system

Abstract

We provide the system. [Solution] A means for receiving video data acquired from a mobile device in operation, A means for analyzing received video data and detecting specific operational behaviors, A means for generating countermeasures appropriate to the situation based on the detected operational behavior, A means of presenting the generated countermeasures to the pilot as audio information, Means of providing information to external organizations as needed, A means of notifying the user terminal of detected danger information and providing visual and audible explanations, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, with the development of transportation, dangerous driving behaviors, especially tailgating, have become a social problem. Such behaviors are highly likely to induce serious accidents, and prompt and effective countermeasures are required. However, since traffic conditions change moment by moment, it is difficult for drivers to instantly come up with appropriate countermeasures. In addition, conventional driving recorders only record information and cannot provide real-time responses. Against this background, there is a need to develop a system that can automatically detect dangerous driving behaviors, propose appropriate countermeasures, and promptly provide information to relevant agencies as needed.

Means for Solving the Problems

[0005] This invention provides a system for analyzing video information acquired in real time from a vehicle. This system uses a generative AI to detect specific dangerous driving behaviors and generates countermeasures appropriate to the situation. The generated countermeasures are presented to the driver as audio information, prompting immediate action. Furthermore, by providing information to external organizations such as the police, medical institutions, and insurance companies as needed, rapid response is possible. This contributes to creating a safe and stress-free driving environment and helps prevent traffic accidents.

[0006] "Vehicles in operation" refers to automobiles and other means of transportation that are moving on the road.

[0007] "Visual information" refers to visual data acquired from camera devices and other sources, and includes image and video data to be analyzed.

[0008] "Means of receiving" refers to methods or devices for obtaining information from other devices or systems.

[0009] "Means of analysis" refers to methods and devices for understanding received information and extracting specific patterns or behaviors.

[0010] "Driving behavior" refers to the actions and manner of driving a vehicle operated by the driver.

[0011] "Means of detection" refers to methods or systems for finding specific conditions or patterns.

[0012] "Means of generation" refers to the process or technology of creating new data or instructions based on existing information.

[0013] "Audio information" refers to instructions and data transmitted by sound, including information provided in a format understandable to the driver.

[0014] "External organizations" refer to organizations such as police, medical institutions, and insurance agencies with which the system may interact.

[0015] "The means of providing" refers to the methods or approaches for transmitting information to other parties or institutions.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the 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.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0030] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The present invention aims to provide a system that analyzes real-time video information acquired from a vehicle, detects dangerous driving behavior, and notifies the driver of appropriate countermeasures. Specifically, it dynamically analyzes driving behavior and identifies dangerous situations by processing video information using a generation AI. The server receives this video information and uses the generation AI engine to analyze the driving situation, including the movements of other vehicles. Furthermore, if dangerous driving behavior is detected, the server accesses a countermeasures database and generates information to propose appropriate countermeasures corresponding to the specific situation.

[0038] This information is sent to the terminal as an audio message and then notified to the user (driver) via the terminal. Based on the presented audio information, the user can take necessary driving actions in a timely manner. Furthermore, this system has a function that automatically provides information to relevant external organizations (police, medical institutions, insurance companies, etc.) via an autonomous AI agent if it determines that the danger is serious. In this way, it is possible to improve driver safety and prevent traffic accidents from occurring.

[0039] For example, if a vehicle rapidly approaches a user's vehicle from behind on a highway, the server detects the vehicle's movement. If the generating AI determines this movement is dangerous, the server immediately generates a voice message saying, "There is a vehicle rapidly approaching from behind. Please adjust your speed," and notifies the user via their device. The user receives this information, adjusts their speed to prevent an accident, and simultaneously notifies external authorities as necessary. This system is innovative in that it processes information in real time and enables instantaneous responses.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server receives real-time video information transmitted from the terminal. The video information is acquired by an in-vehicle camera and includes data capturing the surrounding environment of the vehicle.

[0043] Step 2:

[0044] The server's AI engine analyzes the received video information. Specifically, it uses object recognition algorithms to identify the movement, speed, and direction of other vehicles and obstacles, and evaluates the driving environment.

[0045] Step 3:

[0046] Based on the analysis results, the server evaluates whether to consider a particular driving behavior dangerous. If dangerous behaviors such as aggressive driving or sudden approaches are detected, that driving behavior is identified as dangerous.

[0047] Step 4:

[0048] When dangerous driving behavior is detected, the server accesses a database of countermeasures and generates appropriate countermeasures for the situation. It may also use a generation AI to generate custom messages tailored to new situations.

[0049] Step 5:

[0050] The server converts the generated countermeasures into a voice message and sends it to the terminal. This message is intended to prompt the driver to take specific corrective actions.

[0051] Step 6:

[0052] The terminal plays the voice message received from the server and notifies the user. This allows the user to receive voice warnings or instructions in real time.

[0053] Step 7:

[0054] The user follows the voice message instructions and modifies their driving behavior. For example, they may take actions such as slowing down or changing lanes to avoid potential hazards.

[0055] Step 8:

[0056] If the server determines that the situation is high-risk, it automatically reports the situation to external organizations (e.g., police or medical institutions) according to predefined protocols. This enables a rapid response.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In recent years, the increase in traffic accidents has become a serious problem, hindering people's safe travel. Accidents caused by dangerous driving behavior, in particular, require a swift and accurate response, but current technology is insufficient to efficiently detect them and provide appropriate countermeasures. Therefore, there is a need for technology that can quickly detect dangerous driving behavior while driving and provide appropriate countermeasures to enhance driver safety.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for receiving visual information acquired from a vehicle, means for analyzing the received visual information using a generation AI model to detect dangerous driving behavior, means for generating countermeasures corresponding to specific situations based on the detected dangerous driving behavior, means for presenting the generated countermeasures to the driver as audio information, and means for providing information to an external organization via an autonomous agent when it is determined that the danger is serious. This makes it possible to detect dangerous driving behavior in real time and immediately provide appropriate countermeasures.

[0062] "Visual information" refers to data that indicates the driving environment and surrounding conditions, acquired through visual devices installed in the vehicle.

[0063] A "generative AI model" is a technology that utilizes artificial intelligence built using a deep learning framework to recognize patterns from given data and generate new information.

[0064] "Dangerous driving behavior" refers to driving operations that may violate the Road Traffic Act or vehicle operations that may cause an accident.

[0065] An "autonomous agent" is a software structure that can make decisions and act autonomously without waiting for instructions from an external source.

[0066] "External organizations" refer to organizations related to traffic safety, such as the police, medical facilities, and insurance companies.

[0067] The embodiments for carrying out the invention are described below.

[0068] The server receives visual information acquired from a vision device mounted on the vehicle. This device constantly monitors the vehicle's surroundings and includes high-resolution cameras and sensors. The server has a computing unit for inputting the received visual information into a generative AI model. This generative AI model uses deep learning frameworks such as TENSORFLOW® or PyTorch and is trained to detect dangerous driving behaviors from vast amounts of data.

[0069] The terminal receives voice instructions transmitted from the server and notifies the user, the driver. The primary method of notification is voice guidance transmitted to the driver via a voice output device. This allows the user to take driving actions in real time to prevent accidents.

[0070] As a concrete example, if another vehicle approaches rapidly on a highway, the server uses a generating AI model to analyze the visual information and detect it as a dangerous approach. In this case, an example of a prompt message such as "Another vehicle has been detected approaching rapidly. Please adjust your speed." is fed into the AI ​​model, and an immediate voice message is generated. This voice message is sent to the terminal and notifies the user, "There is a vehicle rapidly approaching from behind. Please adjust your speed."

[0071] This system allows drivers to instantly understand dangerous situations and take appropriate measures, thereby improving safety. The server also utilizes autonomous agents as needed to automatically report the situation to external organizations if an accident is likely. These external organizations include the police, medical institutions, and insurance companies. This approach not only enhances the safety of the driving environment but also helps prevent traffic accidents from occurring.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server receives visual information in real time from the vehicle's mounted visual devices. The input is video footage of the surrounding environment captured by cameras and sensors. This information is quickly transmitted to the server via the vehicle's internet connection. The output is the video data, which is then sent directly to the next analysis step.

[0075] Step 2:

[0076] The server inputs the received visual information into the generating AI model. The input at this stage is the video data received in Step 1. The generating AI model utilizes deep learning technology to perform object recognition and behavioral analysis. Specifically, the AI ​​model analyzes vehicles and road conditions in the video and detects dangerous driving behavior. The output is the analysis result, including whether or not dangerous driving behavior occurred and its details.

[0077] Step 3:

[0078] The server receives the analysis results from the generated AI model and, if dangerous driving behavior is detected, generates appropriate countermeasures. The input includes the analysis results from step 2. For data processing, it refers to the countermeasures database and selects appropriate countermeasures. The output is a voice message to be presented to the driver.

[0079] Step 4:

[0080] The generated voice message is sent from the server to the terminal. The input is the voice message generated in step 3, which the terminal receives. Specifically, the terminal notifies the driver of the voice message. This notification is made through a voice output device. The output provides instructions for the driver to drive safely.

[0081] Step 5:

[0082] The user receives voice messages from the device and adjusts driving operations as needed. The input is voice notifications, specifically instructions such as speed adjustments or lane changes. The output is ensuring the safety of driving behavior.

[0083] Step 6:

[0084] If the server determines the level of danger to be serious, information will be provided to external organizations via an autonomous agent. The input is the risk assessment based on the analysis results from step 2 and the judgment from step 3. As part of the data processing, the necessary information is packaged and automatically notified to external organizations. The output is notification to organizations involved in traffic safety.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] In recent years, with the advancement of autonomous driving technology, the demand for systems to support safe driving has increased. However, many existing systems are limited to detecting and notifying drivers of dangerous driving, and are insufficient in providing concrete response options to drivers or automatic external notifications for serious dangers. Furthermore, mechanisms that allow users to visually and easily understand their situation while driving are not adequately developed. Against this backdrop, there is a need for new systems that reduce the risk of accidents in autonomous vehicles and for ordinary drivers, and improve safety while driving.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for receiving video data acquired from a mobile device in operation, means for analyzing the received video data and detecting specific operational behaviors, and means for notifying the user terminal of the detected danger information and explaining it visually and audibly. This makes it possible for drivers to obtain specific and appropriate countermeasures in real time while driving, dramatically improving driving safety.

[0090] "Mobility devices" is a general term for automatically or manually operated means of transportation used for moving on the ground.

[0091] "Video data" refers to digital visual information used to visually capture the surroundings of a mobile device.

[0092] "Analysis" is the process of extracting specific information or patterns from acquired data.

[0093] "Operational behavior" refers to the characteristics of specific actions or behaviors performed by a mobile device.

[0094] "Countermeasures" refer to guidelines or means for taking appropriate responses or actions in a specific situation.

[0095] "Audio information" refers to information transmitted through hearing, and is typically used as announcements or guide voices.

[0096] "External organizations" refer to external governing bodies or protective services related to the operation of mobile devices.

[0097] A "user terminal" refers to an electronic device used by drivers or administrators to receive information.

[0098] "Visual explanation" refers to illustrative or video methods used to convey information to users through visual media.

[0099] The invention describes embodiments for carrying out the invention. This system includes a mobile device, a server, and a user terminal. The server receives real-time video data from the mobile device equipped with a video sensor and analyzes the data to detect specific operational behaviors. This analysis uses a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to perform object identification and identify movement patterns. The server generates appropriate countermeasures according to the degree of the detected danger. These countermeasures are transmitted as audio information to the user terminal and notified to the operator via the terminal. The terminal presents detailed explanations so that the user can understand the situation visually and audibly.

[0100] Furthermore, this system has a function that automatically sends notifications to external organizations such as law enforcement agencies, medical institutions, and insurance companies if the danger is deemed serious. This allows users to act quickly and appropriately even in situations where immediate action is required.

[0101] For example, if the surrounding environment is inclement weather and visibility is poor, the server analyzes the situation and sends a voice notification to the user's terminal saying, "Due to poor visibility, please slow down." This allows the driver to take appropriate driving actions.

[0102] An example of a prompt to input into the generating AI model would be: "Analyze the real-time video footage obtained from the vehicle's sensors and identify potential obstacles and dangerous driving behaviors."

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server receives video data in real time from cameras and sensors mounted on the mobile device. The input is raw data from the cameras and sensors, while the output is digital video data for use within the server. Specifically, data from the sensors is transferred to the server via the network.

[0106] Step 2:

[0107] The server analyzes the received video data using a generating AI model. The input is the digital video data obtained in step 1, and the output is information about the identified operational behavior. The server inputs this video into the AI ​​model and performs data processing to identify object recognition and motion patterns.

