system

Abstract

We provide the system. [Solution] A means for acquiring vehicle and pedestrian movement information in an intersection area using a data collection device, A means for calculating the risk of accidents at intersections using a prediction function based on acquired movement information, A means for adjusting the signal control device near the intersection based on the calculated accident risk, A means of displaying a warning to the user's terminal, 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 a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The frequent occurrence of traffic accidents at intersections, especially the increase in accidents involving children and the elderly, has become a serious social problem. Existing traffic safety systems have difficulty in providing real-time responses to individual intersections and incidents, and lack effective means to prevent accidents. As a result, there is a current situation where traffic accidents continue to occur at many intersections with insufficient safety measures.

Means for Solving the Problems

[0005] This invention proposes a system that acquires vehicle and pedestrian movement information using a data collection device installed at an intersection and calculates accident risk in real time using a prediction function. Based on the calculated accident risk, this system automatically adjusts the signal control device and sends a warning to the user terminal, thereby preventing accidents. Furthermore, by using sensors that acquire image data and audio data as data collection devices, more detailed and accurate risk prediction becomes possible, improving the safety of intersections.

[0006] A "data acquisition device" is a hardware device installed to acquire information on the movement of vehicles and pedestrians in an intersection area, and may include sensors and cameras.

[0007] A "predictive function" is software or an algorithm that analyzes collected data and calculates the future risk of accidents based on traffic conditions at intersections.

[0008] "Accident risk" is a quantitative or qualitative indicator that shows the probability or danger of traffic accidents that may occur at an intersection in the future.

[0009] A "signal control device" is a general term for the hardware and software used to control the operation of traffic signals at an intersection, and it has the function of adjusting the timing and display of the signals.

[0010] A "user terminal" is an electronic device used by drivers and traffic managers to receive or display information such as warnings, and includes in-vehicle devices and mobile applications.

[0011] A "warning" is a notification given to a user when the risk of a traffic accident increases, and it is a message intended to encourage safe driving and caution. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled 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.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled 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, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The present invention is a system aimed at preventing traffic accidents at intersections, and includes a data collection device, a prediction function, a signal control device, and a user terminal.

[0034] First, data collection devices, acting as terminals, are installed at intersections to acquire real-time movement information of vehicles and pedestrians using cameras and various sensors. This information is collected as detailed data, including image data, speed, direction, and number of people.

[0035] The server receives this movement information and analyzes it using a dedicated algorithm. The analysis combines historical statistical data with current traffic conditions to predict the risk of future accidents at specific intersections. This predictive information is used for immediate accident prevention and traffic signal control.

[0036] If the risk of an accident exceeds a certain threshold, the server sends a command to the signal control unit to adjust the timing of the red and green lights. For example, if the server detects that a group of children are about to cross an intersection, it requests the signal control unit to extend the duration of the green light accordingly.

[0037] The user terminal includes an application that provides drivers and traffic managers with risk information for when they reach their destination. Drivers receive visual and audible warnings from the terminal, encouraging safe driving. Traffic managers can check the latest traffic conditions and risk assessments at intersections via a management console and make further adjustments as needed.

[0038] As a concrete example, during the morning rush hour, the system alleviates congestion by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of a child, it alerts the drivers of the relevant vehicles to ensure safe travel.

[0039] This configuration enables a system that can flexibly respond to intersection conditions and effectively reduce the risk of accidents.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The terminal uses cameras and various sensors installed at intersections to collect real-time data on vehicles and pedestrians. This data includes images, speed, direction, and the number of pedestrians.

[0043] Step 2:

[0044] The device transmits the collected data to the server via the internet. The data is transferred in an optimized format so that it can be processed in real time.

[0045] Step 3:

[0046] The server applies an AI algorithm to analyze the received data. Based on past accident data and current traffic conditions, it calculates the accident risk at each intersection.

[0047] Step 4:

[0048] The server evaluates the calculated accident risk, and if it determines that the risk is high, it sends a command to the signal control device. This command adjusts the timing of the traffic signals in real time.

[0049] Step 5:

[0050] If the user is a driver, the user's device receives a warning from the server and provides visual or audible alerts. This allows the driver to respond to risks immediately.

[0051] Step 6:

[0052] If the user is a traffic manager, they can view real-time evaluation data on the management console and further adjust signal control and driver notifications as needed.

[0053] Step 7:

[0054] The server stores the final traffic data and accident risk assessment in a database and continuously updates the learning model to improve the overall accuracy of the system. This information contributes to improving the accuracy of future risk predictions.

[0055] (Example 1)

[0056] 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."

[0057] Modern traffic accidents at intersections often occur due to the high density of vehicles and pedestrians, as well as the inappropriate timing of traffic signal control. Furthermore, insufficient real-time information dissemination to drivers and traffic managers also contributes to the increased risk. Therefore, there is a need for systems that reduce accident risk and guarantee safe traffic flow.

[0058] 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.

[0059] In this invention, the server includes means for acquiring vehicle and pedestrian movement information in the intersection area using a data collection device, means for calculating accident risk by combining past statistical information and current situation information based on the acquired information, and means for dynamically adjusting the signal display pattern in the signal control device. This enables real-time reduction of accident risk according to traffic conditions, efficient signal control, and rapid provision of information to drivers.

[0060] A "data acquisition device" is a device installed to acquire vehicle and pedestrian movement information in an intersection area, and includes cameras and sensors for acquiring image data and speed data.

[0061] "Accident risk" is a value calculated based on statistical information and current traffic conditions to determine the likelihood of a traffic accident occurring at an intersection. This value serves as the basis for signal control and warnings to users.

[0062] A "signal control device" is a device installed near an intersection that dynamically adjusts the display time of traffic signals according to the calculated accident risk.

[0063] A "user terminal" refers to a device or application that provides drivers and traffic managers with information on intersection conditions and risks, and issues warnings as needed.

[0064] "Feedback data" refers to data collected from users and traffic managers, which is used to improve the system's analytical accuracy and response performance.

[0065] This invention is a system for preventing traffic accidents at intersections, and its components include a data collection device, a server, a signal control device, and a user terminal. These elements work together to reduce accident risk and improve traffic safety.

[0066] The data collection devices, acting as terminals, are positioned at intersections. These devices are equipped with high-resolution cameras and speed sensors to capture the real-time movement of vehicles and pedestrians, acquiring image data and detailed information such as speed, direction, and number of people. This data is immediately transmitted to a server for further analysis.

[0067] The server has a dedicated analysis algorithm that processes multiple pieces of movement information it receives. This algorithm is designed to combine historical statistics with current movement conditions to predict future accident risks. The specific analysis method employs machine learning models, and the use of generative AI models enables highly accurate predictions. The server also has an interface for issuing commands to signal control devices, dynamically adjusting the signal display pattern according to the risk level.

[0068] The signal control unit receives commands from a server and has the function of controlling the display timing of traffic lights at an intersection. For example, it can ensure safety by extending the display time of the green light when a group of pedestrians are about to pass through the intersection.

[0069] The application used as a user terminal is a tool for providing important traffic information to drivers and traffic managers. The terminal attracts the driver's attention through real-time visual and audio notifications, supporting safe driving. It also provides traffic managers with analysis results based on intersection data, offering support information for management as needed.

[0070] For example, this system can alleviate congestion during the morning rush hour by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of children near an intersection, it can send a warning to the driver via their device, such as "Please be careful of children at the intersection ahead."

[0071] An example of a prompt for a generated AI model would be text such as, "Design a program that uses real-time data at an intersection to control traffic signals, broken down into the steps of data collection, analysis, control, and notification."

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

[0073] Step 1:

[0074] The data collection device, acting as a terminal, uses cameras and sensors installed at intersections to acquire real-time movement information of vehicles and pedestrians. This information is collected in a detailed format, including image data, speed, direction, and number of people. Inputs include current video footage and sensor data from the area around the intersection. Outputs are these converted into analyzable numerical and image data.

[0075] Step 2:

[0076] The server receives movement information transmitted from the terminal and processes the data using a dedicated analysis algorithm. This algorithm combines historical traffic data with current conditions to predict the risk of future accidents. Specifically, the server applies a generative AI model to build a predictive model based on the input data. The input is movement data from the terminal, and the output is an accident risk value.

[0077] Step 3:

[0078] If the predicted accident risk value exceeds a certain threshold, the server sends a command to the signal control unit to adjust the signal display timing. For example, if the detected risk is high, the server commands the signal control unit to extend the duration of the red light. The input is the accident risk value, and the output is an instruction for the adjusted signal timing.

[0079] Step 4:

[0080] Based on the analysis results, the server sends real-time warnings to the user's terminal. Drivers are alerted by voice and on-screen warnings to be careful when approaching intersections. Inputs include risk information, and outputs include user-specific warning messages and operation guides.

[0081] Step 5:

[0082] The terminal collects feedback data from users and traffic managers and sends it to a server. This data will be used to improve the accuracy of future analyses. Specifically, the terminal provides a feedback interface, allowing users to input suggestions and opinions for improving safety. Input is user feedback data, and output is aggregated as feedback data sent to the server.

[0083] (Application Example 1)

[0084] 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."

[0085] The challenge lies in achieving optimal signal control and information provision to enable autonomous driving equipment to navigate intersections safely and efficiently, while simultaneously preventing accidents at intersections and ensuring a smooth flow of traffic.

[0086] 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.

[0087] In this invention, the server includes means for acquiring movement information of moving objects and people in an intersection area using a data acquisition device, means for calculating accident risk at the intersection using a prediction function based on the acquired movement information, and means for providing signal information and accident risk information to an autonomous driving device to support safe driving. This reduces the risk of accidents at intersections and enables the safe and smooth passage of autonomous driving devices.

[0088] A "data acquisition device" is a device installed to acquire real-time information on the movement of moving objects and people in an intersection area, and includes cameras and sensors.

[0089] The "predictive function" is a feature that analyzes collected movement data and calculates the future risk of accidents at a specific intersection.

[0090] A "signal control device" is a device that controls signal display devices installed at intersections, adjusting the timing of signal display according to the situation.

[0091] A "user terminal" is a device used by drivers or traffic managers that has the function of displaying accident risk information and warnings.

[0092] "Autonomous driving equipment" refers to devices or systems for automatically operating a vehicle, which perform safe driving based on external signal information and accident risk information.

[0093] The system for implementing this invention aims to improve safety at intersections by integrating a data collection device, a prediction function, a signal control device, a user terminal, and information provision to autonomous driving equipment.

[0094] The server receives video and sensor information from data collection devices installed at intersections and uses this information to analyze real-time location data of moving objects and people. Software such as Python and TENSORFLOW® is used for the analysis, and the risk of accidents is calculated by integrating this with historical traffic data and current conditions. The server also uses generative AI models to optimize signal control to match the predicted risk.

[0095] Meanwhile, user terminals are provided with immediate warnings regarding accident risk information and traffic signal status. The terminals have visual and audio notification mechanisms to inform drivers and traffic managers of hazards near intersections and encourage safe driving. Specifically, a hazard level indicator is displayed on the terminal screen, and a voice assistant can provide timely instructions.

[0096] Furthermore, the autonomous driving system receives signal information and accident risk information from a server. This helps the autonomous vehicle make appropriate decisions regarding deceleration, stopping, or proceeding when approaching intersections. This information is fed into the vehicle's main controller and helps with real-time driving control.

[0097] The operation of this system will, for example, appropriately adjust traffic light waiting times at congested intersections, resulting in smoother traffic flow with less disruption. In areas with many pedestrians, traffic lights will be extended, making travel safer.

[0098] An example of a prompt message would be, "What algorithm predicts the safest signal timing based on current traffic volume data and the movement of vehicles approaching an intersection, and then issues instructions to the autonomous vehicle?" This enables the realization of a safe and efficient traffic system that utilizes the latest traffic information.

