text data and records it as "user feedback." In addition, the voice data is also saved and sent to the emotion engine.

[1431] Step 2:

[1432] The device collects data in real time from multiple sensors installed in the vehicle.

[1433] Specifically, the heart rate sensor indicates 120 bpm, and the driving time sensor records data for three hours. This information is saved in the device as "sensor data."

[1434] Step 3:

[1435] The device sends the collected sensor data and user feedback to the server.

[1436] Specifically, the terminal uploads data to a server via the Internet or an in-vehicle network.

[1437] Step 4:

[1438] The server analyzes the received data and determines the driver's driving condition.

[1439] Specifically, the server confirms that the user feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, and evaluates this as a "fatigue state."

[1440] Step 5:

[1441] The server uses an emotion engine to recognize emotions from the user's voice.

[1442] Specifically, voice analysis technology is used to assess whether a driver is feeling stressed or anxious based on the voice saying "I'm tired."

[1443] Step 6:

[1444] The server sends the analysis results and emotion recognition results to the user's device and suggests transitioning to autonomous driving mode based on the driver's condition.

[1445] Specifically, if the driver is determined to be in a "fatigued" and "stressed" state, a message stating "We recommend switching to autonomous driving mode" is generated and sent to the device.

[1446] Step 7:

[1447] The user terminal receives the message from the server and displays it to the driver.

[1448] Specifically, a message will appear on the device screen saying, "We recommend switching to autonomous driving mode."

[1449] Step 8:

[1450] The server sends the sensor data and emotion recognition results to the generative AI, which then generates information about safe driving.

[1451] Specifically, safe driving information is generated such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety."

[1452] Step 9:

[1453] The user terminal presents the generated safe driving information to the driver.

[1454] Specifically, the device will display the message, "You appear to be tired. Please maintain a speed of 60 km / h and ensure safety."

[1455] Step 10:

[1456] The server generates the communication messages with pedestrians required during autonomous driving.

[1457] Specifically, when a vehicle approaches a crosswalk, a message is created saying, "A vehicle is waiting to pass. Please wait."

[1458] Step 11:

[1459] The user terminal transmits the generated communication message to the pedestrian.

[1460] Specifically, an announcement will be made through the vehicle's speakers and display saying, "A vehicle is waiting to pass. Please wait."

[1461] Example 2

[1462] 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."

[1463] Conventional autonomous driving technology does not fully consider the driver's driving condition or emotional state, and therefore has the problem of not responding appropriately when the driver is fatigued or stressed. This can lead to reduced safety and increased driver burden, which is a problem.

[1464] 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.

[1465] In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors mounted on the vehicle, means for analyzing the collected voice feedback and sensor data to determine the driver's driving state and emotional state, means for proposing transition to autonomous driving mode based on the driver's driving state and emotional state, means for transmitting the analysis results to generative artificial intelligence and generating information on safe driving, means for presenting the generated information on safe driving to the driver, and means for generating communication messages with pedestrians during autonomous driving and transmitting them to outside the vehicle. This makes it possible to analyze the driver's driving state and emotional state in real time and provide appropriate autonomous driving suggestions and safe driving information.

[1466] "Voice feedback" refers to opinions or status reports provided by the user through voice.

[1467] A "sensor" is a device installed in a vehicle that detects and measures heart rate, driving time, road conditions, etc.

[1468] "Driving condition" refers to the state of a driver's physical and mental driving ability.

[1469] "Emotional state" indicates the driver's current emotions and stress level.

[1470] "Autonomous driving mode" refers to a driving mode in which the vehicle is automatically controlled and driven without driver intervention.

[1471] "Generative AI" refers to an AI technology that generates appropriate countermeasures and information based on analysis results.

[1472] "Safe driving information" refers to information that provides drivers with advice and recommended driving behaviors that they need to continue driving safely.

[1473] "Communication messages" are messages generated by autonomous vehicles to facilitate communication with pedestrians and other road users.