[0108] Step 3:

[0109] The server assesses the risk level based on the analysis and generates countermeasures. The input is information about the operational behavior obtained in step 2, and the output is data showing specific countermeasures. Specifically, it refers to a pre-configured database of countermeasures based on the risk level and selects the appropriate countermeasure.

[0110] Step 4:

[0111] The server sends the generated countermeasures as voice information to the user's terminal. The input is the countermeasure data obtained in step 3, and the output is the voice message notified to the user. A speech synthesis engine is used to convert the countermeasures into voice format and send them to the terminal over the network.

[0112] Step 5:

[0113] The device notifies the user of the received audio information and also provides a visual explanation of the situation. The input is the audio message received in step 4, and the output is the notification action to the user. The device plays the audio through the speaker and displays the visual information on the display.

[0114] Step 6:

[0115] If the risk is serious, the server automatically notifies external organizations. The input is the risk level information obtained in step 3, and the output is the notification to the relevant organizations. The server automatically sends the necessary information to external organizations via email or API.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention relates to a system that analyzes video information acquired from a vehicle in motion, and by combining it with an emotion engine, recognizes the user's emotional state and further enhances driving assistance. This system understands the user's emotional state while driving and analyzes driving behavior in real time. The server uses video information received from the terminal to evaluate the surrounding traffic situation by combining generation AI and object recognition technology, and if dangerous driving behavior is detected, it generates countermeasures and provides them to the driver.

[0118] Furthermore, the emotion engine analyzes the user's facial expressions and voice tone to identify their emotional state. Based on this, it determines how the user's mental state is affecting their driving and adjusts countermeasures as needed. For example, if the user is feeling stressed, it can offer suggestions for relaxation.

[0119] The server integrates data obtained from video information with the results of the emotion engine's analysis to generate the most appropriate action for the driver as an audio message, which is then presented to the user via the terminal. This process is also integrated with a means of sharing information with external organizations and has the function to automatically notify the police, medical institutions, etc., as needed.

[0120] As a concrete example, consider a situation where a user is driving on a highway and a vehicle suddenly appears to overtake them. The server detects this sudden approach through a generating AI and, after analysis by an emotion engine, determines that the user is feeling stressed. Based on this result, the server generates a response such as "Take a deep breath and act calmly," and instructs the user via the terminal. In this way, the present invention realizes driving assistance that minimizes stress while maintaining driver safety.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The terminal transmits video information acquired through the vehicle's in-vehicle camera to the server. This information includes video footage of the driver's face and the traffic conditions around the vehicle.

[0124] Step 2:

[0125] The server receives video information and uses object recognition technology to analyze the traffic situation around the vehicle. This allows it to identify the movement and position of other vehicles and evaluate the driving environment.

[0126] Step 3:

[0127] The server uses generated AI to analyze the driving environment and determine whether dangerous driving behavior exists. For example, it can detect a vehicle approaching rapidly and identify that behavior as aggressive driving.

[0128] Step 4:

[0129] The server activates an emotion engine and analyzes facial expressions and voice tone from the driver's facial video. This analysis identifies the user's emotional state and assesses levels of stress and tension, for example.

[0130] Step 5:

[0131] The server integrates the analyzed driving conditions and emotional state, and generates the optimal countermeasures accordingly. These countermeasures take into account the driver's mental state.

[0132] Step 6:

[0133] The server converts the generated countermeasures into an audio message and sends it to the user via the terminal. The user can receive this message by voice.

[0134] Step 7:

[0135] The user adjusts their driving appropriately by following voice instructions from the device. For example, they may be prompted to act calmly.

[0136] Step 8:

[0137] If necessary, the server will process information sharing with external organizations. In cases where the risk is deemed particularly high, notifications will be automatically sent to the police and medical institutions.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] In transportation systems, there is a need to consider the impact of the driver's psychological state on driving behavior and to realize safer and more comfortable driving assistance. Current driving assistance systems lack the function to understand the driver's emotional state in real time and provide appropriate measures based on that understanding. As a result, there is a challenge in that appropriate support cannot be provided when the driver is experiencing stress or anxiety.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for receiving video data acquired from a transport vehicle in operation, means for analyzing the received video and audio data to detect the user's emotional state and specific driving behaviors, and means for generating situation-appropriate countermeasures based on the detected driving behaviors and emotional state using a generative AI model and emotion analysis technology. This enables driving assistance that takes the driver's emotional state into consideration in real time.

[0143] "Video data" refers to image or video information acquired by cameras and sensors mounted on transportation equipment while it is in operation, and is fundamental information for understanding the driving environment and surrounding conditions.

[0144] "Voice data" refers to data collected from the driver's voice and surrounding sounds, and is used to analyze the driver's emotional state and environmental sounds.

[0145] A "generative AI model" is an artificial intelligence technology that uses learning algorithms to analyze specific patterns and actions, and generates reasoning and countermeasures necessary for driver assistance.

[0146] "Emotional analysis technology" is a technology that analyzes facial expressions and voice characteristics to identify a user's emotional state, and is used to understand the driver's psychological state.

[0147] "Object recognition technology" is a technology that detects objects such as other transportation equipment and obstacles based on video data, and analyzes their position and movement patterns.

[0148] "External organizations" refer to relevant organizations that provide or receive information related to driving, including safety maintenance organizations, medical organizations, and protective organizations.

[0149] "Driving assistance messages" are voice messages generated to provide drivers with situation-appropriate instructions and advice.

[0150] This invention is a system that analyzes the driver's emotional state using video and audio data acquired from a vehicle in operation, thereby supporting safe and comfortable driving. Information transmission and analysis primarily occur between a server, a terminal, and the user.

[0151] The server receives video and audio data acquired from the terminal and begins data processing. This uses terminals equipped with high-resolution cameras and high-performance microphones to accurately record the driving environment and the driver's condition. The server analyzes the received video data using a generating AI model and object recognition technology to understand the surrounding traffic conditions and specific driving behaviors. In this process, it identifies other vehicles and obstacles and assesses potential hazards to the driver.

[0152] Simultaneously, the server analyzes voice data and driver facial expression data using emotion analysis technology to identify the driver's emotional state. Emotion analysis technology is used to determine tension, stress, and relaxation from voice tone and facial expressions. Based on these analysis results, the server evaluates how the driver's emotional state is influencing their actual driving behavior.

[0153] The server uses a generative AI model to comprehensively analyze traffic conditions and emotional states, and generates optimal driving assistance messages for the user. This is done using automated voice message generation software, and the generated messages are sent to the terminal and presented to the driver. For example, if a driver feels tense due to a vehicle rapidly approaching on a highway, they might be given instructions such as, "Take a deep breath and calm down."

[0154] This system also has the capability to share information with external organizations as needed. This makes it possible to notify safety maintenance agencies and medical organizations of abnormal situations during operation in real time.

[0155] An example of a prompt would be, "Please suggest an appropriate driver assistance message for when an overtaking vehicle suddenly appears while driving on a highway." This prompt allows the generating AI model to quickly generate appropriate countermeasures.

[0156] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0157] Step 1:

[0158] The terminal collects video and audio data using cameras and microphones mounted on the transport vehicle while it is in motion. This data is transmitted to a server in real time. The input is video from the camera and audio from the microphone, and the output is the complete set of this data.

[0159] Step 2:

[0160] The server analyzes the video data received from the terminal using a generating AI model and object recognition technology. Specifically, it detects other objects in the video, such as other transportation equipment, pedestrians, and traffic lights, and analyzes their movement and position. The input is the video data from step 1, and the output is the detected object information and its movement pattern.

[0161] Step 3:

[0162] The server analyzes the received audio data using emotion analysis technology to identify the driver's emotional state. It reads emotions such as tension, stress, and relaxation from the voice tone and speech patterns. The input is the audio data from step 1, and the output is the identified emotional state.

[0163] Step 4:

[0164] The server integrates the analysis results from steps 2 and 3 and uses a generative AI model to generate optimal driving assistance messages for the driver. It determines how the driver should respond based on traffic conditions and emotional state. The input is detected object information and emotional state, and the output is the generated driving assistance message.

[0165] Step 5:

[0166] The server sends the generated driver assistance message to the terminal, which then presents it to the driver. Specifically, it is output as an audio message through the speaker, conveying instructions and advice to the driver. The input is the driver assistance message from step 4, and the output is the presentation of the audio message.

[0167] Step 6:

[0168] If necessary, the server notifies external organizations of the driving status and the driver's condition. For example, if dangerous driving continues, information is automatically sent to safety maintenance organizations or medical organizations. The input is the analysis results from steps 2 to 4, and the output is the notification information sent to external organizations.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0171] There is a need for a system that provides appropriate driving assistance information that takes into account the emotional state of the driver while driving, thereby reducing driver stress and tension and improving safety. Furthermore, a system that allows for smooth information sharing with external organizations based on surrounding conditions and the driver's state is also required.

[0172] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0173] In this invention, the server includes means for receiving video information and the user's emotional state acquired from a vehicle in motion, means for analyzing the received information to detect specific driving behaviors and emotional states, and means for generating countermeasures appropriate to the situation based on the detected driving behaviors and emotional states. This enables real-time driving assistance that takes the user's emotional state into consideration.

[0174] "Vehicle in operation" refers to a vehicle that is moving or stationary, and that is engaged in the act of driving on a road.

[0175] "Visual information" refers to visual data acquired from cameras and sensor devices, including information such as the position and movement of objects.

[0176] "Emotional state" refers to the psychological and emotional state the user is experiencing, and is judged from facial expressions, tone of voice, and other factors.

[0177] "Analysis" refers to the process of deciphering data and extracting useful information, particularly for recognizing emotional states and driving behavior.

[0178] "Object recognition technology" is a technology that detects specific objects based on video information and identifies their location and movement.

[0179] "Countermeasure generation" is the process of designing and creating specific actions and advice to mitigate the risks associated with detected driving behaviors and emotional states.

[0180] "Visual information" refers to information that is visually perceptible and presented to the user through a display device.

[0181] "External organizations" are third-party organizations that interact with the system and exchange information, and include public safety agencies, medical service providers, and property insurance companies.

[0182] This invention is implemented as a system that analyzes video information acquired from a vehicle in motion and the user's emotional state to provide appropriate driving assistance. The server receives video and audio data from endpoints using a camera and microphone. This includes, for example, a camera and microphone mounted on smart glasses. The server analyzes this data using an image analysis library (e.g., OpenCV) and an audio analysis library (e.g., Google® Cloud Speech-to-Text). Subsequently, it utilizes an emotion recognition API (e.g., Microsoft® Azure® Emotion API) to analyze the user's facial expressions and voice tone and identify their emotional state.

[0183] The analyzed data is integrated with a generative AI and used in a process to generate optimal actions to promote safe driving. The generated actions are presented to the user through visual and audio interfaces. Visual information is displayed on the smart glasses' screen, and audio information is provided via the voice speaker.

[0184] For example, if a user shows signs of frustration while stuck in traffic, the system can offer suggestions such as, "Would you like to play your favorite music to relax?" Another example of a prompt might be, "Evaluate the user's stress level based on their facial expression data and come up with specific advice to reduce the driver's stress." In this way, the system can support a safer and less stressful driving experience.

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The server receives video and audio data through the camera and microphone attached to the terminal. The input is raw data including the user's facial expressions and voice tone, and the output is data in a format suitable for analysis. This input data is analyzed in the next step, ensuring high-quality data processing.

[0188] Step 2:

[0189] The server uses an image analysis library (e.g., OpenCV) to extract important features from video data. In this step, video data is used as input, and facial feature points (eyes, mouth shape, etc.) are obtained as output. Based on this data, data processing is performed to estimate the user's emotions.

[0190] Step 3:

[0191] The server analyzes audio data using a speech analysis library (e.g., Google Cloud Speech-to-Text). The input is audio data, and the output is tone and pitch information extracted from the speech. This analyzed data is then used to perform data calculations to infer specific emotions.

[0192] Step 4:

[0193] The server utilizes an emotion recognition API (e.g., Microsoft Azure Emotion API) to integrate the data obtained in steps 2 and 3 to identify the user's emotional state. The input consists of facial features and voice tone data, and the output is an estimated result of the emotional state. This process is a crucial step that forms the basis of generative AI.

[0194] Step 5:

[0195] The server inputs emotional state information into a generating AI model and generates appropriate countermeasures for the driving situation. The input consists of emotional state and driving behavior data, and the output generates specific actions and advice. This output is then presented to the user in the next step.

[0196] Step 6:

[0197] The terminal presents generated advice to the user via visual and audio interfaces. The input is the generated countermeasure information, and the output is the display of visual information on the terminal's screen and voice guidance through the speaker. This allows the user to receive driving assistance information in real time.