[0099] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0100] Step 1:

[0101] The server acquires location information of moving objects and people from data collection devices installed at intersections. Inputs include video data from cameras and location data from sensors. These are received and stored on an NEC cloud platform. As output, the location data is converted into a format usable in the next analysis step.

[0102] Step 2:

[0103] The server uses acquired location information to predict accident risk. The input is the location data processed in step 1. This data is analyzed using Python and TensorFlow to calculate collision risk based on movement patterns and speed. The output generates numerical values ​​for accident risk at each intersection.

[0104] Step 3:

[0105] The server creates commands for the signal control unit based on the generated accident risk figures. The input is the accident risk figures from step 2. The generating AI model executes an algorithm to optimize the timing of the green and red lights. The output is the timing to be applied to the intersection signals.

[0106] Step 4:

[0107] The user terminal receives signal timing information and accident risk information sent from the server. The input is the output from step 3. The terminal notifies the driver of this information visually and audibly and issues a warning. As output, a warning message is displayed on the terminal's display, and voice guidance is provided if necessary.

[0108] Step 5:

[0109] The autonomous driving system calculates the optimal course of action for safe driving based on signals and accident risk information provided by the server. The input is the information from step 4. Dedicated in-vehicle software is used for the calculations, making decisions such as speed adjustments and stopping. As an output, the vehicle's driving control is performed in real time.

[0110] 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.

[0111] The present invention relates to an intersection safety system incorporating an emotion engine that recognizes the emotional state of users. This system includes a data collection device, a prediction function, a signal control device, and a user terminal equipped with the emotion engine.

[0112] The terminal functions as a data collection device installed at intersections, collecting detailed information on the movement of vehicles and pedestrians through cameras and sensors. This information is obtained as image and audio data and transmitted to a server as information that takes various factors into account.

[0113] The server analyzes the data and uses an AI algorithm to calculate the accident risk at the intersection. Based on the calculated risk assessment, the signal control system adjusts the timing of the traffic lights. This adjustment may take the form of holding the signal for a longer period to improve safety when there are many children passing through.

[0114] User terminals equipped with an emotion engine recognize the emotional state of drivers and traffic managers. The terminals use voice analysis and facial recognition technology to detect changes in the user's stress levels and attention span, and transmit this information to a server. Based on this emotion data, the server adjusts the content and format of warnings and sends notifications at appropriate timing and intensity according to the emotion.

[0115] For example, during peak commuting hours when drivers are more likely to experience stress, if the emotion engine detects high levels of tension in the user, the device will display a gentle warning encouraging them to take a break. Conversely, if emotions are more unstable than usual, a more emphatic warning will be issued to draw attention. Furthermore, data from the emotion engine is stored on a server and contributes to improving future prediction algorithms.

[0116] By incorporating an emotional engine, it becomes possible to implement multifaceted safety measures that not only adjust to traffic conditions but also take into account people's psychological states, further improving the effectiveness of accident prevention at intersections.

[0117] The following describes the processing flow.

[0118] Step 1:

[0119] The terminal uses cameras and sensors installed at intersections to collect real-time data on vehicle and pedestrian movement and ambient sounds. This includes image and audio data.

[0120] Step 2:

[0121] The terminal sends the collected data to the server. Upon receiving the data, the server uses an AI algorithm to analyze the traffic situation and calculate the risk of accidents.

[0122] Step 3:

[0123] The server adjusts the timing of traffic light displays via the signal control device based on the calculated accident risk. For example, if the risk is high, the red light duration is extended to allow pedestrians to cross safely.

[0124] Step 4:

[0125] The emotion engine installed in the user's device analyzes the user's voice and facial expressions to evaluate their emotional state. For example, it uses facial recognition technology to determine stress levels and attention levels.

[0126] Step 5:

[0127] The server receives emotional data and adjusts the content of notifications and the intensity of warnings based on the user's psychological state. For example, if the user is under high stress, it will send a message in a gentle tone encouraging them to take a break.

[0128] Step 6:

[0129] If the user is the driver, the user terminal provides customized warnings visually or audibly, encouraging safe driving in accordance with traffic conditions and the user's emotional state.

[0130] Step 7:

[0131] The server stores emotional and traffic data, which will be used to improve future predictive algorithms and the accuracy of emotion recognition. This makes it possible to continuously improve the overall effectiveness of the system.

[0132] (Example 2)

[0133] 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".

[0134] Conventional intersection safety systems had limitations in adjusting traffic signals based on changes in traffic conditions. In particular, they often disregarded the psychological state of users, failing to effectively prevent accidents caused by driver stress or inattention. Furthermore, they lacked sufficient flexibility in signal control and warnings in response to traffic volume and pedestrian conditions.

[0135] 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.

[0136] In this invention, the server includes information acquisition means for acquiring vehicle and pedestrian movement information in an intersection area, prediction means for calculating accident risk at the intersection using the acquired movement information, signal adjustment means for adjusting the timing of traffic light display based on the calculated accident risk, and emotion recognition and warning presentation means for recognizing the emotional state of users and presenting appropriate warnings based on that information. This makes it possible to provide multifaceted safety measures that are in line with traffic conditions and the psychological state of users.

[0137] "Information acquisition means" refers to a device or mechanism for collecting vehicle and pedestrian movement information in an intersection area, and has the function of acquiring data using sensors, cameras, etc.

[0138] The "prediction mechanism" is a mechanism for calculating the risk of accidents at intersections based on acquired movement information, and it has the function of predicting future situations using an AI algorithm.

[0139] A "signal adjustment means" is a device or mechanism that dynamically changes the display timing of traffic signals at an intersection based on the calculated accident risk, and has the function of performing control to optimize traffic flow.

[0140] "Emotion recognition means" refers to technologies that analyze and interpret the user's emotional state and detect changes in stress and attention, and have the function of determining psychological state using voice analysis, facial recognition, etc.

[0141] A "warning notification system" is a system that generates appropriate warnings according to the user's emotional state and traffic conditions and notifies the user's terminal, and has the function of providing alerts via voice and visuals.

[0142] This invention is a system for improving intersection safety and consists of several elements. First, a terminal is installed at the intersection and functions as a means of acquiring information. This terminal is equipped with a high-resolution camera and an audio sensor to collect information on vehicles and pedestrians passing through the intersection in real time. For example, a general camera module and an acoustic sensor module are used for this. The data from the terminal is transmitted to a server via wireless or wired communication.

[0143] The server is equipped with AI algorithms to analyze the received data, utilizing data analysis frameworks such as TensorFlow and PyTorch. The server uses data from information acquisition methods to predict accident risk at intersections. This prediction takes into account multiple factors, including vehicle speed, the number of pedestrians, and peak traffic conditions.

[0144] Based on the calculated risk assessment, the server controls the signal adjustment mechanism. The signal adjustment mechanism dynamically changes the timing of the traffic light display, for example, by displaying the green light for a longer period when there are many pedestrians, thereby improving safety.

[0145] Furthermore, this system incorporates emotion recognition capabilities that monitor the emotional state of users (drivers and traffic managers). For example, it can use voice analysis software and a camera installed on the terminal to estimate the driver's stress level and attention span. Appropriate warnings are then presented to the user's terminal based on their psychological state. These warnings can range from gentle messages encouraging drivers to take breaks to more emphasized alerts to draw their attention.

[0146] As a concrete example, during rush hour when drivers are prone to stress, if the emotion recognition system detects a high level of tension, the server sends a message to the user's terminal saying, "Caution is needed. Please take a break." This further enhances traffic safety.

[0147] Examples of prompts to input into the generating AI model include, "Please provide a specific operational example and explanation of a safety system that combines traffic signal control and emotion recognition at intersections." In this way, the present invention makes it possible to reduce accident risk and enhance safety at intersections in accordance with traffic conditions and the psychological state of users.

[0148] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0149] Step 1:

[0150] The terminals are installed at intersections and function as a means of acquiring information. Specifically, they use cameras and audio sensors to collect real-time data on the movement, speed, and number of vehicles and pedestrians passing through the intersection. This information is input to the terminals as image and audio data, processed by a digital signal processing unit, and then transmitted to a server.

[0151] Step 2:

[0152] The server receives image and audio data transmitted from the terminal. The received data is preprocessed to remove noise and standardize the format. Using this processed data, a generative AI model is used to predict the risk of accidents at intersections. In this process, factors such as changes in traffic volume and vehicle speed are taken into consideration to calculate a specific risk assessment.

[0153] Step 3:

[0154] The server controls the signal adjustment mechanism based on the calculated risk assessment. If a high risk is determined, it sends a signal to the signal control device to change the timing of the traffic light display. For example, during peak traffic hours, the green light is extended to ensure pedestrian safety. This dynamically optimizes the signal control pattern.

[0155] Step 4:

[0156] The device analyzes the user's voice and facial expression data using emotion recognition technology. Specifically, it uses voice analysis software to analyze the tone and speed of the voice, and a camera to evaluate facial expressions. This data is then sent to a server to provide indicators of stress and attention levels.

[0157] Step 5:

[0158] The server analyzes emotional data from users and generates appropriate warning messages based on the results. If it determines that the user's emotions are more unstable than usual, it displays a warning message on the user's device stating, "Caution is needed. Please take a break." This process helps ensure safe driving continues.

[0159] (Application Example 2)

[0160] 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 device 14 will be referred to as the "terminal."

[0161] In today's traffic environment, preventing traffic accidents at intersections is crucial, but conventional systems have only addressed risks associated with changing traffic conditions. Furthermore, the influence of the psychological state of drivers and passengers on traffic safety cannot be ignored. However, a comprehensive approach to improving safety that considers all these factors has not yet been established.

[0162] 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.

[0163] In this invention, the server includes means for acquiring movement information in the intersection area using a data collection device, means for analyzing the psychological state of passengers using an emotion recognition function, and means for presenting appropriate audio content and travel routes based on the analysis results. This makes it possible to prevent accidents and provide a safe travel experience that takes into account the dynamic changes in the traffic environment and the emotional state of users.

[0164] A "data acquisition device" is a device that acquires information on the movement of vehicles and pedestrians in an intersection area, and includes sensors that collect image data and audio data.

[0165] The "predictive function" is a function that uses acquired movement information to calculate the risk of accidents at intersections.

[0166] A "signal control device" is a device that adjusts the timing of traffic signals near an intersection based on the calculated accident risk.

[0167] The "emotion recognition function" is a feature that uses voice analysis and facial recognition technology to analyze the psychological state of passengers and, based on the results, presents appropriate audio content and travel routes.

[0168] A "user terminal" is a device used to display warnings to traffic managers and drivers, and is a system equipped with an emotion engine.

[0169] To implement this invention, a data collection device is required to collect vehicle and pedestrian movement information in the intersection area, a server is required to perform analysis and control, and a user terminal is required to recognize emotional states. The data collection device acquires vehicle and pedestrian information in real time using cameras and voice sensors installed at the intersection.

[0170] The server uses collected movement data to calculate the accident risk at intersections using AI algorithms. TensorFlow and OpenCV are used as computational software for this process. Based on the calculated risk assessment, the traffic signal control system adjusts the signal timing. For example, if there are many children crossing during school hours, the signal may be held on for a longer period to enhance safety.

[0171] Furthermore, the user terminal incorporates an emotion engine that utilizes voice analysis and facial recognition technology. This terminal analyzes the emotional state of the driver and passengers in real time and, if necessary, plays relaxing music or suggests taking a break. The analyzed emotion data is sent to a server, and any necessary warnings or suggestions are displayed on the user terminal.