[1474] MODE FOR CARRYING OUT THE INVENTION

[1475] The system based on the present invention analyzes the driving and emotional state of the user, and provides appropriate transition to autonomous driving mode and safe driving information. This system is composed of the following elements.

[1476] System Components

[1477] 1. User device: An in-vehicle device or smartphone is used. It is equipped with voice recognition functionality and is responsible for collecting voice feedback from the user.

[1478] 2. Server: Analyzes collected data and plays a central role in generating countermeasures and information using generative artificial intelligence.

[1479] 3. Sensors: Multiple sensors installed in the vehicle (heart rate sensors, driving time measurement sensors, road condition sensors, etc.) are used.

[1480] 4. Emotion engine: Used to analyze the user's emotional state.

[1481] Data collection and analysis

[1482] The user device uses voice recognition to collect the user's voice feedback in real time and convert it into text data. For example, imagine a situation where the user says, "I'm tired." At the same time, data is also obtained from the voice data to analyze emotions.

[1483] The sensors collect real-time data such as heart rate, driving time, and road conditions, and transmit the data to a server via the user's device.

[1484] Data analysis and recommendations

[1485] The server analyzes the voice feedback and sensor data collected in real time to determine the driver's driving and emotional state. For example, if the voice feedback is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigued."

[1486] Next, an emotion engine is used to analyze the user's emotional state from their voice data to determine whether they are stressed or not.

[1487] Providing information and suggesting autonomous driving modes

[1488] Based on the results of the analysis, the user's device will suggest switching to autonomous driving mode. For example, if the user is "fatigued" and feeling stressed, the device will display a message saying, "We recommend switching to autonomous driving mode."

[1489] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, the server provides the generative AI with the following prompt:

[1490] "Generate a response when a driver expresses fatigue, their heart rate is over 120 bpm, and they've been driving for more than three hours."

[1491] "Please provide suggestions to drivers on how to drive safely if they are feeling fatigued."

[1492] The generated information is displayed on the user's device in the form of, for example, "You seem tired. Please maintain a speed of 60 km / h and make sure to check for safety."

[1493] Communication with pedestrians during autonomous driving

[1494] The server generates communication messages for pedestrians during autonomous driving. When the vehicle approaches a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the user's terminal using the vehicle's speakers and display.

[1495] In this way, the system comprehensively evaluates the user's driving and emotional state and provides appropriate responses in real time, thereby enhancing safety and comfort.

[1496] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1497] Detailed explanation of the processing steps

[1498] Step 1:

[1499] The user provides vocal feedback.

[1500] Specific operation: The user says "I'm tired." The device collects the voice feedback in real time and converts it into text data. At the same time, it performs preprocessing to analyze emotions from the voice data.

[1501] Input: User's voice feedback

[1502] Data processing: Preprocessing for speech-to-text conversion and sentiment analysis

[1503] Output: Preprocessing results of text data and emotion data

[1504] Step 2:

[1505] The terminal collects data in real time from multiple sensors installed in the vehicle.

[1506] Specific operation: The heart rate sensor measures 120 bpm, and the driving time sensor records the driving time for 3 hours. This data is collected on the user's device and sent to the server.

[1507] Input: Data from heart rate sensor and driving time measurement sensor

[1508] Data processing: Real-time data collection, data aggregation and transmission to the server

[1509] Output: Collected sensor data (heart rate and driving time)

[1510] Step 3:

[1511] The server receives and analyzes the audio feedback and sensor data.

[1512] Specific operation: The server analyzes the preprocessing results of the text data and emotion data, and integrates the heart rate data and driving time data. For example, if the text data is "tired," the heart rate is 120 bpm, and the driving time is more than three hours, the server will determine the driver's state as "fatigue state."