[0198] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0199] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0200] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0201] [Second Embodiment]

[0202] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0203] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0204] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0205] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0206] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0207] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0208] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0209] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0210] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0211] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0212] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0213] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0214] The present invention aims to provide a system that analyzes real-time video information acquired from a vehicle, detects dangerous driving behavior, and notifies the driver of appropriate countermeasures. Specifically, it dynamically analyzes driving behavior and identifies dangerous situations by processing video information using a generation AI. The server receives this video information and uses the generation AI engine to analyze the driving situation, including the movements of other vehicles. Furthermore, if dangerous driving behavior is detected, the server accesses a countermeasures database and generates information to propose appropriate countermeasures corresponding to the specific situation.

[0215] This information is sent to the terminal as an audio message and then notified to the user (driver) via the terminal. Based on the presented audio information, the user can take necessary driving actions in a timely manner. Furthermore, this system has a function that automatically provides information to relevant external organizations (police, medical institutions, insurance companies, etc.) via an autonomous AI agent if it determines that the danger is serious. In this way, it is possible to improve driver safety and prevent traffic accidents from occurring.

[0216] For example, if a vehicle rapidly approaches a user's vehicle from behind on a highway, the server detects the vehicle's movement. If the generating AI determines this movement is dangerous, the server immediately generates a voice message saying, "There is a vehicle rapidly approaching from behind. Please adjust your speed," and notifies the user via their device. The user receives this information, adjusts their speed to prevent an accident, and simultaneously notifies external authorities as necessary. This system is innovative in that it processes information in real time and enables instantaneous responses.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The server receives real-time video information transmitted from the terminal. The video information is acquired by an in-vehicle camera and includes data capturing the surrounding environment of the vehicle.

[0220] Step 2:

[0221] The server's AI engine analyzes the received video information. Specifically, it uses object recognition algorithms to identify the movement, speed, and direction of other vehicles and obstacles, and evaluates the driving environment.

[0222] Step 3:

[0223] Based on the analysis results, the server evaluates whether to consider a particular driving behavior dangerous. If dangerous behaviors such as aggressive driving or sudden approaches are detected, that driving behavior is identified as dangerous.

[0224] Step 4:

[0225] When dangerous driving behavior is detected, the server accesses a database of countermeasures and generates appropriate countermeasures for the situation. It may also use a generation AI to generate custom messages tailored to new situations.

[0226] Step 5:

[0227] The server converts the generated countermeasures into a voice message and sends it to the terminal. This message is intended to prompt the driver to take specific corrective actions.

[0228] Step 6:

[0229] The terminal plays the voice message received from the server and notifies the user. This allows the user to receive voice warnings or instructions in real time.

[0230] Step 7:

[0231] The user follows the voice message instructions and modifies their driving behavior. For example, they may take actions such as slowing down or changing lanes to avoid potential hazards.

[0232] Step 8:

[0233] If the server determines that the situation is high-risk, it automatically reports the situation to external organizations (e.g., police or medical institutions) according to predefined protocols. This enables a rapid response.

[0234] (Example 1)

[0235] Next, we will describe Example 1. 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".

[0236] In recent years, the increase in traffic accidents has become a serious problem, hindering people's safe travel. Accidents caused by dangerous driving behavior, in particular, require a swift and accurate response, but current technology is insufficient to efficiently detect them and provide appropriate countermeasures. Therefore, there is a need for technology that can quickly detect dangerous driving behavior while driving and provide appropriate countermeasures to enhance driver safety.

[0237] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0238] In this invention, the server includes means for receiving visual information acquired from a vehicle, means for analyzing the received visual information using a generation AI model to detect dangerous driving behavior, means for generating countermeasures corresponding to specific situations based on the detected dangerous driving behavior, means for presenting the generated countermeasures to the driver as audio information, and means for providing information to an external organization via an autonomous agent when it is determined that the danger is serious. This makes it possible to detect dangerous driving behavior in real time and immediately provide appropriate countermeasures.

[0239] "Visual information" refers to data that indicates the driving environment and surrounding conditions, acquired through visual devices installed in the vehicle.

[0240] A "generative AI model" is a technology that utilizes artificial intelligence built using a deep learning framework to recognize patterns from given data and generate new information.

[0241] "Dangerous driving behavior" refers to driving operations that may violate the Road Traffic Act or vehicle operations that may cause an accident.

[0242] An "autonomous agent" is a software structure that can make decisions and act autonomously without waiting for instructions from an external source.

[0243] "External organizations" refer to organizations related to traffic safety, such as the police, medical facilities, and insurance companies.

[0244] The embodiments for carrying out the invention are described below.

[0245] The server receives visual information acquired from a vision device mounted on the vehicle. This device constantly monitors the vehicle's surroundings and includes high-resolution cameras and sensors. The server has a computing unit to input the received visual information into a generative AI model. This generative AI model uses deep learning frameworks such as TensorFlow or PyTorch and is trained to detect dangerous driving behaviors from vast amounts of data.

[0246] The terminal receives voice instructions transmitted from the server and notifies the user, the driver. The primary method of notification is voice guidance transmitted to the driver via a voice output device. This allows the user to take driving actions in real time to prevent accidents.

[0247] As a concrete example, if another vehicle approaches rapidly on a highway, the server uses a generating AI model to analyze the visual information and detect it as a dangerous approach. In this case, an example of a prompt message such as "Another vehicle has been detected approaching rapidly. Please adjust your speed." is fed into the AI ​​model, and an immediate voice message is generated. This voice message is sent to the terminal and notifies the user, "There is a vehicle rapidly approaching from behind. Please adjust your speed."

[0248] This system allows drivers to instantly understand dangerous situations and take appropriate measures, thereby improving safety. The server also utilizes autonomous agents as needed to automatically report the situation to external organizations if an accident is likely. These external organizations include the police, medical institutions, and insurance companies. This approach not only enhances the safety of the driving environment but also helps prevent traffic accidents from occurring.

[0249] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0250] Step 1:

[0251] The server receives visual information in real time from the vehicle's mounted visual devices. The input is video footage of the surrounding environment captured by cameras and sensors. This information is quickly transmitted to the server via the vehicle's internet connection. The output is the video data, which is then sent directly to the next analysis step.

[0252] Step 2:

[0253] The server inputs the received visual information into the generating AI model. The input at this stage is the video data received in Step 1. The generating AI model utilizes deep learning technology to perform object recognition and behavioral analysis. Specifically, the AI ​​model analyzes vehicles and road conditions in the video and detects dangerous driving behavior. The output is the analysis result, including whether or not dangerous driving behavior occurred and its details.

[0254] Step 3:

[0255] The server receives the analysis results from the generated AI model and, if dangerous driving behavior is detected, generates appropriate countermeasures. The input includes the analysis results from step 2. For data processing, it refers to the countermeasures database and selects appropriate countermeasures. The output is a voice message to be presented to the driver.

[0256] Step 4:

[0257] The generated voice message is sent from the server to the terminal. The input is the voice message generated in step 3, which the terminal receives. Specifically, the terminal notifies the driver of the voice message. This notification is made through a voice output device. The output provides instructions for the driver to drive safely.

[0258] Step 5:

[0259] The user receives voice messages from the device and adjusts driving operations as needed. The input is voice notifications, specifically instructions such as speed adjustments or lane changes. The output is ensuring the safety of driving behavior.

[0260] Step 6:

[0261] If the server determines the level of danger to be serious, information will be provided to external organizations via an autonomous agent. The input is the risk assessment based on the analysis results from step 2 and the judgment from step 3. As part of the data processing, the necessary information is packaged and automatically notified to external organizations. The output is notification to organizations involved in traffic safety.

[0262] (Application Example 1)

[0263] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] In recent years, with the advancement of autonomous driving technology, the demand for systems to support safe driving has increased. However, many existing systems are limited to detecting and notifying drivers of dangerous driving, and are insufficient in providing concrete response options to drivers or automatic external notifications for serious dangers. Furthermore, mechanisms that allow users to visually and easily understand their situation while driving are not adequately developed. Against this backdrop, there is a need for new systems that reduce the risk of accidents in autonomous vehicles and for ordinary drivers, and improve safety while driving.

[0265] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0266] In this invention, the server includes means for receiving video data acquired from a mobile device in operation, means for analyzing the received video data and detecting specific operational behaviors, and means for notifying the user terminal of the detected danger information and explaining it visually and audibly. This makes it possible for drivers to obtain specific and appropriate countermeasures in real time while driving, dramatically improving driving safety.

[0267] "Mobility devices" is a general term for automatically or manually operated means of transportation used for moving on the ground.

[0268] "Video data" refers to digital visual information used to visually capture the surroundings of a mobile device.

[0269] "Analysis" is the process of extracting specific information or patterns from acquired data.

[0270] "Operational behavior" refers to the characteristics of specific actions or behaviors performed by a mobile device.

[0271] "Countermeasures" refer to guidelines or means for taking appropriate responses or actions in a specific situation.

[0272] "Audio information" refers to information transmitted through hearing, and is typically used as announcements or guide voices.

[0273] "External organizations" refer to external governing bodies or protective services related to the operation of mobile devices.

[0274] A "user terminal" refers to an electronic device used by drivers or administrators to receive information.

[0275] "Visual explanation" refers to illustrative or video methods used to convey information to users through visual media.

[0276] The invention describes embodiments for carrying out the invention. This system includes a mobile device, a server, and a user terminal. The server receives real-time video data from the mobile device equipped with a video sensor and analyzes the data to detect specific operational behaviors. This analysis uses a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to perform object identification and identify movement patterns. The server generates appropriate countermeasures according to the degree of the detected danger. These countermeasures are transmitted as audio information to the user terminal and notified to the operator via the terminal. The terminal presents detailed explanations so that the user can understand the situation visually and audibly.

[0277] Furthermore, this system has a function that automatically sends notifications to external organizations such as law enforcement agencies, medical institutions, and insurance companies if the danger is deemed serious. This allows users to act quickly and appropriately even in situations where immediate action is required.

[0278] For example, if the surrounding environment is inclement weather and visibility is poor, the server analyzes the situation and sends a voice notification to the user's terminal saying, "Due to poor visibility, please slow down." This allows the driver to take appropriate driving actions.

[0279] As an example of a prompt sentence to be input into the generation AI model, "Analyze the real-time video obtained from the vehicle's sensors and identify possible traffic obstacles and dangerous driving behaviors." can be considered.

[0280] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0281] Step 1:

[0282] The server receives video data in real time from cameras and sensors installed in the mobile device. The input is raw data from the cameras and sensors, and the output is digital video data for use within the server. As a specific operation, the data from the sensors is transferred to the server via the network.

[0283] Step 2:

[0284] The server analyzes the received video data using the generation AI model. The input is the digital video data obtained in Step 1, and the output is information about the identified operation behaviors. The server inputs this video into the AI model and performs data processing to identify object recognition and motion patterns.

[0285] Step 3:

[0286] The server evaluates the risk level based on the analysis and generates countermeasures. The input is the information about the operation behaviors obtained in Step 2, and the output is data indicating specific countermeasures. As a specific operation, it refers to a pre-set countermeasure database according to the risk level and selects the corresponding countermeasure.

[0287] Step 4:

[0288] The server sends the generated countermeasures as voice information to the user's terminal. The input is the countermeasure data obtained in step 3, and the output is the voice message notified to the user. A speech synthesis engine is used to convert the countermeasures into voice format and send them to the terminal over the network.

[0289] Step 5:

[0290] The device notifies the user of the received audio information and also provides a visual explanation of the situation. The input is the audio message received in step 4, and the output is the notification action to the user. The device plays the audio through the speaker and displays the visual information on the display.

[0291] Step 6:

[0292] If the risk is serious, the server automatically notifies external organizations. The input is the risk level information obtained in step 3, and the output is the notification to the relevant organizations. The server automatically sends the necessary information to external organizations via email or API.

[0293] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0294] This invention relates to a system that analyzes video information acquired from a vehicle in motion, and by combining it with an emotion engine, recognizes the user's emotional state and further enhances driving assistance. This system understands the user's emotional state while driving and analyzes driving behavior in real time. The server uses video information received from the terminal to evaluate the surrounding traffic situation by combining generation AI and object recognition technology, and if dangerous driving behavior is detected, it generates countermeasures and provides them to the driver.

[0295] Furthermore, the emotion engine analyzes the user's facial expressions and voice tone to identify their emotional state. Based on this, it determines how the user's mental state is affecting their driving and adjusts countermeasures as needed. For example, if the user is feeling stressed, it can offer suggestions for relaxation.

[0296] The server integrates data obtained from video information with the results of the emotion engine's analysis to generate the most appropriate action for the driver as an audio message, which is then presented to the user via the terminal. This process is also integrated with a means of sharing information with external organizations and has the function to automatically notify the police, medical institutions, etc., as needed.