[0172] For example, when a family is on a long road trip, if the emotion engine determines that the children are bored, it will play their favorite music and suggest taking a break at a park along the way. An example of a prompt sentence to provide to the generative AI model might be, "The passengers in the car seem a little worried. Please suggest ways to help them relax."

[0173] By integrating these elements, a multifaceted system can be realized to provide a sophisticated and safe transportation environment.

[0174] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0175] Step 1:

[0176] The data collection device uses cameras and audio sensors installed at intersections to acquire real-time information on the movement of vehicles and pedestrians. It receives video and audio from the environment as input, converts this into digital data, and transmits it to a server. The output is data on the position and speed of vehicles and pedestrians.

[0177] Step 2:

[0178] The server inputs the received movement information into an AI algorithm to calculate accident risk. TensorFlow is used to analyze image and audio data and perform accident risk assessment. The analysis outputs the probability of an accident occurring within a specific time window. This output is an accident risk score used to configure the signal control device.

[0179] Step 3:

[0180] The server controls the signal control device to optimize the timing of signal display based on the calculated accident risk. The input is an accident risk score, which is used to calculate the signal change time. Specifically, if the accident risk is high, adjustments are made, such as extending the time the signal is displayed in blue. The output is the adjusted signal display schedule.

[0181] Step 4:

[0182] The user terminal uses emotion recognition to analyze the emotional state of passengers and drivers and sends the results to the server. Input data consists of facial images and audio obtained from the camera and microphone, which are used for facial recognition and voice tone analysis. The output is an assessment of the passengers' stress and relaxation levels.

[0183] Step 5:

[0184] The server uses the received emotional data to send appropriate warnings and suggestions to the user's terminal. Taking an emotional state assessment as input, if the user is experiencing stress, it outputs instructions to play relaxing music and, in some cases, suggests a rest stop. Outputs include music playback instructions and route change suggestions.

[0185] Step 6:

[0186] Users can receive suggestions from their devices and respond to them to maintain a comfortable in-car environment. Ultimately, passengers and drivers receive an improved travel experience and a sense of security.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] [Second Embodiment]

[0191] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0192] 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.

[0193] 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).

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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".

[0203] The present invention is a system aimed at preventing traffic accidents at intersections, and includes a data collection device, a prediction function, a signal control device, and a user terminal.

[0204] First, data collection devices, acting as terminals, are installed at intersections to acquire real-time movement information of vehicles and pedestrians using cameras and various sensors. This information is collected as detailed data, including image data, speed, direction, and number of people.

[0205] The server receives this movement information and analyzes it using a dedicated algorithm. The analysis combines historical statistical data with current traffic conditions to predict the risk of future accidents at specific intersections. This predictive information is used for immediate accident prevention and traffic signal control.

[0206] If the risk of an accident exceeds a certain threshold, the server sends a command to the signal control unit to adjust the timing of the red and green lights. For example, if the server detects that a group of children are about to cross an intersection, it requests the signal control unit to extend the duration of the green light accordingly.

[0207] The user terminal includes an application that provides drivers and traffic managers with risk information for when they reach their destination. Drivers receive visual and audible warnings from the terminal, encouraging safe driving. Traffic managers can check the latest traffic conditions and risk assessments at intersections via a management console and make further adjustments as needed.

[0208] As a concrete example, during the morning rush hour, the system alleviates congestion by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of a child, it alerts the drivers of the relevant vehicles to ensure safe travel.

[0209] This configuration enables a system that can flexibly respond to intersection conditions and effectively reduce the risk of accidents.

[0210] The following describes the processing flow.

[0211] Step 1:

[0212] The terminal uses cameras and various sensors installed at intersections to collect real-time data on vehicles and pedestrians. This data includes images, speed, direction, and the number of pedestrians.

[0213] Step 2:

[0214] The device transmits the collected data to the server via the internet. The data is transferred in an optimized format so that it can be processed in real time.

[0215] Step 3:

[0216] The server applies an AI algorithm to analyze the received data. Based on past accident data and current traffic conditions, it calculates the accident risk at each intersection.

[0217] Step 4:

[0218] The server evaluates the calculated accident risk, and if it determines that the risk is high, it sends a command to the signal control device. This command adjusts the timing of the traffic signals in real time.

[0219] Step 5:

[0220] If the user is a driver, the user's device receives a warning from the server and provides visual or audible alerts. This allows the driver to respond to risks immediately.

[0221] Step 6:

[0222] If the user is a traffic manager, they can view real-time evaluation data on the management console and further adjust signal control and driver notifications as needed.

[0223] Step 7:

[0224] The server stores the final traffic data and accident risk assessment in a database and continuously updates the learning model to improve the overall accuracy of the system. This information contributes to improving the accuracy of future risk predictions.

[0225] (Example 1)

[0226] 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."

[0227] Modern traffic accidents at intersections often occur due to the high density of vehicles and pedestrians, as well as the inappropriate timing of traffic signal control. Furthermore, insufficient real-time information dissemination to drivers and traffic managers also contributes to the increased risk. Therefore, there is a need for systems that reduce accident risk and guarantee safe traffic flow.

[0228] 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.

[0229] In this invention, the server includes means for acquiring vehicle and pedestrian movement information in the intersection area using a data collection device, means for calculating accident risk by combining past statistical information and current situation information based on the acquired information, and means for dynamically adjusting the signal display pattern in the signal control device. This enables real-time reduction of accident risk according to traffic conditions, efficient signal control, and rapid provision of information to drivers.

[0230] A "data acquisition device" is a device installed to acquire vehicle and pedestrian movement information in an intersection area, and includes cameras and sensors for acquiring image data and speed data.

[0231] "Accident risk" is a value calculated based on statistical information and current traffic conditions to determine the likelihood of a traffic accident occurring at an intersection. This value serves as the basis for signal control and warnings to users.

[0232] A "signal control device" is a device installed near an intersection that dynamically adjusts the display time of traffic signals according to the calculated accident risk.

[0233] A "user terminal" refers to a device or application that provides drivers and traffic managers with information on intersection conditions and risks, and issues warnings as needed.

[0234] "Feedback data" refers to data collected from users and traffic managers, which is used to improve the system's analytical accuracy and response performance.

[0235] This invention is a system for preventing traffic accidents at intersections, and its components include a data collection device, a server, a signal control device, and a user terminal. These elements work together to reduce accident risk and improve traffic safety.

[0236] The data collection devices, acting as terminals, are positioned at intersections. These devices are equipped with high-resolution cameras and speed sensors to capture the real-time movement of vehicles and pedestrians, acquiring image data and detailed information such as speed, direction, and number of people. This data is immediately transmitted to a server for further analysis.

[0237] The server has a dedicated analysis algorithm that processes multiple pieces of movement information it receives. This algorithm is designed to combine historical statistics with current movement conditions to predict future accident risks. The specific analysis method employs machine learning models, and the use of generative AI models enables highly accurate predictions. The server also has an interface for issuing commands to signal control devices, dynamically adjusting the signal display pattern according to the risk level.

[0238] The signal control unit receives commands from a server and has the function of controlling the display timing of traffic lights at an intersection. For example, it can ensure safety by extending the display time of the green light when a group of pedestrians are about to pass through the intersection.

[0239] The application used as a user terminal is a tool for providing important traffic information to drivers and traffic managers. The terminal attracts the driver's attention through real-time visual and audio notifications, supporting safe driving. It also provides traffic managers with analysis results based on intersection data, offering support information for management as needed.

[0240] For example, this system can alleviate congestion during the morning rush hour by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of children near an intersection, it can send a warning to the driver via their device, such as "Please be careful of children at the intersection ahead."

[0241] An example of a prompt for a generated AI model would be text such as, "Design a program that uses real-time data at an intersection to control traffic signals, broken down into the steps of data collection, analysis, control, and notification."

[0242] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0243] Step 1:

[0244] The data collection device, acting as a terminal, uses cameras and sensors installed at intersections to acquire real-time movement information of vehicles and pedestrians. This information is collected in a detailed format, including image data, speed, direction, and number of people. Inputs include current video footage and sensor data from the area around the intersection. Outputs are these converted into analyzable numerical and image data.

[0245] Step 2:

[0246] The server receives movement information transmitted from the terminal and processes the data using a dedicated analysis algorithm. This algorithm combines historical traffic data with current conditions to predict the risk of future accidents. Specifically, the server applies a generative AI model to build a predictive model based on the input data. The input is movement data from the terminal, and the output is an accident risk value.

[0247] Step 3:

[0248] If the predicted accident risk value exceeds a certain threshold, the server sends a command to the signal control unit to adjust the signal display timing. For example, if the detected risk is high, the server commands the signal control unit to extend the duration of the red light. The input is the accident risk value, and the output is an instruction for the adjusted signal timing.

[0249] Step 4:

[0250] Based on the analysis results, the server sends real-time warnings to the user's terminal. Drivers are alerted by voice and on-screen warnings to be careful when approaching intersections. Inputs include risk information, and outputs include user-specific warning messages and operation guides.

[0251] Step 5:

[0252] The terminal collects feedback data from users and traffic managers and sends it to a server. This data will be used to improve the accuracy of future analyses. Specifically, the terminal provides a feedback interface, allowing users to input suggestions and opinions for improving safety. Input is user feedback data, and output is aggregated as feedback data sent to the server.

[0253] (Application Example 1)

[0254] 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."

[0255] The challenge lies in achieving optimal signal control and information provision to enable autonomous driving equipment to navigate intersections safely and efficiently, while simultaneously preventing accidents at intersections and ensuring a smooth flow of traffic.

[0256] 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.

[0257] In this invention, the server includes means for acquiring movement information of moving objects and people in an intersection area using a data acquisition device, means for calculating accident risk at the intersection using a prediction function based on the acquired movement information, and means for providing signal information and accident risk information to an autonomous driving device to support safe driving. This reduces the risk of accidents at intersections and enables the safe and smooth passage of autonomous driving devices.

[0258] A "data acquisition device" is a device installed to acquire real-time information on the movement of moving objects and people in an intersection area, and includes cameras and sensors.

[0259] The "predictive function" is a feature that analyzes collected movement data and calculates the future risk of accidents at a specific intersection.

[0260] A "signal control device" is a device that controls signal display devices installed at intersections, adjusting the timing of signal display according to the situation.

[0261] A "user terminal" is a device used by drivers or traffic managers that has the function of displaying accident risk information and warnings.

[0262] "Autonomous driving equipment" refers to devices or systems for automatically operating a vehicle, which perform safe driving based on external signal information and accident risk information.

[0263] The system for implementing this invention aims to improve safety at intersections by integrating a data collection device, a prediction function, a signal control device, a user terminal, and information provision to autonomous driving equipment.

[0264] The server receives video and sensor information from data collection devices installed at intersections and uses this information to analyze real-time location data of moving objects and people. Software such as Python and TensorFlow are used for the analysis, and the risk of accidents is calculated by integrating this with historical traffic data and current conditions. The server also uses generative AI models to optimize signal control to match the predicted risk.

[0265] Meanwhile, user terminals are provided with immediate warnings regarding accident risk information and traffic signal status. The terminals have visual and audio notification mechanisms to inform drivers and traffic managers of hazards near intersections and encourage safe driving. Specifically, a hazard level indicator is displayed on the terminal screen, and a voice assistant can provide timely instructions.

[0266] Furthermore, the autonomous driving system receives signal information and accident risk information from a server. This helps the autonomous vehicle make appropriate decisions regarding deceleration, stopping, or proceeding when approaching intersections. This information is fed into the vehicle's main controller and helps with real-time driving control.

[0267] The operation of this system will, for example, appropriately adjust traffic light waiting times at congested intersections, resulting in smoother traffic flow with less disruption. In areas with many pedestrians, traffic lights will be extended, making travel safer.