[1513] Input: Text data of voice feedback and collected sensor data

[1514] Data processing: Analysis of text data and sensor data

[1515] Output: Driver's driving condition (fatigue state)

[1516] Step 4:

[1517] The server uses an emotion engine to analyze the user's emotional state.

[1518] Specific operation: The server inputs the results of preprocessing the voice data into the emotion engine and analyzes emotional states such as stress and anxiety.

[1519] Input: Preprocessed audio data

[1520] Data processing: Emotion analysis using an emotion engine

[1521] Output: User's emotional state (e.g., stress state)

[1522] Step 5:

[1523] Based on the results of the analysis by the server, the device will suggest switching to autonomous driving mode.

[1524] Specific operation: If the driver is determined to be "fatigued" and "stressed," the device will display a message stating "We recommend switching to autonomous driving mode."

[1525] Input: Driver's driving and emotional state analyzed by the server

[1526] Output: Message proposing to switch to autonomous driving mode

[1527] Step 6:

[1528] The server sends the analysis results to the generative artificial intelligence, which generates information about safe driving.

[1529] Specific operation: The server inputs a prompt to the AI: "What to do if the driver says they are tired, their heart rate is over 120 bpm, and they have been driving for more than three hours." Based on this input, the AI ​​generates safe driving information such as, "Keep the speed at 60 km / h and make sure to check for safety."

[1530] Input: Prompt sentences based on the driver's driving and emotional state

[1531] Data Computation: Generating safe driving information using generative AI models

[1532] Output: Safe driving information

[1533] Step 7:

[1534] The terminal presents the generated safe driving information to the user.

[1535] Specific operation: The generated safe driving information is sent to the terminal, and the user is shown a message saying, "You seem tired. Please maintain a speed of 60 km / h and be thorough in checking for safety."

[1536] Input: Generated safe driving information

[1537] Output: Safe driving information presented to the user

[1538] Step 8:

[1539] The server generates communication messages with pedestrians during autonomous driving.

[1540] Specific operation: When a vehicle approaches a crosswalk, a message is generated stating "A vehicle is waiting to pass. Please wait." This message is then announced to the outside via the terminal using the in-car speaker or display.

[1541] Input: Vehicle position data and road condition data

[1542] Data calculation: Generating appropriate communication messages to pedestrians

[1543] Output: Communication message to pedestrians

[1544] (Application example 2)

[1545] 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."

[1546] As autonomous driving technology advances, there is a demand for improved safety that takes into account driver fatigue and emotional state. However, conventional autonomous driving systems are unable to consider the driver's emotional state, making it difficult to suggest transitioning to autonomous driving mode at the optimal time. This has resulted in a lack of systems that can reduce driver fatigue and stress and support safe driving.

[1547] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice feedback from the user, means for acquiring data from multiple sensors installed in the vehicle, means for analyzing the collected voice feedback and sensor data and determining the driver's driving state, means for suggesting transition to autonomous driving mode based on the driver's driving state, means for transmitting the analysis results to a generative AI and generating information on safe driving, means for presenting the generated information on safe driving to the driver, means for generating communication messages with pedestrians during autonomous driving and transmitting them to the outside of the vehicle, means for recognizing the driver's voice feedback and emotional state in real time via a smartphone terminal, and means for providing appropriate advice to the driver based on the emotion recognition results. This enables appropriate suggestions for autonomous driving mode taking the driver's emotional state into consideration and support for safe driving.

[1548] "User voice feedback" refers to voice information provided by the driver through a device such as an in-car terminal or smartphone.

[1549] "Multiple sensors installed in a vehicle" refers to various sensors (e.g., heart rate sensors, driving time measurement sensors, road condition sensors, etc.) installed to grasp the situation inside and outside the vehicle.

[1550] "Collected audio feedback and sensor data" refers to the driver's audio feedback and data acquired by multiple sensors.

[1551] "Means for determining the driver's driving state" refers to a method or technology for evaluating and determining the driver's driving state (e.g., fatigue, decreased attention, etc.) based on collected voice feedback and sensor data.