[0297] As a concrete example, consider a situation where a user is driving on a highway and a vehicle suddenly appears to overtake them. The server detects this sudden approach through a generating AI and, after analysis by an emotion engine, determines that the user is feeling stressed. Based on this result, the server generates a response such as "Take a deep breath and act calmly," and instructs the user via the terminal. In this way, the present invention realizes driving assistance that minimizes stress while maintaining driver safety.

[0298] The following describes the processing flow.

[0299] Step 1:

[0300] The terminal transmits video information acquired through the vehicle's in-vehicle camera to the server. This information includes video footage of the driver's face and the traffic conditions around the vehicle.

[0301] Step 2:

[0302] The server receives video information and uses object recognition technology to analyze the traffic situation around the vehicle. This allows it to identify the movement and position of other vehicles and evaluate the driving environment.

[0303] Step 3:

[0304] The server uses generative AI to determine whether there are any dangerous driving behaviors from the analysis results of the driving environment. For example, it detects an approaching vehicle and identifies its behavior as tailgating.

[0305] Step 4:

[0306] The server activates the emotion engine and analyzes the facial expressions and vocal tones from the driver's face video. Through this analysis, it identifies the user's emotional state and evaluates, for example, the levels of stress and tension.

[0307] Step 5:

[0308] The server integrates the analyzed driving situation and emotional state and generates an optimal countermeasure accordingly. This countermeasure takes into account the driver's mental state.

[0309] Step 6:

[0310] The server converts the generated countermeasure into an audio message and sends it to the user through the terminal. The user can receive this message audibly.

[0311] Step 7:

[0312] The user adjusts their driving appropriately according to the voice instructions from the terminal. For example, they may be prompted to act calmly.

[0313] Step 8:

[0314] If necessary, the server executes a process of providing information to external institutions. Particularly when it is determined that the risk level is high, automatic notifications are sent to the police and medical institutions.

[0315] (Example 2)

[0316] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0317] In transportation systems, there is a need to consider the impact of the driver's psychological state on driving behavior and to realize safer and more comfortable driving assistance. Current driving assistance systems lack the function to understand the driver's emotional state in real time and provide appropriate measures based on that understanding. As a result, there is a challenge in that appropriate support cannot be provided when the driver is experiencing stress or anxiety.

[0318] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0319] In this invention, the server includes means for receiving video data acquired from a transport vehicle in operation, means for analyzing the received video and audio data to detect the user's emotional state and specific driving behaviors, and means for generating situation-appropriate countermeasures based on the detected driving behaviors and emotional state using a generative AI model and emotion analysis technology. This enables driving assistance that takes the driver's emotional state into consideration in real time.

[0320] "Video data" refers to image or video information acquired by cameras and sensors mounted on transportation equipment while it is in operation, and is fundamental information for understanding the driving environment and surrounding conditions.

[0321] "Voice data" refers to data collected from the driver's voice and surrounding sounds, and is used to analyze the driver's emotional state and environmental sounds.

[0322] A "generative AI model" is an artificial intelligence technology that uses learning algorithms to analyze specific patterns and actions, and generates reasoning and countermeasures necessary for driver assistance.

[0323] "Emotional analysis technology" is a technology that analyzes facial expressions and voice characteristics to identify a user's emotional state, and is used to understand the driver's psychological state.

[0324] "Object recognition technology" is a technology that detects objects such as other transportation equipment and obstacles based on video data, and analyzes their position and movement patterns.

[0325] "External organizations" refer to relevant organizations that provide or receive information related to driving, including safety maintenance organizations, medical organizations, and protective organizations.

[0326] "Driving assistance messages" are voice messages generated to provide drivers with situation-appropriate instructions and advice.

[0327] This invention is a system that analyzes the driver's emotional state using video and audio data acquired from a vehicle in operation, thereby supporting safe and comfortable driving. Information transmission and analysis primarily occur between a server, a terminal, and the user.

[0328] The server receives video and audio data acquired from the terminal and begins data processing. This uses terminals equipped with high-resolution cameras and high-performance microphones to accurately record the driving environment and the driver's condition. The server analyzes the received video data using a generating AI model and object recognition technology to understand the surrounding traffic conditions and specific driving behaviors. In this process, it identifies other vehicles and obstacles and assesses potential hazards to the driver.

[0329] Simultaneously, the server analyzes voice data and driver facial expression data using emotion analysis technology to identify the driver's emotional state. Emotion analysis technology is used to determine tension, stress, and relaxation from voice tone and facial expressions. Based on these analysis results, the server evaluates how the driver's emotional state is influencing their actual driving behavior.

[0330] The server uses a generative AI model to comprehensively analyze traffic conditions and emotional states, and generates optimal driving assistance messages for the user. This is done using automated voice message generation software, and the generated messages are sent to the terminal and presented to the driver. For example, if a driver feels tense due to a vehicle rapidly approaching on a highway, they might be given instructions such as, "Take a deep breath and calm down."

[0331] This system also has the capability to share information with external organizations as needed. This makes it possible to notify safety maintenance agencies and medical organizations of abnormal situations during operation in real time.

[0332] An example of a prompt would be, "Please suggest an appropriate driver assistance message for when an overtaking vehicle suddenly appears while driving on a highway." This prompt allows the generating AI model to quickly generate appropriate countermeasures.

[0333] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0334] Step 1:

[0335] The terminal collects video and audio data using cameras and microphones mounted on the transport vehicle while it is in motion. This data is transmitted to a server in real time. The input is video from the camera and audio from the microphone, and the output is the complete set of this data.

[0336] Step 2:

[0337] The server analyzes the video data received from the terminal using a generating AI model and object recognition technology. Specifically, it detects other objects in the video, such as other transportation equipment, pedestrians, and traffic lights, and analyzes their movement and position. The input is the video data from step 1, and the output is the detected object information and its movement pattern.

[0338] Step 3:

[0339] The server analyzes the received audio data using emotion analysis technology to identify the driver's emotional state. It reads emotions such as tension, stress, and relaxation from the voice tone and speech patterns. The input is the audio data from step 1, and the output is the identified emotional state.

[0340] Step 4:

[0341] The server integrates the analysis results from steps 2 and 3 and uses a generative AI model to generate optimal driving assistance messages for the driver. It determines how the driver should respond based on traffic conditions and emotional state. The input is detected object information and emotional state, and the output is the generated driving assistance message.

[0342] Step 5:

[0343] The server sends the generated driver assistance message to the terminal, which then presents it to the driver. Specifically, it is output as an audio message through the speaker, conveying instructions and advice to the driver. The input is the driver assistance message from step 4, and the output is the presentation of the audio message.

[0344] Step 6:

[0345] If necessary, the server notifies external organizations of the driving status and the driver's condition. For example, if dangerous driving continues, information is automatically sent to safety maintenance organizations or medical organizations. The input is the analysis results from steps 2 to 4, and the output is the notification information sent to external organizations.

[0346] (Application Example 2)

[0347] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0348] There is a need for a system that provides appropriate driving assistance information that takes into account the emotional state of the driver while driving, thereby reducing driver stress and tension and improving safety. Furthermore, a system that allows for smooth information sharing with external organizations based on surrounding conditions and the driver's state is also required.

[0349] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0350] In this invention, the server includes means for receiving video information and the user's emotional state acquired from a vehicle in motion, means for analyzing the received information to detect specific driving behaviors and emotional states, and means for generating countermeasures appropriate to the situation based on the detected driving behaviors and emotional states. This enables real-time driving assistance that takes the user's emotional state into consideration.

[0351] "Vehicle in operation" refers to a vehicle that is moving or stationary, and that is engaged in the act of driving on a road.

[0352] "Visual information" refers to visual data acquired from cameras and sensor devices, including information such as the position and movement of objects.

[0353] "Emotional state" refers to the psychological and emotional state the user is experiencing, and is judged from facial expressions, tone of voice, and other factors.

[0354] "Analysis" refers to the process of deciphering data and extracting useful information, particularly for recognizing emotional states and driving behavior.

[0355] "Object recognition technology" is a technology that detects specific objects based on video information and identifies their location and movement.

[0356] "Countermeasure generation" is the process of designing and creating specific actions and advice to mitigate the risks associated with detected driving behaviors and emotional states.

[0357] "Visual information" refers to information that is visually perceptible and presented to the user through a display device.

[0358] "External organizations" are third-party organizations that interact with the system and exchange information, and include public safety agencies, medical service providers, and property insurance companies.

[0359] This invention is implemented as a system that analyzes video information acquired from a vehicle in motion and the user's emotional state to provide appropriate driving assistance. The server receives video and audio data from endpoints using a camera and microphone. This includes, for example, a camera and microphone mounted on smart glasses. The server analyzes this data using an image analysis library (e.g., OpenCV) and an audio analysis library (e.g., Google Cloud Speech-to-Text). Subsequently, it utilizes an emotion recognition API (e.g., Microsoft Azure Emotion API) to analyze the user's facial expressions and voice tone and identify their emotional state.

[0360] The analyzed data is integrated with a generative AI and used in a process to generate optimal actions to promote safe driving. The generated actions are presented to the user through visual and audio interfaces. Visual information is displayed on the smart glasses' screen, and audio information is provided via the voice speaker.

[0361] For example, if a user shows signs of frustration while stuck in traffic, the system can offer suggestions such as, "Would you like to play your favorite music to relax?" Another example of a prompt might be, "Evaluate the user's stress level based on their facial expression data and come up with specific advice to reduce the driver's stress." In this way, the system can support a safer and less stressful driving experience.

[0362] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0363] Step 1:

[0364] The server receives video and audio data through the camera and microphone attached to the terminal. The input is raw data including the user's facial expressions and voice tone, and the output is data in a format suitable for analysis. This input data is analyzed in the next step, ensuring high-quality data processing.

[0365] Step 2:

[0366] The server uses an image analysis library (e.g., OpenCV) to extract important features from video data. In this step, video data is used as input, and facial feature points (eyes, mouth shape, etc.) are obtained as output. Based on this data, data processing is performed to estimate the user's emotions.

[0367] Step 3:

[0368] The server analyzes audio data using a speech analysis library (e.g., Google Cloud Speech-to-Text). The input is audio data, and the output is tone and pitch information extracted from the speech. This analyzed data is then used to perform data calculations to infer specific emotions.

[0369] Step 4:

[0370] The server utilizes an emotion recognition API (e.g., Microsoft Azure Emotion API) to integrate the data obtained in steps 2 and 3 to identify the user's emotional state. The input consists of facial features and voice tone data, and the output is an estimated result of the emotional state. This process is a crucial step that forms the basis of generative AI.

[0371] Step 5:

[0372] The server inputs emotional state information into a generating AI model and generates appropriate countermeasures for the driving situation. The input consists of emotional state and driving behavior data, and the output generates specific actions and advice. This output is then presented to the user in the next step.

[0373] Step 6:

[0374] The terminal presents generated advice to the user via visual and audio interfaces. The input is the generated countermeasure information, and the output is the display of visual information on the terminal's screen and voice guidance through the speaker. This allows the user to receive driving assistance information in real time.

[0375] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0376] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0377] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0378] [Third Embodiment]

[0379] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0380] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0381] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0382] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0383] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0384] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0385] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0386] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0387] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0388] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0389] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0390] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0391] The present invention aims to provide a system that analyzes real-time video information acquired from a vehicle, detects dangerous driving behavior, and notifies the driver of appropriate countermeasures. Specifically, it dynamically analyzes driving behavior and identifies dangerous situations by processing video information using a generation AI. The server receives this video information and uses the generation AI engine to analyze the driving situation, including the movements of other vehicles. Furthermore, if dangerous driving behavior is detected, the server accesses a countermeasures database and generates information to propose appropriate countermeasures corresponding to the specific situation.

[0392] This information is sent to the terminal as an audio message and then notified to the user (driver) via the terminal. Based on the presented audio information, the user can take necessary driving actions in a timely manner. Furthermore, this system has a function that automatically provides information to relevant external organizations (police, medical institutions, insurance companies, etc.) via an autonomous AI agent if it determines that the danger is serious. In this way, it is possible to improve driver safety and prevent traffic accidents from occurring.

[0393] For example, if a vehicle rapidly approaches a user's vehicle from behind on a highway, the server detects the vehicle's movement. If the generating AI determines this movement is dangerous, the server immediately generates a voice message saying, "There is a vehicle rapidly approaching from behind. Please adjust your speed," and notifies the user via their device. The user receives this information, adjusts their speed to prevent an accident, and simultaneously notifies external authorities as necessary. This system is innovative in that it processes information in real time and enables instantaneous responses.

[0394] The following describes the processing flow.