[0268] An example of a prompt message would be, "What algorithm predicts the safest signal timing based on current traffic volume data and the movement of vehicles approaching an intersection, and then issues instructions to the autonomous vehicle?" This enables the realization of a safe and efficient traffic system that utilizes the latest traffic information.

[0269] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0270] Step 1:

[0271] The server acquires location information of moving objects and people from data collection devices installed at intersections. Inputs include video data from cameras and location data from sensors. These are received and stored on an NEC cloud platform. As output, the location data is converted into a format usable in the next analysis step.

[0272] Step 2:

[0273] The server uses acquired location information to predict accident risk. The input is the location data processed in step 1. This data is analyzed using Python and TensorFlow to calculate collision risk based on movement patterns and speed. The output generates numerical values ​​for accident risk at each intersection.

[0274] Step 3:

[0275] The server creates commands for the signal control unit based on the generated accident risk figures. The input is the accident risk figures from step 2. The generating AI model executes an algorithm to optimize the timing of the green and red lights. The output is the timing to be applied to the intersection signals.

[0276] Step 4:

[0277] The user terminal receives signal timing information and accident risk information sent from the server. The input is the output from step 3. The terminal notifies the driver of this information visually and audibly and issues a warning. As output, a warning message is displayed on the terminal's display, and voice guidance is provided if necessary.

[0278] Step 5:

[0279] The autonomous driving system calculates the optimal course of action for safe driving based on signals and accident risk information provided by the server. The input is the information from step 4. Dedicated in-vehicle software is used for the calculations, making decisions such as speed adjustments and stopping. As an output, the vehicle's driving control is performed in real time.

[0280] 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.

[0281] The present invention relates to an intersection safety system incorporating an emotion engine that recognizes the emotional state of users. This system includes a data collection device, a prediction function, a signal control device, and a user terminal equipped with the emotion engine.

[0282] The terminal functions as a data collection device installed at intersections, collecting detailed information on the movement of vehicles and pedestrians through cameras and sensors. This information is obtained as image and audio data and transmitted to a server as information that takes various factors into account.

[0283] The server analyzes the data and uses an AI algorithm to calculate the accident risk at the intersection. Based on the calculated risk assessment, the signal control system adjusts the timing of the traffic lights. This adjustment may take the form of holding the signal for a longer period to improve safety when there are many children passing through.

[0284] A user terminal equipped with an emotion engine recognizes the emotional states of drivers and traffic managers. The terminal uses voice analysis and face recognition technologies to detect changes in the stress and attention of users and transmits this information to the server. Based on this emotional data, the server adjusts the content and format of warnings and issues notifications at appropriate times and with appropriate warning intensities according to the emotions.

[0285] As a specific example, during the commuting hours when drivers are prone to stress, if the emotion engine detects high tension in the user, the terminal displays a gentle warning urging the user to take a break for a while. On the other hand, if the emotion is not calmer than usual, a more emphasized warning that attracts more attention is issued. Furthermore, the data from the emotion engine is accumulated in the server and contributes to the improvement of future prediction algorithms.

[0286] By incorporating an emotion engine, not only can adjustments be made according to the traffic situation, but also multi-faceted safety measures can be taken in line with the psychological state of people, further improving the accident prevention effect at intersections.

[0287] The following describes the processing flow.

[0288] Step 1:

[0289] The terminal uses cameras and sensors installed at intersections to collect the movements of vehicles and pedestrians and environmental sounds in real time. This includes image data and audio data.

[0290] Step 2:

[0291] The terminal transmits the collected data to the server. When the server receives the data, it analyzes the traffic situation using AI algorithms and calculates the accident risk.

[0292] Step 3:

[0293] The server adjusts the timing of traffic light displays via the signal control device based on the calculated accident risk. For example, if the risk is high, the red light duration is extended to allow pedestrians to cross safely.

[0294] Step 4:

[0295] The emotion engine installed in the user's device analyzes the user's voice and facial expressions to evaluate their emotional state. For example, it uses facial recognition technology to determine stress levels and attention levels.

[0296] Step 5:

[0297] The server receives emotional data and adjusts the content of notifications and the intensity of warnings based on the user's psychological state. For example, if the user is under high stress, it will send a message in a gentle tone encouraging them to take a break.

[0298] Step 6:

[0299] If the user is the driver, the user terminal provides customized warnings visually or audibly, encouraging safe driving in accordance with traffic conditions and the user's emotional state.

[0300] Step 7:

[0301] The server stores emotional and traffic data, which will be used to improve future predictive algorithms and the accuracy of emotion recognition. This makes it possible to continuously improve the overall effectiveness of the system.

[0302] (Example 2)

[0303] 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 glasses 214 will be referred to as the "terminal".

[0304] In conventional intersection safety systems, there was a limit to adjusting traffic signals based on changes in traffic conditions. In particular, since control was performed ignoring the psychological state of users, accidents caused by driver stress or carelessness could not be effectively prevented. Also, flexible signal control and warning presentation according to traffic volume and pedestrian conditions were insufficient.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following respective means.

[0306] In this invention, the server includes an information acquisition means for acquiring movement information of vehicles and pedestrians in the intersection area, a prediction means for calculating the accident risk at the intersection using the acquired movement information, a signal adjustment means for adjusting the display timing of the traffic signal based on the calculated accident risk, and an emotion recognition and warning presentation means for recognizing the emotional state of the user and presenting an appropriate warning based on that information. Thereby, it becomes possible to provide multifaceted safety measures according to the traffic situation and the psychological state of the user.

[0307] The "information acquisition means" is a device or mechanism for collecting movement information of vehicles and pedestrians in the intersection area, and has a function of acquiring data using sensors, cameras, etc.

[0308] The "prediction means" is a mechanism for calculating the occurrence risk of an accident at the intersection based on the acquired movement information, and has a function of predicting future situations using an AI algorithm.

[0309] The "signal adjustment means" is a device or mechanism for dynamically changing the display timing of the traffic signal at the intersection based on the calculated accident risk, and has a function of performing control to optimize the traffic flow.

[0310] The "emotion recognition means" is a technology for analyzing and interpreting the emotional state of the user and detecting changes in stress and attention, and has a function of judging the psychological state using voice analysis, face recognition, etc.

[0311] A "warning notification system" is a system that generates appropriate warnings according to the user's emotional state and traffic conditions and notifies the user's terminal, and has the function of providing alerts via voice and visuals.

[0312] This invention is a system for improving intersection safety and consists of several elements. First, a terminal is installed at the intersection and functions as a means of acquiring information. This terminal is equipped with a high-resolution camera and an audio sensor to collect information on vehicles and pedestrians passing through the intersection in real time. For example, a general camera module and an acoustic sensor module are used for this. The data from the terminal is transmitted to a server via wireless or wired communication.

[0313] The server is equipped with AI algorithms to analyze the received data, utilizing data analysis frameworks such as TensorFlow and PyTorch. The server uses data from information acquisition methods to predict accident risk at intersections. This prediction takes into account multiple factors, including vehicle speed, the number of pedestrians, and peak traffic conditions.

[0314] Based on the calculated risk assessment, the server controls the signal adjustment mechanism. The signal adjustment mechanism dynamically changes the timing of the traffic light display, for example, by displaying the green light for a longer period when there are many pedestrians, thereby improving safety.

[0315] Furthermore, this system incorporates emotion recognition capabilities that monitor the emotional state of users (drivers and traffic managers). For example, it can use voice analysis software and a camera installed on the terminal to estimate the driver's stress level and attention span. Appropriate warnings are then presented to the user's terminal based on their psychological state. These warnings can range from gentle messages encouraging drivers to take breaks to more emphasized alerts to draw their attention.

[0316] As a concrete example, during rush hour when drivers are prone to stress, if the emotion recognition system detects a high level of tension, the server sends a message to the user's terminal saying, "Caution is needed. Please take a break." This further enhances traffic safety.

[0317] Examples of prompts to input into the generating AI model include, "Please provide a specific operational example and explanation of a safety system that combines traffic signal control and emotion recognition at intersections." In this way, the present invention makes it possible to reduce accident risk and enhance safety at intersections in accordance with traffic conditions and the psychological state of users.

[0318] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0319] Step 1:

[0320] The terminals are installed at intersections and function as a means of acquiring information. Specifically, they use cameras and audio sensors to collect real-time data on the movement, speed, and number of vehicles and pedestrians passing through the intersection. This information is input to the terminals as image and audio data, processed by a digital signal processing unit, and then transmitted to a server.

[0321] Step 2:

[0322] The server receives image and audio data transmitted from the terminal. The received data is preprocessed to remove noise and standardize the format. Using this processed data, a generative AI model is used to predict the risk of accidents at intersections. In this process, factors such as changes in traffic volume and vehicle speed are taken into consideration to calculate a specific risk assessment.

[0323] Step 3:

[0324] The server controls the signal adjustment mechanism based on the calculated risk assessment. If a high risk is determined, it sends a signal to the signal control device to change the timing of the traffic light display. For example, during peak traffic hours, the green light is extended to ensure pedestrian safety. This dynamically optimizes the signal control pattern.

[0325] Step 4:

[0326] The device analyzes the user's voice and facial expression data using emotion recognition technology. Specifically, it uses voice analysis software to analyze the tone and speed of the voice, and a camera to evaluate facial expressions. This data is then sent to a server to provide indicators of stress and attention levels.

[0327] Step 5:

[0328] The server analyzes emotional data from users and generates appropriate warning messages based on the results. If it determines that the user's emotions are more unstable than usual, it displays a warning message on the user's device stating, "Caution is needed. Please take a break." This process helps ensure safe driving continues.

[0329] (Application Example 2)

[0330] 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 as the "terminal".

[0331] In today's traffic environment, preventing traffic accidents at intersections is crucial, but conventional systems have only addressed risks associated with changing traffic conditions. Furthermore, the influence of the psychological state of drivers and passengers on traffic safety cannot be ignored. However, a comprehensive approach to improving safety that considers all these factors has not yet been established.

[0332] 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.

[0333] In this invention, the server includes means for acquiring movement information in the intersection area using a data collection device, means for analyzing the psychological state of passengers using an emotion recognition function, and means for presenting appropriate audio content and travel routes based on the analysis results. This makes it possible to prevent accidents and provide a safe travel experience that takes into account the dynamic changes in the traffic environment and the emotional state of users.

[0334] A "data acquisition device" is a device that acquires information on the movement of vehicles and pedestrians in an intersection area, and includes sensors that collect image data and audio data.

[0335] The "predictive function" is a function that uses acquired movement information to calculate the risk of accidents at intersections.

[0336] A "signal control device" is a device that adjusts the timing of traffic signals near an intersection based on the calculated accident risk.

[0337] The "emotion recognition function" is a feature that uses voice analysis and facial recognition technology to analyze the psychological state of passengers and, based on the results, presents appropriate audio content and travel routes.

[0338] A "user terminal" is a device used to display warnings to traffic managers and drivers, and is a system equipped with an emotion engine.

[0339] To implement this invention, a data collection device is required to collect vehicle and pedestrian movement information in the intersection area, a server is required to perform analysis and control, and a user terminal is required to recognize emotional states. The data collection device acquires vehicle and pedestrian information in real time using cameras and voice sensors installed at the intersection.

[0340] The server uses collected movement data to calculate the accident risk at intersections using AI algorithms. TensorFlow and OpenCV are used as computational software for this process. Based on the calculated risk assessment, the traffic signal control system adjusts the signal timing. For example, if there are many children crossing during school hours, the signal may be held on for a longer period to enhance safety.

[0341] Furthermore, the user terminal incorporates an emotion engine that utilizes voice analysis and facial recognition technology. This terminal analyzes the emotional state of the driver and passengers in real time and, if necessary, plays relaxing music or suggests taking a break. The analyzed emotion data is sent to a server, and any necessary warnings or suggestions are displayed on the user terminal.