[1552] "Means for proposing transition to automated driving mode" refers to a method or technology that recommends or notifies the driver to switch to automated driving mode based on the determined driving state of the driver.

[1553] "Generative AI" refers to a system or technology that uses artificial intelligence to automatically generate specific information (in this case, information about safe driving) from analysis results.

[1554] "Information regarding safe driving" refers to advice and warnings to assist drivers in safe driving (for example, recommended speeds, safety check methods, etc.).

[1555] The "means for recognizing driver's voice feedback and emotional state in real time via a smartphone device" refers to a technology that uses a smartphone device to receive the driver's voice input in real time, analyzes it, and recognizes the driver's emotional state.

[1556] "Means for generating communication messages with pedestrians during autonomous driving and transmitting them outside the vehicle" refers to technology that creates messages for smooth communication with pedestrians during autonomous driving and transmits them to pedestrians through appropriate means (for example, on-board speakers or displays).

[1557] MODE FOR CARRYING OUT THE INVENTION

[1558] The system based on the present invention combines autonomous driving technology with an emotion recognition engine to evaluate the driving condition and emotional state of the driver, and then transitions to autonomous driving mode and provides advice on safe driving. Specific embodiments are described below.

[1559] System Configuration

[1560] The system consists of the following main components:

[1561] 1. User device (smartphone or in-car device)

[1562] 2. Server

[1563] 3. Multiple sensors installed on the vehicle

[1564] 4. Emotion Recognition Engine

[1565] User Device

[1566] The user device is a smartphone or in-car device equipped with a voice recognition function. Voice recognition is performed using the speech_recognition library and the Google Speech Recognition API, which allows the driver's voice feedback to be collected in real time.

[1567] server

[1568] The server has the following features:

[1569] Analysis of collected audio feedback and sensor data

[1570] Determining the driver's driving and emotional state

[1571] Generating safe driving information using generative AI

[1572] Drive suggests transitioning to autonomous driving mode based on driving and emotional state

[1573] Generating communication messages with pedestrians during autonomous driving

[1574] Multiple sensors installed in the vehicle

[1575] The vehicle is equipped with sensors such as a heart rate sensor, a driving time measurement sensor, and a road condition sensor, which collect data in real time and transmit it to a server via the user's terminal.

[1576] Emotion Recognition Engine

[1577] The emotion recognition engine analyzes voice feedback from the user and recognizes the driver's emotional state (e.g., stress, anxiety, fatigue, etc.), and provides appropriate advice to the driver.

[1578] Specific operation example

[1579] For example, suppose a driver begins to feel fatigued or stressed after driving for a long period of time. At this point, the driver provides verbal feedback to the device, saying, "I'm tired." Sensors installed in the vehicle measure a heart rate of 120 bpm and driving time of three hours. This data is sent to the server in real time, and the server determines the driver's state as "fatigued."

[1580] Next, the emotion recognition engine analyzes the voice data and determines that the driver is feeling stressed. Based on this, the server notifies the user's device, "We recommend switching to autonomous driving mode." The generative AI also generates safe driving information to the driver, such as "You seem tired. Please maintain a speed of 60 km / h and thoroughly check for safety." After that, the system switches to autonomous driving mode, and when the vehicle approaches a pedestrian crossing, a message is generated and announced to pedestrians, saying, "A vehicle is waiting to pass. Please wait."

[1581] The above procedure makes it possible to provide safe driving assistance that takes into account the driver's driving condition and emotional state.

[1582] Prompt Sentence Examples

[1583] To illustrate, consider the following scenario:

[1584] User: While driving, say "I'm tired"

[1585] System: Emotion analysis determines "fatigue state" and notifies "We recommend switching to autonomous driving mode"

[1586] In this way, the system of the present invention provides appropriate responses based on the driver's real-time emotional and driving state, thereby improving safety.