[0395] Step 1:

[0396] The server receives real-time video information transmitted from the terminal. The video information is acquired by an in-vehicle camera and includes data capturing the surrounding environment of the vehicle.

[0397] Step 2:

[0398] The server's AI engine analyzes the received video information. Specifically, it uses object recognition algorithms to identify the movement, speed, and direction of other vehicles and obstacles, and evaluates the driving environment.

[0399] Step 3:

[0400] Based on the analysis results, the server evaluates whether to consider a particular driving behavior dangerous. If dangerous behaviors such as aggressive driving or sudden approaches are detected, that driving behavior is identified as dangerous.

[0401] Step 4:

[0402] When dangerous driving behavior is detected, the server accesses a database of countermeasures and generates appropriate countermeasures for the situation. It may also use a generation AI to generate custom messages tailored to new situations.

[0403] Step 5:

[0404] The server converts the generated countermeasures into a voice message and sends it to the terminal. This message is intended to prompt the driver to take specific corrective actions.

[0405] Step 6:

[0406] The terminal plays the voice message received from the server and notifies the user. This allows the user to receive voice warnings or instructions in real time.

[0407] Step 7:

[0408] The user follows the voice message instructions and modifies their driving behavior. For example, they may take actions such as slowing down or changing lanes to avoid potential hazards.

[0409] Step 8:

[0410] If the server determines that the situation is high-risk, it automatically reports the situation to external organizations (e.g., police or medical institutions) according to predefined protocols. This enables a rapid response.

[0411] (Example 1)

[0412] Next, we will describe Example 1. 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."

[0413] In recent years, the increase in traffic accidents has become a serious problem, hindering people's safe travel. Accidents caused by dangerous driving behavior, in particular, require a swift and accurate response, but current technology is insufficient to efficiently detect them and provide appropriate countermeasures. Therefore, there is a need for technology that can quickly detect dangerous driving behavior while driving and provide appropriate countermeasures to enhance driver safety.

[0414] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0415] In this invention, the server includes means for receiving visual information acquired from a vehicle, means for analyzing the received visual information using a generation AI model to detect dangerous driving behavior, means for generating countermeasures corresponding to specific situations based on the detected dangerous driving behavior, means for presenting the generated countermeasures to the driver as audio information, and means for providing information to an external organization via an autonomous agent when it is determined that the danger is serious. This makes it possible to detect dangerous driving behavior in real time and immediately provide appropriate countermeasures.

[0416] "Visual information" refers to data that indicates the driving environment and surrounding conditions, acquired through visual devices installed in the vehicle.

[0417] A "generative AI model" is a technology that utilizes artificial intelligence built using a deep learning framework to recognize patterns from given data and generate new information.

[0418] "Dangerous driving behavior" refers to driving operations that may violate the Road Traffic Act or vehicle operations that may cause an accident.

[0419] An "autonomous agent" is a software structure that can make decisions and act autonomously without waiting for instructions from an external source.

[0420] "External organizations" refer to organizations related to traffic safety, such as the police, medical facilities, and insurance companies.

[0421] The embodiments for carrying out the invention are described below.

[0422] The server receives visual information acquired from a vision device mounted on the vehicle. This device constantly monitors the vehicle's surroundings and includes high-resolution cameras and sensors. The server has a computing unit to input the received visual information into a generative AI model. This generative AI model uses deep learning frameworks such as TensorFlow or PyTorch and is trained to detect dangerous driving behaviors from vast amounts of data.

[0423] The terminal receives voice instructions transmitted from the server and notifies the user, the driver. The primary method of notification is voice guidance transmitted to the driver via a voice output device. This allows the user to take driving actions in real time to prevent accidents.

[0424] As a concrete example, if another vehicle approaches rapidly on a highway, the server uses a generating AI model to analyze the visual information and detect it as a dangerous approach. In this case, an example of a prompt message such as "Another vehicle has been detected approaching rapidly. Please adjust your speed." is fed into the AI ​​model, and an immediate voice message is generated. This voice message is sent to the terminal and notifies the user, "There is a vehicle rapidly approaching from behind. Please adjust your speed."

[0425] This system allows drivers to instantly understand dangerous situations and take appropriate measures, thereby improving safety. The server also utilizes autonomous agents as needed to automatically report the situation to external organizations if an accident is likely. These external organizations include the police, medical institutions, and insurance companies. This approach not only enhances the safety of the driving environment but also helps prevent traffic accidents from occurring.

[0426] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0427] Step 1:

[0428] The server receives visual information in real time from the vehicle's mounted visual devices. The input is video footage of the surrounding environment captured by cameras and sensors. This information is quickly transmitted to the server via the vehicle's internet connection. The output is the video data, which is then sent directly to the next analysis step.

[0429] Step 2:

[0430] The server inputs the received visual information into the generating AI model. The input at this stage is the video data received in Step 1. The generating AI model utilizes deep learning technology to perform object recognition and behavioral analysis. Specifically, the AI ​​model analyzes vehicles and road conditions in the video and detects dangerous driving behavior. The output is the analysis result, including whether or not dangerous driving behavior occurred and its details.

[0431] Step 3:

[0432] The server receives the analysis results from the generated AI model and, if dangerous driving behavior is detected, generates appropriate countermeasures. The input includes the analysis results from step 2. For data processing, it refers to the countermeasures database and selects appropriate countermeasures. The output is a voice message to be presented to the driver.

[0433] Step 4:

[0434] The generated voice message is sent from the server to the terminal. The input is the voice message generated in step 3, which the terminal receives. Specifically, the terminal notifies the driver of the voice message. This notification is made through a voice output device. The output provides instructions for the driver to drive safely.

[0435] Step 5:

[0436] The user receives voice messages from the device and adjusts driving operations as needed. The input is voice notifications, specifically instructions such as speed adjustments or lane changes. The output is ensuring the safety of driving behavior.

[0437] Step 6:

[0438] If the server determines the level of danger to be serious, information will be provided to external organizations via an autonomous agent. The input is the risk assessment based on the analysis results from step 2 and the judgment from step 3. As part of the data processing, the necessary information is packaged and automatically notified to external organizations. The output is notification to organizations involved in traffic safety.

[0439] (Application Example 1)

[0440] Next, we will explain Application Example 1. In the following explanation, 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."

[0441] In recent years, with the advancement of autonomous driving technology, the demand for systems to support safe driving has increased. However, many existing systems are limited to detecting and notifying drivers of dangerous driving, and are insufficient in providing concrete response options to drivers or automatic external notifications for serious dangers. Furthermore, mechanisms that allow users to visually and easily understand their situation while driving are not adequately developed. Against this backdrop, there is a need for new systems that reduce the risk of accidents in autonomous vehicles and for ordinary drivers, and improve safety while driving.

[0442] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0443] In this invention, the server includes means for receiving video data acquired from a mobile device in operation, means for analyzing the received video data and detecting specific operational behaviors, and means for notifying the user terminal of the detected danger information and explaining it visually and audibly. This makes it possible for drivers to obtain specific and appropriate countermeasures in real time while driving, dramatically improving driving safety.

[0444] "Mobility devices" is a general term for automatically or manually operated means of transportation used for moving on the ground.

[0445] "Video data" refers to digital visual information used to visually capture the surroundings of a mobile device.

[0446] "Analysis" is the process of extracting specific information or patterns from acquired data.

[0447] "Operational behavior" refers to the characteristics of specific actions or behaviors performed by a mobile device.

[0448] "Countermeasures" refer to guidelines or means for taking appropriate responses or actions in a specific situation.

[0449] "Audio information" refers to information transmitted through hearing, and is typically used as announcements or guide voices.

[0450] "External organizations" refer to external governing bodies or protective services related to the operation of mobile devices.

[0451] A "user terminal" refers to an electronic device used by drivers or administrators to receive information.

[0452] "Visual explanation" refers to illustrative or video methods used to convey information to users through visual media.

[0453] The invention describes embodiments for carrying out the invention. This system includes a mobile device, a server, and a user terminal. The server receives real-time video data from the mobile device equipped with a video sensor and analyzes the data to detect specific operational behaviors. This analysis uses a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to perform object identification and identify movement patterns. The server generates appropriate countermeasures according to the degree of the detected danger. These countermeasures are transmitted as audio information to the user terminal and notified to the operator via the terminal. The terminal presents detailed explanations so that the user can understand the situation visually and audibly.

[0454] Furthermore, this system has a function that automatically sends notifications to external organizations such as law enforcement agencies, medical institutions, and insurance companies if the danger is deemed serious. This allows users to act quickly and appropriately even in situations where immediate action is required.

[0455] For example, if the surrounding environment is inclement weather and visibility is poor, the server analyzes the situation and sends a voice notification to the user's terminal saying, "Due to poor visibility, please slow down." This allows the driver to take appropriate driving actions.

[0456] An example of a prompt to input into the generating AI model would be: "Analyze the real-time video footage obtained from the vehicle's sensors and identify potential obstacles and dangerous driving behaviors."

[0457] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0458] Step 1:

[0459] The server receives video data in real time from cameras and sensors mounted on the mobile device. The input is raw data from the cameras and sensors, while the output is digital video data for use within the server. Specifically, data from the sensors is transferred to the server via the network.

[0460] Step 2:

[0461] The server analyzes the received video data using a generating AI model. The input is the digital video data obtained in step 1, and the output is information about the identified operational behavior. The server inputs this video into the AI ​​model and performs data processing to identify object recognition and motion patterns.

[0462] Step 3:

[0463] The server assesses the risk level based on the analysis and generates countermeasures. The input is information about the operational behavior obtained in step 2, and the output is data showing specific countermeasures. Specifically, it refers to a pre-configured database of countermeasures based on the risk level and selects the appropriate countermeasure.

[0464] Step 4:

[0465] The server sends the generated countermeasures as voice information to the user's terminal. The input is the countermeasure data obtained in step 3, and the output is the voice message notified to the user. A speech synthesis engine is used to convert the countermeasures into voice format and send them to the terminal over the network.

[0466] Step 5:

[0467] The device notifies the user of the received audio information and also provides a visual explanation of the situation. The input is the audio message received in step 4, and the output is the notification action to the user. The device plays the audio through the speaker and displays the visual information on the display.

[0468] Step 6:

[0469] If the risk is serious, the server automatically notifies external organizations. The input is the risk level information obtained in step 3, and the output is the notification to the relevant organizations. The server automatically sends the necessary information to external organizations via email or API.

[0470] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0471] This invention relates to a system that analyzes video information acquired from a vehicle in motion, and by combining it with an emotion engine, recognizes the user's emotional state and further enhances driving assistance. This system understands the user's emotional state while driving and analyzes driving behavior in real time. The server uses video information received from the terminal to evaluate the surrounding traffic situation by combining generation AI and object recognition technology, and if dangerous driving behavior is detected, it generates countermeasures and provides them to the driver.

[0472] Furthermore, the emotion engine analyzes the user's facial expressions and voice tone to identify their emotional state. Based on this, it determines how the user's mental state is affecting their driving and adjusts countermeasures as needed. For example, if the user is feeling stressed, it can offer suggestions for relaxation.

[0473] The server integrates data obtained from video information with the results of the emotion engine's analysis to generate the most appropriate action for the driver as an audio message, which is then presented to the user via the terminal. This process is also integrated with a means of sharing information with external organizations and has the function to automatically notify the police, medical institutions, etc., as needed.

[0474] As a concrete example, consider a situation where a user is driving on a highway and a vehicle suddenly appears to overtake them. The server detects this sudden approach through a generating AI and, after analysis by an emotion engine, determines that the user is feeling stressed. Based on this result, the server generates a response such as "Take a deep breath and act calmly," and instructs the user via the terminal. In this way, the present invention realizes driving assistance that minimizes stress while maintaining driver safety.

[0475] The following describes the processing flow.

[0476] Step 1:

[0477] The terminal transmits video information acquired through the vehicle's in-vehicle camera to the server. This information includes video footage of the driver's face and the traffic conditions around the vehicle.

[0478] Step 2:

[0479] The server receives video information and uses object recognition technology to analyze the traffic situation around the vehicle. This allows it to identify the movement and position of other vehicles and evaluate the driving environment.

[0480] Step 3:

[0481] The server uses generated AI to analyze the driving environment and determine whether dangerous driving behavior exists. For example, it can detect a vehicle approaching rapidly and identify that behavior as aggressive driving.

[0482] Step 4:

[0483] The server activates an emotion engine and analyzes facial expressions and voice tone from the driver's facial video. This analysis identifies the user's emotional state and assesses levels of stress and tension, for example.

[0484] Step 5:

[0485] The server integrates the analyzed driving conditions and emotional state, and generates the optimal countermeasures accordingly. These countermeasures take into account the driver's mental state.