[0342] For example, when a family is on a long road trip, if the emotion engine determines that the children are bored, it will play their favorite music and suggest taking a break at a park along the way. An example of a prompt sentence to provide to the generative AI model might be, "The passengers in the car seem a little worried. Please suggest ways to help them relax."

[0343] By integrating these elements, a multifaceted system can be realized to provide a sophisticated and safe transportation environment.

[0344] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0345] Step 1:

[0346] The data collection device uses cameras and audio sensors installed at intersections to acquire real-time information on the movement of vehicles and pedestrians. It receives video and audio from the environment as input, converts this into digital data, and transmits it to a server. The output is data on the position and speed of vehicles and pedestrians.

[0347] Step 2:

[0348] The server inputs the received movement information into an AI algorithm to calculate accident risk. TensorFlow is used to analyze image and audio data and perform accident risk assessment. The analysis outputs the probability of an accident occurring within a specific time window. This output is an accident risk score used to configure the signal control device.

[0349] Step 3:

[0350] The server controls the signal control device to optimize the timing of signal display based on the calculated accident risk. The input is an accident risk score, which is used to calculate the signal change time. Specifically, if the accident risk is high, adjustments are made, such as extending the time the signal is displayed in blue. The output is the adjusted signal display schedule.

[0351] Step 4:

[0352] The user terminal uses emotion recognition to analyze the emotional state of passengers and drivers and sends the results to the server. Input data consists of facial images and audio obtained from the camera and microphone, which are used for facial recognition and voice tone analysis. The output is an assessment of the passengers' stress and relaxation levels.

[0353] Step 5:

[0354] The server uses the received emotional data to send appropriate warnings and suggestions to the user's terminal. Taking an emotional state assessment as input, if the user is experiencing stress, it outputs instructions to play relaxing music and, in some cases, suggests a rest stop. Outputs include music playback instructions and route change suggestions.

[0355] Step 6:

[0356] Users can receive suggestions from their devices and respond to them to maintain a comfortable in-car environment. Ultimately, passengers and drivers receive an improved travel experience and a sense of security.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] [Third Embodiment]

[0361] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0362] 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.

[0363] 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).

[0364] 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.

[0365] 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.

[0366] 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).

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] 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".

[0373] The present invention is a system aimed at preventing traffic accidents at intersections, and includes a data collection device, a prediction function, a signal control device, and a user terminal.

[0374] First, data collection devices, acting as terminals, are installed at intersections to acquire real-time movement information of vehicles and pedestrians using cameras and various sensors. This information is collected as detailed data, including image data, speed, direction, and number of people.

[0375] The server receives this movement information and analyzes it using a dedicated algorithm. The analysis combines historical statistical data with current traffic conditions to predict the risk of future accidents at specific intersections. This predictive information is used for immediate accident prevention and traffic signal control.

[0376] If the risk of an accident exceeds a certain threshold, the server sends a command to the signal control unit to adjust the timing of the red and green lights. For example, if the server detects that a group of children are about to cross an intersection, it requests the signal control unit to extend the duration of the green light accordingly.

[0377] The user terminal includes an application that provides drivers and traffic managers with risk information for when they reach their destination. Drivers receive visual and audible warnings from the terminal, encouraging safe driving. Traffic managers can check the latest traffic conditions and risk assessments at intersections via a management console and make further adjustments as needed.

[0378] As a concrete example, during the morning rush hour, the system alleviates congestion by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of a child, it alerts the drivers of the relevant vehicles to ensure safe travel.

[0379] This configuration enables a system that can flexibly respond to intersection conditions and effectively reduce the risk of accidents.

[0380] The following describes the processing flow.

[0381] Step 1:

[0382] The terminal uses cameras and various sensors installed at intersections to collect real-time data on vehicles and pedestrians. This data includes images, speed, direction, and the number of pedestrians.

[0383] Step 2:

[0384] The device transmits the collected data to the server via the internet. The data is transferred in an optimized format so that it can be processed in real time.

[0385] Step 3:

[0386] The server applies an AI algorithm to analyze the received data. Based on past accident data and current traffic conditions, it calculates the accident risk at each intersection.

[0387] Step 4:

[0388] The server evaluates the calculated accident risk, and if it determines that the risk is high, it sends a command to the signal control device. This command adjusts the timing of the traffic signals in real time.

[0389] Step 5:

[0390] If the user is a driver, the user's device receives a warning from the server and provides visual or audible alerts. This allows the driver to respond to risks immediately.

[0391] Step 6:

[0392] If the user is a traffic manager, they can view real-time evaluation data on the management console and further adjust signal control and driver notifications as needed.

[0393] Step 7:

[0394] The server stores the final traffic data and accident risk assessment in a database and continuously updates the learning model to improve the overall accuracy of the system. This information contributes to improving the accuracy of future risk predictions.

[0395] (Example 1)

[0396] 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."

[0397] Modern traffic accidents at intersections often occur due to the high density of vehicles and pedestrians, as well as the inappropriate timing of traffic signal control. Furthermore, insufficient real-time information dissemination to drivers and traffic managers also contributes to the increased risk. Therefore, there is a need for systems that reduce accident risk and guarantee safe traffic flow.

[0398] 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.

[0399] In this invention, the server includes means for acquiring vehicle and pedestrian movement information in the intersection area using a data collection device, means for calculating accident risk by combining past statistical information and current situation information based on the acquired information, and means for dynamically adjusting the signal display pattern in the signal control device. This enables real-time reduction of accident risk according to traffic conditions, efficient signal control, and rapid provision of information to drivers.

[0400] A "data acquisition device" is a device installed to acquire vehicle and pedestrian movement information in an intersection area, and includes cameras and sensors for acquiring image data and speed data.

[0401] "Accident risk" is a value calculated based on statistical information and current traffic conditions to determine the likelihood of a traffic accident occurring at an intersection. This value serves as the basis for signal control and warnings to users.

[0402] A "signal control device" is a device installed near an intersection that dynamically adjusts the display time of traffic signals according to the calculated accident risk.

[0403] A "user terminal" refers to a device or application that provides drivers and traffic managers with information on intersection conditions and risks, and issues warnings as needed.

[0404] "Feedback data" refers to data collected from users and traffic managers, which is used to improve the system's analytical accuracy and response performance.

[0405] This invention is a system for preventing traffic accidents at intersections, and its components include a data collection device, a server, a signal control device, and a user terminal. These elements work together to reduce accident risk and improve traffic safety.

[0406] The data collection devices, acting as terminals, are positioned at intersections. These devices are equipped with high-resolution cameras and speed sensors to capture the real-time movement of vehicles and pedestrians, acquiring image data and detailed information such as speed, direction, and number of people. This data is immediately transmitted to a server for further analysis.

[0407] The server has a dedicated analysis algorithm that processes multiple pieces of movement information it receives. This algorithm is designed to combine historical statistics with current movement conditions to predict future accident risks. The specific analysis method employs machine learning models, and the use of generative AI models enables highly accurate predictions. The server also has an interface for issuing commands to signal control devices, dynamically adjusting the signal display pattern according to the risk level.

[0408] The signal control unit receives commands from a server and has the function of controlling the display timing of traffic lights at an intersection. For example, it can ensure safety by extending the display time of the green light when a group of pedestrians are about to pass through the intersection.

[0409] The application used as a user terminal is a tool for providing important traffic information to drivers and traffic managers. The terminal attracts the driver's attention through real-time visual and audio notifications, supporting safe driving. It also provides traffic managers with analysis results based on intersection data, offering support information for management as needed.

[0410] For example, this system can alleviate congestion during the morning rush hour by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of children near an intersection, it can send a warning to the driver via their device, such as "Please be careful of children at the intersection ahead."

[0411] An example of a prompt for a generated AI model would be text such as, "Design a program that uses real-time data at an intersection to control traffic signals, broken down into the steps of data collection, analysis, control, and notification."

[0412] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0413] Step 1:

[0414] The data collection device, acting as a terminal, uses cameras and sensors installed at intersections to acquire real-time movement information of vehicles and pedestrians. This information is collected in a detailed format, including image data, speed, direction, and number of people. Inputs include current video footage and sensor data from the area around the intersection. Outputs are these converted into analyzable numerical and image data.

[0415] Step 2:

[0416] The server receives movement information transmitted from the terminal and processes the data using a dedicated analysis algorithm. This algorithm combines historical traffic data with current conditions to predict the risk of future accidents. Specifically, the server applies a generative AI model to build a predictive model based on the input data. The input is movement data from the terminal, and the output is an accident risk value.

[0417] Step 3:

[0418] If the predicted accident risk value exceeds a certain threshold, the server sends a command to the signal control unit to adjust the signal display timing. For example, if the detected risk is high, the server commands the signal control unit to extend the duration of the red light. The input is the accident risk value, and the output is an instruction for the adjusted signal timing.

[0419] Step 4:

[0420] Based on the analysis results, the server sends real-time warnings to the user's terminal. Drivers are alerted by voice and on-screen warnings to be careful when approaching intersections. Inputs include risk information, and outputs include user-specific warning messages and operation guides.

[0421] Step 5:

[0422] The terminal collects feedback data from users and traffic managers and sends it to a server. This data will be used to improve the accuracy of future analyses. Specifically, the terminal provides a feedback interface, allowing users to input suggestions and opinions for improving safety. Input is user feedback data, and output is aggregated as feedback data sent to the server.

[0423] (Application Example 1)

[0424] 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."

[0425] The challenge lies in achieving optimal signal control and information provision to enable autonomous driving equipment to navigate intersections safely and efficiently, while simultaneously preventing accidents at intersections and ensuring a smooth flow of traffic.

[0426] 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.

[0427] In this invention, the server includes means for acquiring movement information of moving objects and people in an intersection area using a data acquisition device, means for calculating accident risk at the intersection using a prediction function based on the acquired movement information, and means for providing signal information and accident risk information to an autonomous driving device to support safe driving. This reduces the risk of accidents at intersections and enables the safe and smooth passage of autonomous driving devices.

[0428] A "data acquisition device" is a device installed to acquire real-time information on the movement of moving objects and people in an intersection area, and includes cameras and sensors.

[0429] The "predictive function" is a feature that analyzes collected movement data and calculates the future risk of accidents at a specific intersection.

[0430] A "signal control device" is a device that controls signal display devices installed at intersections, adjusting the timing of signal display according to the situation.

[0431] A "user terminal" is a device used by drivers or traffic managers that has the function of displaying accident risk information and warnings.

[0432] "Autonomous driving equipment" refers to devices or systems for automatically operating a vehicle, which perform safe driving based on external signal information and accident risk information.

[0433] The system for implementing this invention aims to improve safety at intersections by integrating a data collection device, a prediction function, a signal control device, a user terminal, and information provision to autonomous driving equipment.

[0434] The server receives video and sensor information from data collection devices installed at intersections and uses this information to analyze real-time location data of moving objects and people. Software such as Python and TensorFlow are used for the analysis, and the risk of accidents is calculated by integrating this with historical traffic data and current conditions. The server also uses generative AI models to optimize signal control to match the predicted risk.

[0435] Meanwhile, user terminals are provided with immediate warnings regarding accident risk information and traffic signal status. The terminals have visual and audio notification mechanisms to inform drivers and traffic managers of hazards near intersections and encourage safe driving. Specifically, a hazard level indicator is displayed on the terminal screen, and a voice assistant can provide timely instructions.

[0436] Furthermore, the autonomous driving system receives signal information and accident risk information from a server. This helps the autonomous vehicle make appropriate decisions regarding deceleration, stopping, or proceeding when approaching intersections. This information is fed into the vehicle's main controller and helps with real-time driving control.