[1587] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1588] Step 1:

[1589] The user device collects the driver's voice feedback. Specifically, it uses the speech_recognition library and the Google Speech Recognition API to obtain voice input as text data. This process takes voice data as input and obtains text data as output.

[1590] Step 2:

[1591] Multiple sensors installed in the vehicle collect data such as heart rate, driving time, and road conditions in real time and send it to a server via the user's terminal. The input is real-time data obtained from the sensors, and the output is data sent to the server.

[1592] Step 3:

[1593] The server analyzes the collected voice feedback and sensor data to determine the driver's driving state. Here, the voice data is analyzed using an emotion recognition engine to identify the driver's emotional state. The server also uses sensor data to determine the driver's "fatigue level" and other driving conditions based on heart rate and driving time. The input is the voice feedback and sensor data, and the output is the analysis results.

[1594] Step 4:

[1595] The server suggests switching to autonomous driving mode based on the driver's driving condition and emotional state. For example, if the driver is "fatigued" and "stressed," it generates a message saying "We recommend switching to autonomous driving mode" and sends it to the user's device. The input is the analysis result (driving condition and emotional state), and the output is a suggestion message.

[1596] Step 5:

[1597] The server sends the analysis results to the generative AI, which generates information about safe driving. For example, it generates specific advice such as, "You seem tired. Keep your speed at 60 km / h and make sure to check for safety." The input is the analysis results, and the output is the generated safe driving information.

[1598] Step 6:

[1599] The user device presents the generated safe driving information to the driver. The device communicates the information to the driver using a screen display or audio output. The input is the safe driving information, and the output is a notification or display to the driver.

[1600] Step 7:

[1601] The server generates communication messages for pedestrians during autonomous driving and transmits them outside the vehicle. For example, when approaching a pedestrian crossing, it generates a message saying, "A vehicle is waiting to pass. Please wait," and transmits it through the vehicle's speaker and display. The input is the vehicle's location and situation, and the output is a message to pedestrians.

[1602] The above processing steps realize an automated driving assistance system that takes into account the driver's driving state and emotional state.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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).

[1610] 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.

[1611] 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."

[1612] 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.

[1613] 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).

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] The following is further disclosed regarding the above embodiment.

[1625] (Claim 1)

[1626] a means of collecting audio feedback from users;

[1627] a means for acquiring data from a plurality of sensors mounted on the vehicle;

[1628] a means for analyzing the collected voice feedback and sensor data to determine the driver's driving state;

[1629] A means for suggesting transition to an automated driving mode based on the driver's driving state;

[1630] A means for transmitting the analysis results to the generative AI and generating information related to safe driving;

[1631] a means for presenting the generated information on safe driving to a driver;

[1632] A system that includes a means to generate communication messages with pedestrians and transmit them outside the vehicle during autonomous driving.

[1633] (Claim 2)

[1634] 2. The system of claim 1, wherein the driving condition is a driver fatigue condition.

[1635] (Claim 3)

[1636] 2. The system according to claim 1, wherein the information regarding safe driving includes information regarding a recommended speed and safety checks.

[1637] "Example 1"

[1638] (Claim 1)

[1639] A means of collecting real-time audio feedback from users;

[1640] A means for acquiring data in real time from multiple sensors mounted on a vehicle;

[1641] A means for analyzing and determining the driver's driving state based on the collected voice feedback and sensor data;

[1642] A means for suggesting transition to an automated driving mode based on the driver's driving state;

[1643] A means for transmitting the analysis results to a generative AI model to generate information related to safe driving;

[1644] a means for presenting the generated information on safe driving to a driver;

[1645] A means for generating communication messages with pedestrians during autonomous driving and transmitting them outside the vehicle;

[1646] A system including:

[1647] (Claim 2)

[1648] 2. The system of claim 1, wherein the driving condition is a driver fatigue condition.

[1649] (Claim 3)

[1650] 2. The system according to claim 1, wherein the information about safe driving includes information about recommended speeds and safety checks.