[0486] Step 6:

[0487] The server converts the generated countermeasures into an audio message and sends it to the user via the terminal. The user can receive this message by voice.

[0488] Step 7:

[0489] The user adjusts their driving appropriately by following voice instructions from the device. For example, they may be prompted to act calmly.

[0490] Step 8:

[0491] If necessary, the server will process information sharing with external organizations. In cases where the risk is deemed particularly high, notifications will be automatically sent to the police and medical institutions.

[0492] (Example 2)

[0493] Next, we will describe Example 2. 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."

[0494] In transportation systems, there is a need to consider the impact of the driver's psychological state on driving behavior and to realize safer and more comfortable driving assistance. Current driving assistance systems lack the function to understand the driver's emotional state in real time and provide appropriate measures based on that understanding. As a result, there is a challenge in that appropriate support cannot be provided when the driver is experiencing stress or anxiety.

[0495] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0496] In this invention, the server includes means for receiving video data acquired from a transport vehicle in operation, means for analyzing the received video and audio data to detect the user's emotional state and specific driving behaviors, and means for generating situation-appropriate countermeasures based on the detected driving behaviors and emotional state using a generative AI model and emotion analysis technology. This enables driving assistance that takes the driver's emotional state into consideration in real time.

[0497] "Video data" refers to image or video information acquired by cameras and sensors mounted on transportation equipment while it is in operation, and is fundamental information for understanding the driving environment and surrounding conditions.

[0498] "Voice data" refers to data collected from the driver's voice and surrounding sounds, and is used to analyze the driver's emotional state and environmental sounds.

[0499] A "generative AI model" is an artificial intelligence technology that uses learning algorithms to analyze specific patterns and actions, and generates reasoning and countermeasures necessary for driver assistance.

[0500] "Emotional analysis technology" is a technology that analyzes facial expressions and voice characteristics to identify a user's emotional state, and is used to understand the driver's psychological state.

[0501] "Object recognition technology" is a technology that detects objects such as other transportation equipment and obstacles based on video data, and analyzes their position and movement patterns.

[0502] "External organizations" refer to relevant organizations that provide or receive information related to driving, including safety maintenance organizations, medical organizations, and protective organizations.

[0503] "Driving assistance messages" are voice messages generated to provide drivers with situation-appropriate instructions and advice.

[0504] This invention is a system that analyzes the driver's emotional state using video and audio data acquired from a vehicle in operation, thereby supporting safe and comfortable driving. Information transmission and analysis primarily occur between a server, a terminal, and the user.

[0505] The server receives video and audio data acquired from the terminal and begins data processing. This uses terminals equipped with high-resolution cameras and high-performance microphones to accurately record the driving environment and the driver's condition. The server analyzes the received video data using a generating AI model and object recognition technology to understand the surrounding traffic conditions and specific driving behaviors. In this process, it identifies other vehicles and obstacles and assesses potential hazards to the driver.

[0506] Simultaneously, the server analyzes voice data and driver facial expression data using emotion analysis technology to identify the driver's emotional state. Emotion analysis technology is used to determine tension, stress, and relaxation from voice tone and facial expressions. Based on these analysis results, the server evaluates how the driver's emotional state is influencing their actual driving behavior.

[0507] The server uses a generative AI model to comprehensively analyze traffic conditions and emotional states, and generates optimal driving assistance messages for the user. This is done using automated voice message generation software, and the generated messages are sent to the terminal and presented to the driver. For example, if a driver feels tense due to a vehicle rapidly approaching on a highway, they might be given instructions such as, "Take a deep breath and calm down."

[0508] This system also has the capability to share information with external organizations as needed. This makes it possible to notify safety maintenance agencies and medical organizations of abnormal situations during operation in real time.

[0509] An example of a prompt would be, "Please suggest an appropriate driver assistance message for when an overtaking vehicle suddenly appears while driving on a highway." This prompt allows the generating AI model to quickly generate appropriate countermeasures.

[0510] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0511] Step 1:

[0512] The terminal collects video and audio data using cameras and microphones mounted on the transport vehicle while it is in motion. This data is transmitted to a server in real time. The input is video from the camera and audio from the microphone, and the output is the complete set of this data.

[0513] Step 2:

[0514] The server analyzes the video data received from the terminal using a generating AI model and object recognition technology. Specifically, it detects other objects in the video, such as other transportation equipment, pedestrians, and traffic lights, and analyzes their movement and position. The input is the video data from step 1, and the output is the detected object information and its movement pattern.

[0515] Step 3:

[0516] The server analyzes the received audio data using emotion analysis technology to identify the driver's emotional state. It reads emotions such as tension, stress, and relaxation from the voice tone and speech patterns. The input is the audio data from step 1, and the output is the identified emotional state.

[0517] Step 4:

[0518] The server integrates the analysis results from steps 2 and 3 and uses a generative AI model to generate optimal driving assistance messages for the driver. It determines how the driver should respond based on traffic conditions and emotional state. The input is detected object information and emotional state, and the output is the generated driving assistance message.

[0519] Step 5:

[0520] The server sends the generated driver assistance message to the terminal, which then presents it to the driver. Specifically, it is output as an audio message through the speaker, conveying instructions and advice to the driver. The input is the driver assistance message from step 4, and the output is the presentation of the audio message.

[0521] Step 6:

[0522] If necessary, the server notifies external organizations of the driving status and the driver's condition. For example, if dangerous driving continues, information is automatically sent to safety maintenance organizations or medical organizations. The input is the analysis results from steps 2 to 4, and the output is the notification information sent to external organizations.

[0523] (Application Example 2)

[0524] Next, we will explain application example 2. In the following explanation, 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."

[0525] There is a need for a system that provides appropriate driving assistance information that takes into account the emotional state of the driver while driving, thereby reducing driver stress and tension and improving safety. Furthermore, a system that allows for smooth information sharing with external organizations based on surrounding conditions and the driver's state is also required.

[0526] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0527] In this invention, the server includes means for receiving video information and the user's emotional state acquired from a vehicle in motion, means for analyzing the received information to detect specific driving behaviors and emotional states, and means for generating countermeasures appropriate to the situation based on the detected driving behaviors and emotional states. This enables real-time driving assistance that takes the user's emotional state into consideration.

[0528] "Vehicle in operation" refers to a vehicle that is moving or stationary, and that is engaged in the act of driving on a road.

[0529] "Visual information" refers to visual data acquired from cameras and sensor devices, including information such as the position and movement of objects.

[0530] "Emotional state" refers to the psychological and emotional state the user is experiencing, and is judged from facial expressions, tone of voice, and other factors.

[0531] "Analysis" refers to the process of deciphering data and extracting useful information, particularly for recognizing emotional states and driving behavior.

[0532] "Object recognition technology" is a technology that detects specific objects based on video information and identifies their location and movement.

[0533] "Countermeasure generation" is the process of designing and creating specific actions and advice to mitigate the risks associated with detected driving behaviors and emotional states.

[0534] "Visual information" refers to information that is visually perceptible and presented to the user through a display device.

[0535] "External organizations" are third-party organizations that interact with the system and exchange information, and include public safety agencies, medical service providers, and property insurance companies.

[0536] This invention is implemented as a system that analyzes video information acquired from a vehicle in motion and the user's emotional state to provide appropriate driving assistance. The server receives video and audio data from endpoints using a camera and microphone. This includes, for example, a camera and microphone mounted on smart glasses. The server analyzes this data using an image analysis library (e.g., OpenCV) and an audio analysis library (e.g., Google Cloud Speech-to-Text). Subsequently, it utilizes an emotion recognition API (e.g., Microsoft Azure Emotion API) to analyze the user's facial expressions and voice tone and identify their emotional state.

[0537] The analyzed data is integrated with a generative AI and used in a process to generate optimal actions to promote safe driving. The generated actions are presented to the user through visual and audio interfaces. Visual information is displayed on the smart glasses' screen, and audio information is provided via the voice speaker.

[0538] For example, if a user shows signs of frustration while stuck in traffic, the system can offer suggestions such as, "Would you like to play your favorite music to relax?" Another example of a prompt might be, "Evaluate the user's stress level based on their facial expression data and come up with specific advice to reduce the driver's stress." In this way, the system can support a safer and less stressful driving experience.

[0539] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0540] Step 1:

[0541] The server receives video and audio data through the camera and microphone attached to the terminal. The input is raw data including the user's facial expressions and voice tone, and the output is data in a format suitable for analysis. This input data is analyzed in the next step, ensuring high-quality data processing.

[0542] Step 2:

[0543] The server uses an image analysis library (e.g., OpenCV) to extract important features from video data. In this step, video data is used as input, and facial feature points (eyes, mouth shape, etc.) are obtained as output. Based on this data, data processing is performed to estimate the user's emotions.

[0544] Step 3:

[0545] The server analyzes audio data using a speech analysis library (e.g., Google Cloud Speech-to-Text). The input is audio data, and the output is tone and pitch information extracted from the speech. This analyzed data is then used to perform data calculations to infer specific emotions.

[0546] Step 4:

[0547] The server utilizes an emotion recognition API (e.g., Microsoft Azure Emotion API) to integrate the data obtained in steps 2 and 3 to identify the user's emotional state. The input consists of facial features and voice tone data, and the output is an estimated result of the emotional state. This process is a crucial step that forms the basis of generative AI.

[0548] Step 5:

[0549] The server inputs emotional state information into a generating AI model and generates appropriate countermeasures for the driving situation. The input consists of emotional state and driving behavior data, and the output generates specific actions and advice. This output is then presented to the user in the next step.

[0550] Step 6:

[0551] The terminal presents generated advice to the user via visual and audio interfaces. The input is the generated countermeasure information, and the output is the display of visual information on the terminal's screen and voice guidance through the speaker. This allows the user to receive driving assistance information in real time.

[0552] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0553] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0554] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0555] [Fourth Embodiment]

[0556] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0557] As shown in Figure 7, the 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.

[0558] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0559] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0560] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0561] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0562] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0563] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0564] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0565] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0566] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0567] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0568] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0569] The present invention aims to provide a system that analyzes real-time video information acquired from a vehicle, detects dangerous driving behavior, and notifies the driver of appropriate countermeasures. Specifically, it dynamically analyzes driving behavior and identifies dangerous situations by processing video information using a generation AI. The server receives this video information and uses the generation AI engine to analyze the driving situation, including the movements of other vehicles. Furthermore, if dangerous driving behavior is detected, the server accesses a countermeasures database and generates information to propose appropriate countermeasures corresponding to the specific situation.

[0570] This information is sent to the terminal as an audio message and then notified to the user (driver) via the terminal. Based on the presented audio information, the user can take necessary driving actions in a timely manner. Furthermore, this system has a function that automatically provides information to relevant external organizations (police, medical institutions, insurance companies, etc.) via an autonomous AI agent if it determines that the danger is serious. In this way, it is possible to improve driver safety and prevent traffic accidents from occurring.

[0571] For example, if a vehicle rapidly approaches a user's vehicle from behind on a highway, the server detects the vehicle's movement. If the generating AI determines this movement is dangerous, the server immediately generates a voice message saying, "There is a vehicle rapidly approaching from behind. Please adjust your speed," and notifies the user via their device. The user receives this information, adjusts their speed to prevent an accident, and simultaneously notifies external authorities as necessary. This system is innovative in that it processes information in real time and enables instantaneous responses.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] The server receives real-time video information transmitted from the terminal. The video information is acquired by an in-vehicle camera and includes data capturing the surrounding environment of the vehicle.

[0575] Step 2:

[0576] The server's AI engine analyzes the received video information. Specifically, it uses object recognition algorithms to identify the movement, speed, and direction of other vehicles and obstacles, and evaluates the driving environment.

[0577] Step 3:

[0578] Based on the analysis results, the server evaluates whether to consider a particular driving behavior dangerous. If dangerous behaviors such as aggressive driving or sudden approaches are detected, that driving behavior is identified as dangerous.

[0579] Step 4:

[0580] When dangerous driving behavior is detected, the server accesses a database of countermeasures and generates appropriate countermeasures for the situation. It may also use a generation AI to generate custom messages tailored to new situations.

[0581] Step 5:

[0582] The server converts the generated countermeasures into a voice message and sends it to the terminal. This message is intended to prompt the driver to take specific corrective actions.

[0583] Step 6:

[0584] The terminal plays the voice message received from the server and notifies the user. This allows the user to receive voice warnings or instructions in real time.

[0585] Step 7:

[0586] The user follows the voice message instructions and modifies their driving behavior. For example, they may take actions such as slowing down or changing lanes to avoid potential hazards.

[0587] Step 8:

[0588] If the server determines that the situation is high-risk, it automatically reports the situation to external organizations (e.g., police or medical institutions) according to predefined protocols. This enables a rapid response.