[0437] The operation of this system will, for example, appropriately adjust traffic light waiting times at congested intersections, resulting in smoother traffic flow with less disruption. In areas with many pedestrians, traffic lights will be extended, making travel safer.

[0438] An example of a prompt message would be, "What algorithm predicts the safest signal timing based on current traffic volume data and the movement of vehicles approaching an intersection, and then issues instructions to the autonomous vehicle?" This enables the realization of a safe and efficient traffic system that utilizes the latest traffic information.

[0439] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0440] Step 1:

[0441] The server acquires location information of moving objects and people from data collection devices installed at intersections. Inputs include video data from cameras and location data from sensors. These are received and stored on an NEC cloud platform. As output, the location data is converted into a format usable in the next analysis step.

[0442] Step 2:

[0443] The server uses acquired location information to predict accident risk. The input is the location data processed in step 1. This data is analyzed using Python and TensorFlow to calculate collision risk based on movement patterns and speed. The output generates numerical values ​​for accident risk at each intersection.

[0444] Step 3:

[0445] The server creates commands for the signal control unit based on the generated accident risk figures. The input is the accident risk figures from step 2. The generating AI model executes an algorithm to optimize the timing of the green and red lights. The output is the timing to be applied to the intersection signals.

[0446] Step 4:

[0447] The user terminal receives signal timing information and accident risk information sent from the server. The input is the output from step 3. The terminal notifies the driver of this information visually and audibly and issues a warning. As output, a warning message is displayed on the terminal's display, and voice guidance is provided if necessary.

[0448] Step 5:

[0449] The autonomous driving system calculates the optimal course of action for safe driving based on signals and accident risk information provided by the server. The input is the information from step 4. Dedicated in-vehicle software is used for the calculations, making decisions such as speed adjustments and stopping. As an output, the vehicle's driving control is performed in real time.

[0450] 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.

[0451] The present invention relates to an intersection safety system incorporating an emotion engine that recognizes the emotional state of users. This system includes a data collection device, a prediction function, a signal control device, and a user terminal equipped with the emotion engine.

[0452] The terminal functions as a data collection device installed at intersections, collecting detailed information on the movement of vehicles and pedestrians through cameras and sensors. This information is obtained as image and audio data and transmitted to a server as information that takes various factors into account.

[0453] The server analyzes the data and uses an AI algorithm to calculate the accident risk at the intersection. Based on the calculated risk assessment, the signal control system adjusts the timing of the traffic lights. This adjustment may take the form of holding the signal for a longer period to improve safety when there are many children passing through.

[0454] User terminals equipped with an emotion engine recognize the emotional state of drivers and traffic managers. The terminals use voice analysis and facial recognition technology to detect changes in the user's stress levels and attention span, and transmit this information to a server. Based on this emotion data, the server adjusts the content and format of warnings and sends notifications at appropriate timing and intensity according to the emotion.

[0455] For example, during peak commuting hours when drivers are more likely to experience stress, if the emotion engine detects high levels of tension in the user, the device will display a gentle warning encouraging them to take a break. Conversely, if emotions are more unstable than usual, a more emphatic warning will be issued to draw attention. Furthermore, data from the emotion engine is stored on a server and contributes to improving future prediction algorithms.

[0456] By incorporating an emotional engine, it becomes possible to implement multifaceted safety measures that not only adjust to traffic conditions but also take into account people's psychological states, further improving the effectiveness of accident prevention at intersections.

[0457] The following describes the processing flow.

[0458] Step 1:

[0459] The terminal uses cameras and sensors installed at intersections to collect real-time data on vehicle and pedestrian movement and ambient sounds. This includes image and audio data.

[0460] Step 2:

[0461] The terminal sends the collected data to the server. Upon receiving the data, the server uses an AI algorithm to analyze the traffic situation and calculate the risk of accidents.

[0462] Step 3:

[0463] The server adjusts the timing of traffic light displays via the signal control device based on the calculated accident risk. For example, if the risk is high, the red light duration is extended to allow pedestrians to cross safely.

[0464] Step 4:

[0465] The emotion engine installed in the user's device analyzes the user's voice and facial expressions to evaluate their emotional state. For example, it uses facial recognition technology to determine stress levels and attention levels.

[0466] Step 5:

[0467] The server receives emotional data and adjusts the content of notifications and the intensity of warnings based on the user's psychological state. For example, if the user is under high stress, it will send a message in a gentle tone encouraging them to take a break.

[0468] Step 6:

[0469] If the user is the driver, the user terminal provides customized warnings visually or audibly, encouraging safe driving in accordance with traffic conditions and the user's emotional state.

[0470] Step 7:

[0471] The server stores emotional and traffic data, which will be used to improve future predictive algorithms and the accuracy of emotion recognition. This makes it possible to continuously improve the overall effectiveness of the system.

[0472] (Example 2)

[0473] 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."

[0474] Conventional intersection safety systems had limitations in adjusting traffic signals based on changes in traffic conditions. In particular, they often disregarded the psychological state of users, failing to effectively prevent accidents caused by driver stress or inattention. Furthermore, they lacked sufficient flexibility in signal control and warnings in response to traffic volume and pedestrian conditions.

[0475] 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.

[0476] In this invention, the server includes information acquisition means for acquiring vehicle and pedestrian movement information in an intersection area, prediction means for calculating accident risk at the intersection using the acquired movement information, signal adjustment means for adjusting the timing of traffic light display based on the calculated accident risk, and emotion recognition and warning presentation means for recognizing the emotional state of users and presenting appropriate warnings based on that information. This makes it possible to provide multifaceted safety measures that are in line with traffic conditions and the psychological state of users.

[0477] "Information acquisition means" refers to a device or mechanism for collecting vehicle and pedestrian movement information in an intersection area, and has the function of acquiring data using sensors, cameras, etc.

[0478] The "prediction mechanism" is a mechanism for calculating the risk of accidents at intersections based on acquired movement information, and it has the function of predicting future situations using an AI algorithm.

[0479] A "signal adjustment means" is a device or mechanism that dynamically changes the display timing of traffic signals at an intersection based on the calculated accident risk, and has the function of performing control to optimize traffic flow.

[0480] "Emotion recognition means" refers to technologies that analyze and interpret the user's emotional state and detect changes in stress and attention, and have the function of determining psychological state using voice analysis, facial recognition, etc.

[0481] A "warning notification system" is a system that generates appropriate warnings according to the user's emotional state and traffic conditions and notifies the user's terminal, and has the function of providing alerts via voice and visuals.

[0482] This invention is a system for improving intersection safety and consists of several elements. First, a terminal is installed at the intersection and functions as a means of acquiring information. This terminal is equipped with a high-resolution camera and an audio sensor to collect information on vehicles and pedestrians passing through the intersection in real time. For example, a general camera module and an acoustic sensor module are used for this. The data from the terminal is transmitted to a server via wireless or wired communication.

[0483] The server is equipped with AI algorithms to analyze the received data, utilizing data analysis frameworks such as TensorFlow and PyTorch. The server uses data from information acquisition methods to predict accident risk at intersections. This prediction takes into account multiple factors, including vehicle speed, the number of pedestrians, and peak traffic conditions.

[0484] Based on the calculated risk assessment, the server controls the signal adjustment mechanism. The signal adjustment mechanism dynamically changes the timing of the traffic light display, for example, by displaying the green light for a longer period when there are many pedestrians, thereby improving safety.

[0485] Furthermore, this system incorporates emotion recognition capabilities that monitor the emotional state of users (drivers and traffic managers). For example, it can use voice analysis software and a camera installed on the terminal to estimate the driver's stress level and attention span. Appropriate warnings are then presented to the user's terminal based on their psychological state. These warnings can range from gentle messages encouraging drivers to take breaks to more emphasized alerts to draw their attention.

[0486] As a concrete example, during rush hour when drivers are prone to stress, if the emotion recognition system detects a high level of tension, the server sends a message to the user's terminal saying, "Caution is needed. Please take a break." This further enhances traffic safety.

[0487] Examples of prompts to input into the generating AI model include, "Please provide a specific operational example and explanation of a safety system that combines traffic signal control and emotion recognition at intersections." In this way, the present invention makes it possible to reduce accident risk and enhance safety at intersections in accordance with traffic conditions and the psychological state of users.

[0488] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0489] Step 1:

[0490] The terminals are installed at intersections and function as a means of acquiring information. Specifically, they use cameras and audio sensors to collect real-time data on the movement, speed, and number of vehicles and pedestrians passing through the intersection. This information is input to the terminals as image and audio data, processed by a digital signal processing unit, and then transmitted to a server.

[0491] Step 2:

[0492] The server receives image and audio data transmitted from the terminal. The received data is preprocessed to remove noise and standardize the format. Using this processed data, a generative AI model is used to predict the risk of accidents at intersections. In this process, factors such as changes in traffic volume and vehicle speed are taken into consideration to calculate a specific risk assessment.

[0493] Step 3:

[0494] The server controls the signal adjustment mechanism based on the calculated risk assessment. If a high risk is determined, it sends a signal to the signal control device to change the timing of the traffic light display. For example, during peak traffic hours, the green light is extended to ensure pedestrian safety. This dynamically optimizes the signal control pattern.

[0495] Step 4:

[0496] The device analyzes the user's voice and facial expression data using emotion recognition technology. Specifically, it uses voice analysis software to analyze the tone and speed of the voice, and a camera to evaluate facial expressions. This data is then sent to a server to provide indicators of stress and attention levels.

[0497] Step 5:

[0498] The server analyzes emotional data from users and generates appropriate warning messages based on the results. If it determines that the user's emotions are more unstable than usual, it displays a warning message on the user's device stating, "Caution is needed. Please take a break." This process helps ensure safe driving continues.

[0499] (Application Example 2)

[0500] 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."

[0501] In today's traffic environment, preventing traffic accidents at intersections is crucial, but conventional systems have only addressed risks associated with changing traffic conditions. Furthermore, the influence of the psychological state of drivers and passengers on traffic safety cannot be ignored. However, a comprehensive approach to improving safety that considers all these factors has not yet been established.

[0502] 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.

[0503] In this invention, the server includes means for acquiring movement information in the intersection area using a data collection device, means for analyzing the psychological state of passengers using an emotion recognition function, and means for presenting appropriate audio content and travel routes based on the analysis results. This makes it possible to prevent accidents and provide a safe travel experience that takes into account the dynamic changes in the traffic environment and the emotional state of users.

[0504] A "data acquisition device" is a device that acquires information on the movement of vehicles and pedestrians in an intersection area, and includes sensors that collect image data and audio data.

[0505] The "predictive function" is a function that uses acquired movement information to calculate the risk of accidents at intersections.

[0506] A "signal control device" is a device that adjusts the timing of traffic signals near an intersection based on the calculated accident risk.

[0507] The "emotion recognition function" is a feature that uses voice analysis and facial recognition technology to analyze the psychological state of passengers and, based on the results, presents appropriate audio content and travel routes.

[0508] A "user terminal" is a device used to display warnings to traffic managers and drivers, and is a system equipped with an emotion engine.

[0509] To implement this invention, a data collection device is required to collect vehicle and pedestrian movement information in the intersection area, a server is required to perform analysis and control, and a user terminal is required to recognize emotional states. The data collection device acquires vehicle and pedestrian information in real time using cameras and voice sensors installed at the intersection.

[0510] The server uses collected movement data to calculate the accident risk at intersections using AI algorithms. TensorFlow and OpenCV are used as computational software for this process. Based on the calculated risk assessment, the traffic signal control system adjusts the signal timing. For example, if there are many children crossing during school hours, the signal may be held on for a longer period to enhance safety.