[1651] "Application Example 1"

[1652] (Claim 1)

[1653] a means of collecting audio feedback from users;

[1654] a means for acquiring data from a plurality of sensors mounted on the vehicle;

[1655] a means for analyzing the collected voice feedback and sensor data to determine the driver's driving state;

[1656] A means for suggesting transition to an automated driving mode based on the driver's driving state;

[1657] A means for transmitting the analysis results to a generative AI model and generating information related to safe driving;

[1658] a means for presenting the generated information on safe driving to a driver;

[1659] a means for generating a communication message for a pedestrian when the vehicle approaches the pedestrian and transmitting the message to an outside of the vehicle;

[1660] A system that monitors driving conditions in real time based on sensor data and includes a means to display safe driving information on an in-vehicle terminal or head-mounted display when necessary.

[1661] (Claim 2)

[1662] 2. The system according to claim 1, wherein the driving condition is a driver's fatigue or stress condition.

[1663] (Claim 3)

[1664] 2. The system of claim 1, wherein the information regarding safe driving includes a recommended speed, information regarding safety checks, and prompts for the driver generated using a generative AI model.

[1665] "Example 2: Combining Emotion Engines"

[1666] (Claim 1)

[1667] a means of collecting audio feedback from users;

[1668] a means for acquiring data from a plurality of sensors mounted on the vehicle;

[1669] a means for analyzing the collected voice feedback and sensor data to determine the driver's driving state;

[1670] A means for suggesting transition to an automated driving mode based on the driver's driving state and emotional state;

[1671] A means for transmitting the analysis results to a generative artificial intelligence to generate information related to safe driving;

[1672] a means for presenting the generated information on safe driving to a driver;

[1673] A system that includes a means to generate communication messages with pedestrians and transmit them outside the vehicle during autonomous driving.

[1674] (Claim 2)

[1675] 2. The system of claim 1, wherein the driving conditions are driver fatigue and stress conditions.

[1676] (Claim 3)

[1677] 2. The system according to claim 1, wherein the information regarding safe driving includes information regarding a recommended speed and safety checks.

[1678] "Application example 2 when combining emotion engines"

[1679] (Claim 1)

[1680] a means of collecting audio feedback from users;

[1681] a means for acquiring data from a plurality of sensors mounted on the vehicle;

[1682] a means for analyzing the collected voice feedback and sensor data to determine the driver's driving state;

[1683] A means for suggesting transition to an automated driving mode based on the driver's driving state;

[1684] A means for transmitting the analysis results to the generative AI and generating information related to safe driving;

[1685] a means for presenting the generated information on safe driving to a driver;

[1686] A means for generating communication messages with pedestrians during autonomous driving and transmitting them outside the vehicle;

[1687] A means of recognizing the driver's voice feedback and emotional state in real time via a smartphone device;

[1688] The system includes a means for providing appropriate advice to the driver based on emotion recognition results.

[1689] (Claim 2)

[1690] 2. The system of claim 1, wherein the driving condition is a driver fatigue condition.

[1691] (Claim 3)

[1692] 2. The system according to claim 1, wherein the information regarding safe driving includes information regarding a recommended speed and safety checks. [Explanation of symbols]

[1693] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting audio feedback from users; a means for acquiring data from a plurality of sensors mounted on the vehicle; a means for analyzing the collected voice feedback and sensor data to determine the driver's driving state; A means for suggesting transition to an automated driving mode based on the driver's driving state; A means for transmitting the analysis results to the generative AI and generating information related to safe driving; a means for presenting the generated information on safe driving to a driver; A system that includes a means to generate communication messages with pedestrians and transmit them outside the vehicle during autonomous driving.

2. 2. The system of claim 1, wherein the driving condition is a driver fatigue condition.

3. 2. The system according to claim 1, wherein the information relating to safe driving includes information relating to a recommended speed and safety checks.

Images