[0589] (Example 1)

[0590] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0591] In recent years, the increase in traffic accidents has become a serious problem, hindering people's safe travel. Accidents caused by dangerous driving behavior, in particular, require a swift and accurate response, but current technology is insufficient to efficiently detect them and provide appropriate countermeasures. Therefore, there is a need for technology that can quickly detect dangerous driving behavior while driving and provide appropriate countermeasures to enhance driver safety.

[0592] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0593] In this invention, the server includes means for receiving visual information acquired from a vehicle, means for analyzing the received visual information using a generation AI model to detect dangerous driving behavior, means for generating countermeasures corresponding to specific situations based on the detected dangerous driving behavior, means for presenting the generated countermeasures to the driver as audio information, and means for providing information to an external organization via an autonomous agent when it is determined that the danger is serious. This makes it possible to detect dangerous driving behavior in real time and immediately provide appropriate countermeasures.

[0594] "Visual information" refers to data that indicates the driving environment and surrounding conditions, acquired through visual devices installed in the vehicle.

[0595] A "generative AI model" is a technology that utilizes artificial intelligence built using a deep learning framework to recognize patterns from given data and generate new information.

[0596] "Dangerous driving behavior" refers to driving operations that may violate the Road Traffic Act or vehicle operations that may cause an accident.

[0597] An "autonomous agent" is a software structure that can make decisions and act autonomously without waiting for instructions from an external source.

[0598] "External organizations" refer to organizations related to traffic safety, such as the police, medical facilities, and insurance companies.

[0599] The embodiments for carrying out the invention are described below.

[0600] The server receives visual information acquired from a vision device mounted on the vehicle. This device constantly monitors the vehicle's surroundings and includes high-resolution cameras and sensors. The server has a computing unit to input the received visual information into a generative AI model. This generative AI model uses deep learning frameworks such as TensorFlow or PyTorch and is trained to detect dangerous driving behaviors from vast amounts of data.

[0601] The terminal receives voice instructions transmitted from the server and notifies the user, the driver. The primary method of notification is voice guidance transmitted to the driver via a voice output device. This allows the user to take driving actions in real time to prevent accidents.

[0602] As a concrete example, if another vehicle approaches rapidly on a highway, the server uses a generating AI model to analyze the visual information and detect it as a dangerous approach. In this case, an example of a prompt message such as "Another vehicle has been detected approaching rapidly. Please adjust your speed." is fed into the AI ​​model, and an immediate voice message is generated. This voice message is sent to the terminal and notifies the user, "There is a vehicle rapidly approaching from behind. Please adjust your speed."

[0603] This system allows drivers to instantly understand dangerous situations and take appropriate measures, thereby improving safety. The server also utilizes autonomous agents as needed to automatically report the situation to external organizations if an accident is likely. These external organizations include the police, medical institutions, and insurance companies. This approach not only enhances the safety of the driving environment but also helps prevent traffic accidents from occurring.

[0604] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0605] Step 1:

[0606] The server receives visual information in real time from the vehicle's mounted visual devices. The input is video footage of the surrounding environment captured by cameras and sensors. This information is quickly transmitted to the server via the vehicle's internet connection. The output is the video data, which is then sent directly to the next analysis step.

[0607] Step 2:

[0608] The server inputs the received visual information into the generating AI model. The input at this stage is the video data received in Step 1. The generating AI model utilizes deep learning technology to perform object recognition and behavioral analysis. Specifically, the AI ​​model analyzes vehicles and road conditions in the video and detects dangerous driving behavior. The output is the analysis result, including whether or not dangerous driving behavior occurred and its details.

[0609] Step 3:

[0610] The server receives the analysis results from the generated AI model and, if dangerous driving behavior is detected, generates appropriate countermeasures. The input includes the analysis results from step 2. For data processing, it refers to the countermeasures database and selects appropriate countermeasures. The output is a voice message to be presented to the driver.

[0611] Step 4:

[0612] The generated voice message is sent from the server to the terminal. The input is the voice message generated in step 3, which the terminal receives. Specifically, the terminal notifies the driver of the voice message. This notification is made through a voice output device. The output provides instructions for the driver to drive safely.

[0613] Step 5:

[0614] The user receives voice messages from the device and adjusts driving operations as needed. The input is voice notifications, specifically instructions such as speed adjustments or lane changes. The output is ensuring the safety of driving behavior.

[0615] Step 6:

[0616] If the server determines the level of danger to be serious, information will be provided to external organizations via an autonomous agent. The input is the risk assessment based on the analysis results from step 2 and the judgment from step 3. As part of the data processing, the necessary information is packaged and automatically notified to external organizations. The output is notification to organizations involved in traffic safety.

[0617] (Application Example 1)

[0618] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0619] In recent years, with the advancement of autonomous driving technology, the demand for systems to support safe driving has increased. However, many existing systems are limited to detecting and notifying drivers of dangerous driving, and are insufficient in providing concrete response options to drivers or automatic external notifications for serious dangers. Furthermore, mechanisms that allow users to visually and easily understand their situation while driving are not adequately developed. Against this backdrop, there is a need for new systems that reduce the risk of accidents in autonomous vehicles and for ordinary drivers, and improve safety while driving.

[0620] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0621] In this invention, the server includes means for receiving video data acquired from a mobile device in operation, means for analyzing the received video data and detecting specific operational behaviors, and means for notifying the user terminal of the detected danger information and explaining it visually and audibly. This makes it possible for drivers to obtain specific and appropriate countermeasures in real time while driving, dramatically improving driving safety.

[0622] "Mobility devices" is a general term for automatically or manually operated means of transportation used for moving on the ground.

[0623] "Video data" refers to digital visual information used to visually capture the surroundings of a mobile device.

[0624] "Analysis" is the process of extracting specific information or patterns from acquired data.

[0625] "Operational behavior" refers to the characteristics of specific actions or behaviors performed by a mobile device.

[0626] "Countermeasures" refer to guidelines or means for taking appropriate responses or actions in a specific situation.

[0627] "Audio information" refers to information transmitted through hearing, and is typically used as announcements or guide voices.

[0628] "External organizations" refer to external governing bodies or protective services related to the operation of mobile devices.

[0629] A "user terminal" refers to an electronic device used by drivers or administrators to receive information.

[0630] "Visual explanation" refers to illustrative or video methods used to convey information to users through visual media.

[0631] The invention describes embodiments for carrying out the invention. This system includes a mobile device, a server, and a user terminal. The server receives real-time video data from the mobile device equipped with a video sensor and analyzes the data to detect specific operational behaviors. This analysis uses a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to perform object identification and identify movement patterns. The server generates appropriate countermeasures according to the degree of the detected danger. These countermeasures are transmitted as audio information to the user terminal and notified to the operator via the terminal. The terminal presents detailed explanations so that the user can understand the situation visually and audibly.

[0632] Furthermore, this system has a function that automatically sends notifications to external organizations such as law enforcement agencies, medical institutions, and insurance companies if the danger is deemed serious. This allows users to act quickly and appropriately even in situations where immediate action is required.

[0633] For example, if the surrounding environment is inclement weather and visibility is poor, the server analyzes the situation and sends a voice notification to the user's terminal saying, "Due to poor visibility, please slow down." This allows the driver to take appropriate driving actions.

[0634] An example of a prompt to input into the generating AI model would be: "Analyze the real-time video footage obtained from the vehicle's sensors and identify potential obstacles and dangerous driving behaviors."

[0635] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0636] Step 1:

[0637] The server receives video data in real time from cameras and sensors mounted on the mobile device. The input is raw data from the cameras and sensors, while the output is digital video data for use within the server. Specifically, data from the sensors is transferred to the server via the network.

[0638] Step 2:

[0639] The server analyzes the received video data using a generating AI model. The input is the digital video data obtained in step 1, and the output is information about the identified operational behavior. The server inputs this video into the AI ​​model and performs data processing to identify object recognition and motion patterns.

[0640] Step 3:

[0641] The server assesses the risk level based on the analysis and generates countermeasures. The input is information about the operational behavior obtained in step 2, and the output is data showing specific countermeasures. Specifically, it refers to a pre-configured database of countermeasures based on the risk level and selects the appropriate countermeasure.

[0642] Step 4:

[0643] The server sends the generated countermeasures as voice information to the user's terminal. The input is the countermeasure data obtained in step 3, and the output is the voice message notified to the user. A speech synthesis engine is used to convert the countermeasures into voice format and send them to the terminal over the network.

[0644] Step 5:

[0645] The device notifies the user of the received audio information and also provides a visual explanation of the situation. The input is the audio message received in step 4, and the output is the notification action to the user. The device plays the audio through the speaker and displays the visual information on the display.

[0646] Step 6:

[0647] If the risk is serious, the server automatically notifies external organizations. The input is the risk level information obtained in step 3, and the output is the notification to the relevant organizations. The server automatically sends the necessary information to external organizations via email or API.

[0648] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0649] This invention relates to a system that analyzes video information acquired from a vehicle in motion, and by combining it with an emotion engine, recognizes the user's emotional state and further enhances driving assistance. This system understands the user's emotional state while driving and analyzes driving behavior in real time. The server uses video information received from the terminal to evaluate the surrounding traffic situation by combining generation AI and object recognition technology, and if dangerous driving behavior is detected, it generates countermeasures and provides them to the driver.

[0650] Furthermore, the emotion engine analyzes the user's facial expressions and voice tone to identify their emotional state. Based on this, it determines how the user's mental state is affecting their driving and adjusts countermeasures as needed. For example, if the user is feeling stressed, it can offer suggestions for relaxation.

[0651] The server integrates data obtained from video information with the results of the emotion engine's analysis to generate the most appropriate action for the driver as an audio message, which is then presented to the user via the terminal. This process is also integrated with a means of sharing information with external organizations and has the function to automatically notify the police, medical institutions, etc., as needed.

[0652] As a concrete example, consider a situation where a user is driving on a highway and a vehicle suddenly appears to overtake them. The server detects this sudden approach through a generating AI and, after analysis by an emotion engine, determines that the user is feeling stressed. Based on this result, the server generates a response such as "Take a deep breath and act calmly," and instructs the user via the terminal. In this way, the present invention realizes driving assistance that minimizes stress while maintaining driver safety.

[0653] The following describes the processing flow.

[0654] Step 1:

[0655] The terminal transmits video information acquired through the vehicle's in-vehicle camera to the server. This information includes video footage of the driver's face and the traffic conditions around the vehicle.

[0656] Step 2:

[0657] The server receives video information and uses object recognition technology to analyze the traffic situation around the vehicle. This allows it to identify the movement and position of other vehicles and evaluate the driving environment.

[0658] Step 3:

[0659] The server uses generated AI to analyze the driving environment and determine whether dangerous driving behavior exists. For example, it can detect a vehicle approaching rapidly and identify that behavior as aggressive driving.

[0660] Step 4:

[0661] The server activates an emotion engine and analyzes facial expressions and voice tone from the driver's facial video. This analysis identifies the user's emotional state and assesses levels of stress and tension, for example.

[0662] Step 5:

[0663] The server integrates the analyzed driving conditions and emotional state, and generates the optimal countermeasures accordingly. These countermeasures take into account the driver's mental state.

[0664] Step 6:

[0665] The server converts the generated countermeasures into an audio message and sends it to the user via the terminal. The user can receive this message by voice.

[0666] Step 7:

[0667] The user adjusts their driving appropriately by following voice instructions from the device. For example, they may be prompted to act calmly.

[0668] Step 8:

[0669] If necessary, the server will process information sharing with external organizations. In cases where the risk is deemed particularly high, notifications will be automatically sent to the police and medical institutions.

[0670] (Example 2)

[0671] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0672] In transportation systems, there is a need to consider the impact of the driver's psychological state on driving behavior and to realize safer and more comfortable driving assistance. Current driving assistance systems lack the function to understand the driver's emotional state in real time and provide appropriate measures based on that understanding. As a result, there is a challenge in that appropriate support cannot be provided when the driver is experiencing stress or anxiety.

[0673] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0674] In this invention, the server includes means for receiving video data acquired from a transport vehicle in operation, means for analyzing the received video and audio data to detect the user's emotional state and specific driving behaviors, and means for generating situation-appropriate countermeasures based on the detected driving behaviors and emotional state using a generative AI model and emotion analysis technology. This enables driving assistance that takes the driver's emotional state into consideration in real time.

[0675] "Video data" refers to image or video information acquired by cameras and sensors mounted on transportation equipment while it is in operation, and is fundamental information for understanding the driving environment and surrounding conditions.

[0676] "Voice data" refers to data collected from the driver's voice and surrounding sounds, and is used to analyze the driver's emotional state and environmental sounds.