[0511] Furthermore, the user terminal incorporates an emotion engine that utilizes voice analysis and facial recognition technology. This terminal analyzes the emotional state of the driver and passengers in real time and, if necessary, plays relaxing music or suggests taking a break. The analyzed emotion data is sent to a server, and any necessary warnings or suggestions are displayed on the user terminal.

[0512] For example, when a family is on a long road trip, if the emotion engine determines that the children are bored, it will play their favorite music and suggest taking a break at a park along the way. An example of a prompt sentence to provide to the generative AI model might be, "The passengers in the car seem a little worried. Please suggest ways to help them relax."

[0513] By integrating these elements, a multifaceted system can be realized to provide a sophisticated and safe transportation environment.

[0514] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0515] Step 1:

[0516] The data collection device uses cameras and audio sensors installed at intersections to acquire real-time information on the movement of vehicles and pedestrians. It receives video and audio from the environment as input, converts this into digital data, and transmits it to a server. The output is data on the position and speed of vehicles and pedestrians.

[0517] Step 2:

[0518] The server inputs the received movement information into an AI algorithm to calculate accident risk. TensorFlow is used to analyze image and audio data and perform accident risk assessment. The analysis outputs the probability of an accident occurring within a specific time window. This output is an accident risk score used to configure the signal control device.

[0519] Step 3:

[0520] The server controls the signal control device to optimize the timing of signal display based on the calculated accident risk. The input is an accident risk score, which is used to calculate the signal change time. Specifically, if the accident risk is high, adjustments are made, such as extending the time the signal is displayed in blue. The output is the adjusted signal display schedule.

[0521] Step 4:

[0522] The user terminal uses emotion recognition to analyze the emotional state of passengers and drivers and sends the results to the server. Input data consists of facial images and audio obtained from the camera and microphone, which are used for facial recognition and voice tone analysis. The output is an assessment of the passengers' stress and relaxation levels.

[0523] Step 5:

[0524] The server uses the received emotional data to send appropriate warnings and suggestions to the user's terminal. Taking an emotional state assessment as input, if the user is experiencing stress, it outputs instructions to play relaxing music and, in some cases, suggests a rest stop. Outputs include music playback instructions and route change suggestions.

[0525] Step 6:

[0526] Users can receive suggestions from their devices and respond to them to maintain a comfortable in-car environment. Ultimately, passengers and drivers receive an improved travel experience and a sense of security.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] [Fourth Embodiment]

[0531] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0532] 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.

[0533] 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).

[0534] 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.

[0535] 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.

[0536] 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).

[0537] 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.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] 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.

[0543] 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".

[0544] The present invention is a system aimed at preventing traffic accidents at intersections, and includes a data collection device, a prediction function, a signal control device, and a user terminal.

[0545] First, data collection devices, acting as terminals, are installed at intersections to acquire real-time movement information of vehicles and pedestrians using cameras and various sensors. This information is collected as detailed data, including image data, speed, direction, and number of people.

[0546] The server receives this movement information and analyzes it using a dedicated algorithm. The analysis combines historical statistical data with current traffic conditions to predict the risk of future accidents at specific intersections. This predictive information is used for immediate accident prevention and traffic signal control.

[0547] If the risk of an accident exceeds a certain threshold, the server sends a command to the signal control unit to adjust the timing of the red and green lights. For example, if the server detects that a group of children are about to cross an intersection, it requests the signal control unit to extend the duration of the green light accordingly.

[0548] The user terminal includes an application that provides drivers and traffic managers with risk information for when they reach their destination. Drivers receive visual and audible warnings from the terminal, encouraging safe driving. Traffic managers can check the latest traffic conditions and risk assessments at intersections via a management console and make further adjustments as needed.

[0549] As a concrete example, during the morning rush hour, the system alleviates congestion by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of a child, it alerts the drivers of the relevant vehicles to ensure safe travel.

[0550] This configuration enables a system that can flexibly respond to intersection conditions and effectively reduce the risk of accidents.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] The terminal uses cameras and various sensors installed at intersections to collect real-time data on vehicles and pedestrians. This data includes images, speed, direction, and the number of pedestrians.

[0554] Step 2:

[0555] The device transmits the collected data to the server via the internet. The data is transferred in an optimized format so that it can be processed in real time.

[0556] Step 3:

[0557] The server applies an AI algorithm to analyze the received data. Based on past accident data and current traffic conditions, it calculates the accident risk at each intersection.

[0558] Step 4:

[0559] The server evaluates the calculated accident risk, and if it determines that the risk is high, it sends a command to the signal control device. This command adjusts the timing of the traffic signals in real time.

[0560] Step 5:

[0561] If the user is a driver, the user's device receives a warning from the server and provides visual or audible alerts. This allows the driver to respond to risks immediately.

[0562] Step 6:

[0563] If the user is a traffic manager, they can view real-time evaluation data on the management console and further adjust signal control and driver notifications as needed.

[0564] Step 7:

[0565] The server stores the final traffic data and accident risk assessment in a database and continuously updates the learning model to improve the overall accuracy of the system. This information contributes to improving the accuracy of future risk predictions.

[0566] (Example 1)

[0567] 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".

[0568] Modern traffic accidents at intersections often occur due to the high density of vehicles and pedestrians, as well as the inappropriate timing of traffic signal control. Furthermore, insufficient real-time information dissemination to drivers and traffic managers also contributes to the increased risk. Therefore, there is a need for systems that reduce accident risk and guarantee safe traffic flow.

[0569] 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.

[0570] In this invention, the server includes means for acquiring vehicle and pedestrian movement information in the intersection area using a data collection device, means for calculating accident risk by combining past statistical information and current situation information based on the acquired information, and means for dynamically adjusting the signal display pattern in the signal control device. This enables real-time reduction of accident risk according to traffic conditions, efficient signal control, and rapid provision of information to drivers.

[0571] A "data acquisition device" is a device installed to acquire vehicle and pedestrian movement information in an intersection area, and includes cameras and sensors for acquiring image data and speed data.

[0572] "Accident risk" is a value calculated based on statistical information and current traffic conditions to determine the likelihood of a traffic accident occurring at an intersection. This value serves as the basis for signal control and warnings to users.

[0573] A "signal control device" is a device installed near an intersection that dynamically adjusts the display time of traffic signals according to the calculated accident risk.

[0574] A "user terminal" refers to a device or application that provides drivers and traffic managers with information on intersection conditions and risks, and issues warnings as needed.

[0575] "Feedback data" refers to data collected from users and traffic managers, which is used to improve the system's analytical accuracy and response performance.

[0576] This invention is a system for preventing traffic accidents at intersections, and its components include a data collection device, a server, a signal control device, and a user terminal. These elements work together to reduce accident risk and improve traffic safety.

[0577] The data collection devices, acting as terminals, are positioned at intersections. These devices are equipped with high-resolution cameras and speed sensors to capture the real-time movement of vehicles and pedestrians, acquiring image data and detailed information such as speed, direction, and number of people. This data is immediately transmitted to a server for further analysis.

[0578] The server has a dedicated analysis algorithm that processes multiple pieces of movement information it receives. This algorithm is designed to combine historical statistics with current movement conditions to predict future accident risks. The specific analysis method employs machine learning models, and the use of generative AI models enables highly accurate predictions. The server also has an interface for issuing commands to signal control devices, dynamically adjusting the signal display pattern according to the risk level.

[0579] The signal control unit receives commands from a server and has the function of controlling the display timing of traffic lights at an intersection. For example, it can ensure safety by extending the display time of the green light when a group of pedestrians are about to pass through the intersection.

[0580] The application used as a user terminal is a tool for providing important traffic information to drivers and traffic managers. The terminal attracts the driver's attention through real-time visual and audio notifications, supporting safe driving. It also provides traffic managers with analysis results based on intersection data, offering support information for management as needed.

[0581] For example, this system can alleviate congestion during the morning rush hour by maintaining red lights for longer than usual when many vehicles begin to congregate near intersections. Additionally, if the system's sensors detect the presence of children near an intersection, it can send a warning to the driver via their device, such as "Please be careful of children at the intersection ahead."

[0582] An example of a prompt for a generated AI model would be text such as, "Design a program that uses real-time data at an intersection to control traffic signals, broken down into the steps of data collection, analysis, control, and notification."

[0583] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0584] Step 1:

[0585] The data collection device, acting as a terminal, uses cameras and sensors installed at intersections to acquire real-time movement information of vehicles and pedestrians. This information is collected in a detailed format, including image data, speed, direction, and number of people. Inputs include current video footage and sensor data from the area around the intersection. Outputs are these converted into analyzable numerical and image data.

[0586] Step 2:

[0587] The server receives movement information transmitted from the terminal and processes the data using a dedicated analysis algorithm. This algorithm combines historical traffic data with current conditions to predict the risk of future accidents. Specifically, the server applies a generative AI model to build a predictive model based on the input data. The input is movement data from the terminal, and the output is an accident risk value.

[0588] Step 3:

[0589] If the predicted accident risk value exceeds a certain threshold, the server sends a command to the signal control unit to adjust the signal display timing. For example, if the detected risk is high, the server commands the signal control unit to extend the duration of the red light. The input is the accident risk value, and the output is an instruction for the adjusted signal timing.

[0590] Step 4:

[0591] Based on the analysis results, the server sends real-time warnings to the user's terminal. Drivers are alerted by voice and on-screen warnings to be careful when approaching intersections. Inputs include risk information, and outputs include user-specific warning messages and operation guides.

[0592] Step 5:

[0593] The terminal collects feedback data from users and traffic managers and sends it to a server. This data will be used to improve the accuracy of future analyses. Specifically, the terminal provides a feedback interface, allowing users to input suggestions and opinions for improving safety. Input is user feedback data, and output is aggregated as feedback data sent to the server.

[0594] (Application Example 1)

[0595] 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".

[0596] The challenge lies in achieving optimal signal control and information provision to enable autonomous driving equipment to navigate intersections safely and efficiently, while simultaneously preventing accidents at intersections and ensuring a smooth flow of traffic.

[0597] 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.

[0598] In this invention, the server includes means for acquiring movement information of moving objects and people in an intersection area using a data acquisition device, means for calculating accident risk at the intersection using a prediction function based on the acquired movement information, and means for providing signal information and accident risk information to an autonomous driving device to support safe driving. This reduces the risk of accidents at intersections and enables the safe and smooth passage of autonomous driving devices.

[0599] A "data acquisition device" is a device installed to acquire real-time information on the movement of moving objects and people in an intersection area, and includes cameras and sensors.

[0600] The "predictive function" is a feature that analyzes collected movement data and calculates the future risk of accidents at a specific intersection.

[0601] A "signal control device" is a device that controls signal display devices installed at intersections, adjusting the timing of signal display according to the situation.

[0602] A "user terminal" is a device used by drivers or traffic managers that has the function of displaying accident risk information and warnings.

[0603] "Autonomous driving equipment" refers to devices or systems for automatically operating a vehicle, which perform safe driving based on external signal information and accident risk information.

[0604] The system for implementing this invention aims to improve safety at intersections by integrating a data collection device, a prediction function, a signal control device, a user terminal, and information provision to autonomous driving equipment.

[0605] The server receives video and sensor information from data collection devices installed at intersections and uses this information to analyze real-time location data of moving objects and people. Software such as Python and TensorFlow are used for the analysis, and the risk of accidents is calculated by integrating this with historical traffic data and current conditions. The server also uses generative AI models to optimize signal control to match the predicted risk.

[0606] Meanwhile, user terminals are provided with immediate warnings regarding accident risk information and traffic signal status. The terminals have visual and audio notification mechanisms to inform drivers and traffic managers of hazards near intersections and encourage safe driving. Specifically, a hazard level indicator is displayed on the terminal screen, and a voice assistant can provide timely instructions.