[0677] A "generative AI model" is an artificial intelligence technology that uses learning algorithms to analyze specific patterns and actions, and generates reasoning and countermeasures necessary for driver assistance.

[0678] "Emotional analysis technology" is a technology that analyzes facial expressions and voice characteristics to identify a user's emotional state, and is used to understand the driver's psychological state.

[0679] "Object recognition technology" is a technology that detects objects such as other transportation equipment and obstacles based on video data, and analyzes their position and movement patterns.

[0680] "External organizations" refer to relevant organizations that provide or receive information related to driving, including safety maintenance organizations, medical organizations, and protective organizations.

[0681] "Driving assistance messages" are voice messages generated to provide drivers with situation-appropriate instructions and advice.

[0682] This invention is a system that analyzes the driver's emotional state using video and audio data acquired from a vehicle in operation, thereby supporting safe and comfortable driving. Information transmission and analysis primarily occur between a server, a terminal, and the user.

[0683] The server receives video and audio data acquired from the terminal and begins data processing. This uses terminals equipped with high-resolution cameras and high-performance microphones to accurately record the driving environment and the driver's condition. The server analyzes the received video data using a generating AI model and object recognition technology to understand the surrounding traffic conditions and specific driving behaviors. In this process, it identifies other vehicles and obstacles and assesses potential hazards to the driver.

[0684] Simultaneously, the server analyzes voice data and driver facial expression data using emotion analysis technology to identify the driver's emotional state. Emotion analysis technology is used to determine tension, stress, and relaxation from voice tone and facial expressions. Based on these analysis results, the server evaluates how the driver's emotional state is influencing their actual driving behavior.

[0685] The server uses a generative AI model to comprehensively analyze traffic conditions and emotional states, and generates optimal driving assistance messages for the user. This is done using automated voice message generation software, and the generated messages are sent to the terminal and presented to the driver. For example, if a driver feels tense due to a vehicle rapidly approaching on a highway, they might be given instructions such as, "Take a deep breath and calm down."

[0686] This system also has the capability to share information with external organizations as needed. This makes it possible to notify safety maintenance agencies and medical organizations of abnormal situations during operation in real time.

[0687] An example of a prompt would be, "Please suggest an appropriate driver assistance message for when an overtaking vehicle suddenly appears while driving on a highway." This prompt allows the generating AI model to quickly generate appropriate countermeasures.

[0688] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0689] Step 1:

[0690] The terminal collects video and audio data using cameras and microphones mounted on the transport vehicle while it is in motion. This data is transmitted to a server in real time. The input is video from the camera and audio from the microphone, and the output is the complete set of this data.

[0691] Step 2:

[0692] The server analyzes the video data received from the terminal using a generating AI model and object recognition technology. Specifically, it detects other objects in the video, such as other transportation equipment, pedestrians, and traffic lights, and analyzes their movement and position. The input is the video data from step 1, and the output is the detected object information and its movement pattern.

[0693] Step 3:

[0694] The server analyzes the received audio data using emotion analysis technology to identify the driver's emotional state. It reads emotions such as tension, stress, and relaxation from the voice tone and speech patterns. The input is the audio data from step 1, and the output is the identified emotional state.

[0695] Step 4:

[0696] The server integrates the analysis results from steps 2 and 3 and uses a generative AI model to generate optimal driving assistance messages for the driver. It determines how the driver should respond based on traffic conditions and emotional state. The input is detected object information and emotional state, and the output is the generated driving assistance message.

[0697] Step 5:

[0698] The server sends the generated driver assistance message to the terminal, which then presents it to the driver. Specifically, it is output as an audio message through the speaker, conveying instructions and advice to the driver. The input is the driver assistance message from step 4, and the output is the presentation of the audio message.

[0699] Step 6:

[0700] If necessary, the server notifies external organizations of the driving status and the driver's condition. For example, if dangerous driving continues, information is automatically sent to safety maintenance organizations or medical organizations. The input is the analysis results from steps 2 to 4, and the output is the notification information sent to external organizations.

[0701] (Application Example 2)

[0702] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] There is a need for a system that provides appropriate driving assistance information that takes into account the emotional state of the driver while driving, thereby reducing driver stress and tension and improving safety. Furthermore, a system that allows for smooth information sharing with external organizations based on surrounding conditions and the driver's state is also required.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0705] In this invention, the server includes means for receiving video information and the user's emotional state acquired from a vehicle in motion, means for analyzing the received information to detect specific driving behaviors and emotional states, and means for generating countermeasures appropriate to the situation based on the detected driving behaviors and emotional states. This enables real-time driving assistance that takes the user's emotional state into consideration.

[0706] "Vehicle in operation" refers to a vehicle that is moving or stationary, and that is engaged in the act of driving on a road.

[0707] "Visual information" refers to visual data acquired from cameras and sensor devices, including information such as the position and movement of objects.

[0708] "Emotional state" refers to the psychological and emotional state the user is experiencing, and is judged from facial expressions, tone of voice, and other factors.

[0709] "Analysis" refers to the process of deciphering data and extracting useful information, particularly for recognizing emotional states and driving behavior.

[0710] "Object recognition technology" is a technology that detects specific objects based on video information and identifies their location and movement.

[0711] "Countermeasure generation" is the process of designing and creating specific actions and advice to mitigate the risks associated with detected driving behaviors and emotional states.

[0712] "Visual information" refers to information that is visually perceptible and presented to the user through a display device.

[0713] "External organizations" are third-party organizations that interact with the system and exchange information, and include public safety agencies, medical service providers, and property insurance companies.

[0714] This invention is implemented as a system that analyzes video information acquired from a vehicle in motion and the user's emotional state to provide appropriate driving assistance. The server receives video and audio data from endpoints using a camera and microphone. This includes, for example, a camera and microphone mounted on smart glasses. The server analyzes this data using an image analysis library (e.g., OpenCV) and an audio analysis library (e.g., Google Cloud Speech-to-Text). Subsequently, it utilizes an emotion recognition API (e.g., Microsoft Azure Emotion API) to analyze the user's facial expressions and voice tone and identify their emotional state.

[0715] The analyzed data is integrated with a generative AI and used in a process to generate optimal actions to promote safe driving. The generated actions are presented to the user through visual and audio interfaces. Visual information is displayed on the smart glasses' screen, and audio information is provided via the voice speaker.

[0716] For example, if a user shows signs of frustration while stuck in traffic, the system can offer suggestions such as, "Would you like to play your favorite music to relax?" Another example of a prompt might be, "Evaluate the user's stress level based on their facial expression data and come up with specific advice to reduce the driver's stress." In this way, the system can support a safer and less stressful driving experience.

[0717] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0718] Step 1:

[0719] The server receives video and audio data through the camera and microphone attached to the terminal. The input is raw data including the user's facial expressions and voice tone, and the output is data in a format suitable for analysis. This input data is analyzed in the next step, ensuring high-quality data processing.

[0720] Step 2:

[0721] The server uses an image analysis library (e.g., OpenCV) to extract important features from video data. In this step, video data is used as input, and facial feature points (eyes, mouth shape, etc.) are obtained as output. Based on this data, data processing is performed to estimate the user's emotions.

[0722] Step 3:

[0723] The server analyzes audio data using a speech analysis library (e.g., Google Cloud Speech-to-Text). The input is audio data, and the output is tone and pitch information extracted from the speech. This analyzed data is then used to perform data calculations to infer specific emotions.

[0724] Step 4:

[0725] The server utilizes an emotion recognition API (e.g., Microsoft Azure Emotion API) to integrate the data obtained in steps 2 and 3 to identify the user's emotional state. The input consists of facial features and voice tone data, and the output is an estimated result of the emotional state. This process is a crucial step that forms the basis of generative AI.

[0726] Step 5:

[0727] The server inputs emotional state information into a generating AI model and generates appropriate countermeasures for the driving situation. The input consists of emotional state and driving behavior data, and the output generates specific actions and advice. This output is then presented to the user in the next step.

[0728] Step 6:

[0729] The terminal presents generated advice to the user via visual and audio interfaces. The input is the generated countermeasure information, and the output is the display of visual information on the terminal's screen and voice guidance through the speaker. This allows the user to receive driving assistance information in real time.

[0730] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0731] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0732] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0733] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0734] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0735] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0736] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0737] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0738] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0739] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0740] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0741] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0742] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0743] 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.

[0744] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0745] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0746] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0747] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0748] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0749] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0750] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0751] The following is further disclosed regarding the embodiments described above.

[0752] (Claim 1)

[0753] A means for receiving video information acquired from a vehicle in motion,

[0754] A means for analyzing received video information and detecting specific driving behaviors,

[0755] A means for generating countermeasures appropriate to the situation based on detected driving behavior,

[0756] A means of presenting the generated countermeasures to the driver as audio information,

[0757] Means of providing information to external organizations as needed,

[0758] A system that includes this.

[0759] (Claim 2)

[0760] The system according to claim 1, characterized in that the analysis means identifies other vehicles and their behavior patterns using object recognition technology.

[0761] (Claim 3)

[0762] The system according to claim 1, characterized in that the aforementioned external organizations include the police, medical institutions, and insurance organizations.

[0763] "Example 1"

[0764] (Claim 1)

[0765] A means for receiving visual information acquired from a vehicle,

[0766] A means for detecting dangerous driving behavior by analyzing received visual information using a generation AI model,

[0767] A means for generating countermeasures to respond to specific situations based on detected dangerous driving behaviors,

[0768] A means of presenting the generated countermeasures to the driver as audio information,

[0769] A means of providing information to external organizations via an autonomous agent when the danger is deemed serious,

[0770] A system that includes this.

[0771] (Claim 2)

[0772] The system according to claim 1, characterized in that the analysis means uses object recognition technology to identify other moving objects and their behavioral patterns.

[0773] (Claim 3)

[0774] The system according to claim 1, characterized in that the aforementioned external organizations include public institutions, medical facilities, and insurance companies.

[0775] "Application Example 1"

[0776] (Claim 1)

[0777] A means for receiving video data acquired from a mobile device in operation,

[0778] A means for analyzing received video data and detecting specific operational behaviors,

[0779] A means for generating countermeasures appropriate to the situation based on the detected operational behavior,

[0780] A means of presenting the generated countermeasures to the pilot as audio information,

[0781] Means of providing information to external organizations as needed,

[0782] A means of notifying the user terminal of detected danger information and providing visual and audible explanations,

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, characterized in that the analysis means identifies other mobile devices and their operating patterns using object recognition technology.

[0786] (Claim 3)

[0787] The system according to claim 1, characterized in that the external organization includes a law enforcement agency, a medical institution, and an insurance agency.

[0788] "Example 2 of combining an emotion engine"

[0789] (Claim 1)

[0790] A means for receiving video data acquired from a transport device in operation,

[0791] A means for analyzing received video and audio data to detect the user's emotional state and specific driving behaviors,

[0792] A means for generating situation-appropriate countermeasures based on detected driving behavior and emotional state, using a generative AI model and emotion analysis technology.

[0793] A means of presenting the generated countermeasures to the user as audio information,

[0794] Means of providing information to external organizations,

[0795] A system that includes this.

[0796] (Claim 2)

[0797] The system according to claim 1, characterized in that the analysis means uses object recognition technology to identify other transport devices and their behavioral patterns, and uses emotion analysis technology to determine the emotional state of the user.

[0798] (Claim 3)

[0799] The system according to claim 1, characterized in that the external organization includes a safety maintenance organization, a medical organization, and a protective organization.

[0800] "Application example 2 when combining with an emotional engine"

[0801] (Claim 1)

[0802] A means for receiving video information acquired from a vehicle in motion,

[0803] A means for analyzing received video information and detecting specific driving behaviors,

[0804] A means for generating countermeasures appropriate to the situation based on detected driving behavior and the user's emotional state,

[0805] A means of presenting the generated countermeasures to the driver as visual and audio information,

[0806] Means of providing information to external organizations as needed,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, characterized in that the analysis means identifies the emotional state of other vehicles and their users using object recognition technology and voice tone analysis technology.

[0810] (Claim 3)

[0811] The system according to claim 1, characterized in that the external organizations include public safety organizations, medical service providers, and property insurance organizations. [Explanation of symbols]

[0812] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving video data acquired from a mobile device in operation, A means for analyzing received video data and detecting specific operational behaviors, A means for generating countermeasures appropriate to the situation based on the detected operational behavior, A means of presenting the generated countermeasures to the pilot as audio information, Means of providing information to external organizations as needed, A means of notifying the user terminal of detected danger information and providing visual and audible explanations, A system that includes this.

2. The system according to claim 1, characterized in that the analysis means identifies other mobile devices and their operating patterns using object identification technology.

3. The system according to claim 1, characterized in that the external organization includes a law enforcement agency, a medical institution, and an insurance agency.

Images