[0607] Furthermore, the autonomous driving system receives signal information and accident risk information from a server. This helps the autonomous vehicle make appropriate decisions regarding deceleration, stopping, or proceeding when approaching intersections. This information is fed into the vehicle's main controller and helps with real-time driving control.

[0608] The operation of this system will, for example, appropriately adjust traffic light waiting times at congested intersections, resulting in smoother traffic flow with less disruption. In areas with many pedestrians, traffic lights will be extended, making travel safer.

[0609] An example of a prompt message would be, "What algorithm predicts the safest signal timing based on current traffic volume data and the movement of vehicles approaching an intersection, and then issues instructions to the autonomous vehicle?" This enables the realization of a safe and efficient traffic system that utilizes the latest traffic information.

[0610] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0611] Step 1:

[0612] The server acquires location information of moving objects and people from data collection devices installed at intersections. Inputs include video data from cameras and location data from sensors. These are received and stored on an NEC cloud platform. As output, the location data is converted into a format usable in the next analysis step.

[0613] Step 2:

[0614] The server uses acquired location information to predict accident risk. The input is the location data processed in step 1. This data is analyzed using Python and TensorFlow to calculate collision risk based on movement patterns and speed. The output generates numerical values ​​for accident risk at each intersection.

[0615] Step 3:

[0616] The server creates commands for the signal control unit based on the generated accident risk figures. The input is the accident risk figures from step 2. The generating AI model executes an algorithm to optimize the timing of the green and red lights. The output is the timing to be applied to the intersection signals.

[0617] Step 4:

[0618] The user terminal receives signal timing information and accident risk information sent from the server. The input is the output from step 3. The terminal notifies the driver of this information visually and audibly and issues a warning. As output, a warning message is displayed on the terminal's display, and voice guidance is provided if necessary.

[0619] Step 5:

[0620] The autonomous driving system calculates the optimal course of action for safe driving based on signals and accident risk information provided by the server. The input is the information from step 4. Dedicated in-vehicle software is used for the calculations, making decisions such as speed adjustments and stopping. As an output, the vehicle's driving control is performed in real time.

[0621] 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.

[0622] The present invention relates to an intersection safety system incorporating an emotion engine that recognizes the emotional state of users. This system includes a data collection device, a prediction function, a signal control device, and a user terminal equipped with the emotion engine.

[0623] The terminal functions as a data collection device installed at intersections, collecting detailed information on the movement of vehicles and pedestrians through cameras and sensors. This information is obtained as image and audio data and transmitted to a server as information that takes various factors into account.

[0624] The server analyzes the data and uses an AI algorithm to calculate the accident risk at the intersection. Based on the calculated risk assessment, the signal control system adjusts the timing of the traffic lights. This adjustment may take the form of holding the signal for a longer period to improve safety when there are many children passing through.

[0625] User terminals equipped with an emotion engine recognize the emotional state of drivers and traffic managers. The terminals use voice analysis and facial recognition technology to detect changes in the user's stress levels and attention span, and transmit this information to a server. Based on this emotion data, the server adjusts the content and format of warnings and sends notifications at appropriate timing and intensity according to the emotion.

[0626] For example, during peak commuting hours when drivers are more likely to experience stress, if the emotion engine detects high levels of tension in the user, the device will display a gentle warning encouraging them to take a break. Conversely, if emotions are more unstable than usual, a more emphatic warning will be issued to draw attention. Furthermore, data from the emotion engine is stored on a server and contributes to improving future prediction algorithms.

[0627] By incorporating an emotional engine, it becomes possible to implement multifaceted safety measures that not only adjust to traffic conditions but also take into account people's psychological states, further improving the effectiveness of accident prevention at intersections.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The terminal uses cameras and sensors installed at intersections to collect real-time data on vehicle and pedestrian movement and ambient sounds. This includes image and audio data.

[0631] Step 2:

[0632] The terminal sends the collected data to the server. Upon receiving the data, the server uses an AI algorithm to analyze the traffic situation and calculate the risk of accidents.

[0633] Step 3:

[0634] The server adjusts the timing of traffic light displays via the signal control device based on the calculated accident risk. For example, if the risk is high, the red light duration is extended to allow pedestrians to cross safely.

[0635] Step 4:

[0636] The emotion engine installed in the user's device analyzes the user's voice and facial expressions to evaluate their emotional state. For example, it uses facial recognition technology to determine stress levels and attention levels.

[0637] Step 5:

[0638] The server receives emotional data and adjusts the content of notifications and the intensity of warnings based on the user's psychological state. For example, if the user is under high stress, it will send a message in a gentle tone encouraging them to take a break.

[0639] Step 6:

[0640] If the user is the driver, the user terminal provides customized warnings visually or audibly, encouraging safe driving in accordance with traffic conditions and the user's emotional state.

[0641] Step 7:

[0642] The server stores emotional and traffic data, which will be used to improve future predictive algorithms and the accuracy of emotion recognition. This makes it possible to continuously improve the overall effectiveness of the system.

[0643] (Example 2)

[0644] 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".

[0645] Conventional intersection safety systems had limitations in adjusting traffic signals based on changes in traffic conditions. In particular, they often disregarded the psychological state of users, failing to effectively prevent accidents caused by driver stress or inattention. Furthermore, they lacked sufficient flexibility in signal control and warnings in response to traffic volume and pedestrian conditions.

[0646] 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.

[0647] In this invention, the server includes information acquisition means for acquiring vehicle and pedestrian movement information in an intersection area, prediction means for calculating accident risk at the intersection using the acquired movement information, signal adjustment means for adjusting the timing of traffic light display based on the calculated accident risk, and emotion recognition and warning presentation means for recognizing the emotional state of users and presenting appropriate warnings based on that information. This makes it possible to provide multifaceted safety measures that are in line with traffic conditions and the psychological state of users.

[0648] "Information acquisition means" refers to a device or mechanism for collecting vehicle and pedestrian movement information in an intersection area, and has the function of acquiring data using sensors, cameras, etc.

[0649] The "prediction mechanism" is a mechanism for calculating the risk of accidents at intersections based on acquired movement information, and it has the function of predicting future situations using an AI algorithm.

[0650] A "signal adjustment means" is a device or mechanism that dynamically changes the display timing of traffic signals at an intersection based on the calculated accident risk, and has the function of performing control to optimize traffic flow.

[0651] "Emotion recognition means" refers to technologies that analyze and interpret the user's emotional state and detect changes in stress and attention, and have the function of determining psychological state using voice analysis, facial recognition, etc.

[0652] A "warning notification system" is a system that generates appropriate warnings according to the user's emotional state and traffic conditions and notifies the user's terminal, and has the function of providing alerts via voice and visuals.

[0653] This invention is a system for improving intersection safety and consists of several elements. First, a terminal is installed at the intersection and functions as a means of acquiring information. This terminal is equipped with a high-resolution camera and an audio sensor to collect information on vehicles and pedestrians passing through the intersection in real time. For example, a general camera module and an acoustic sensor module are used for this. The data from the terminal is transmitted to a server via wireless or wired communication.

[0654] The server is equipped with AI algorithms to analyze the received data, utilizing data analysis frameworks such as TensorFlow and PyTorch. The server uses data from information acquisition methods to predict accident risk at intersections. This prediction takes into account multiple factors, including vehicle speed, the number of pedestrians, and peak traffic conditions.

[0655] Based on the calculated risk assessment, the server controls the signal adjustment mechanism. The signal adjustment mechanism dynamically changes the timing of the traffic light display, for example, by displaying the green light for a longer period when there are many pedestrians, thereby improving safety.

[0656] Furthermore, this system incorporates emotion recognition capabilities that monitor the emotional state of users (drivers and traffic managers). For example, it can use voice analysis software and a camera installed on the terminal to estimate the driver's stress level and attention span. Appropriate warnings are then presented to the user's terminal based on their psychological state. These warnings can range from gentle messages encouraging drivers to take breaks to more emphasized alerts to draw their attention.

[0657] As a concrete example, during rush hour when drivers are prone to stress, if the emotion recognition system detects a high level of tension, the server sends a message to the user's terminal saying, "Caution is needed. Please take a break." This further enhances traffic safety.

[0658] Examples of prompts to input into the generating AI model include, "Please provide a specific operational example and explanation of a safety system that combines traffic signal control and emotion recognition at intersections." In this way, the present invention makes it possible to reduce accident risk and enhance safety at intersections in accordance with traffic conditions and the psychological state of users.

[0659] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0660] Step 1:

[0661] The terminals are installed at intersections and function as a means of acquiring information. Specifically, they use cameras and audio sensors to collect real-time data on the movement, speed, and number of vehicles and pedestrians passing through the intersection. This information is input to the terminals as image and audio data, processed by a digital signal processing unit, and then transmitted to a server.

[0662] Step 2:

[0663] The server receives image and audio data transmitted from the terminal. The received data is preprocessed to remove noise and standardize the format. Using this processed data, a generative AI model is used to predict the risk of accidents at intersections. In this process, factors such as changes in traffic volume and vehicle speed are taken into consideration to calculate a specific risk assessment.

[0664] Step 3:

[0665] The server controls the signal adjustment mechanism based on the calculated risk assessment. If a high risk is determined, it sends a signal to the signal control device to change the timing of the traffic light display. For example, during peak traffic hours, the green light is extended to ensure pedestrian safety. This dynamically optimizes the signal control pattern.

[0666] Step 4:

[0667] The device analyzes the user's voice and facial expression data using emotion recognition technology. Specifically, it uses voice analysis software to analyze the tone and speed of the voice, and a camera to evaluate facial expressions. This data is then sent to a server to provide indicators of stress and attention levels.

[0668] Step 5:

[0669] The server analyzes emotional data from users and generates appropriate warning messages based on the results. If it determines that the user's emotions are more unstable than usual, it displays a warning message on the user's device stating, "Caution is needed. Please take a break." This process helps ensure safe driving continues.

[0670] (Application Example 2)

[0671] 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".

[0672] In today's traffic environment, preventing traffic accidents at intersections is crucial, but conventional systems have only addressed risks associated with changing traffic conditions. Furthermore, the influence of the psychological state of drivers and passengers on traffic safety cannot be ignored. However, a comprehensive approach to improving safety that considers all these factors has not yet been established.

[0673] 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.

[0674] In this invention, the server includes means for acquiring movement information in the intersection area using a data collection device, means for analyzing the psychological state of passengers using an emotion recognition function, and means for presenting appropriate audio content and travel routes based on the analysis results. This makes it possible to prevent accidents and provide a safe travel experience that takes into account the dynamic changes in the traffic environment and the emotional state of users.

[0675] A "data acquisition device" is a device that acquires information on the movement of vehicles and pedestrians in an intersection area, and includes sensors that collect image data and audio data.

[0676] The "predictive function" is a function that uses acquired movement information to calculate the risk of accidents at intersections.

[0677] A "signal control device" is a device that adjusts the timing of traffic signals near an intersection based on the calculated accident risk.

[0678] The "emotion recognition function" is a feature that uses voice analysis and facial recognition technology to analyze the psychological state of passengers and, based on the results, presents appropriate audio content and travel routes.

[0679] A "user terminal" is a device used to display warnings to traffic managers and drivers, and is a system equipped with an emotion engine.

[0680] To implement this invention, a data collection device is required to collect vehicle and pedestrian movement information in the intersection area, a server is required to perform analysis and control, and a user terminal is required to recognize emotional states. The data collection device acquires vehicle and pedestrian information in real time using cameras and voice sensors installed at the intersection.

[0681] The server uses collected movement data to calculate the accident risk at intersections using AI algorithms. TensorFlow and OpenCV are used as computational software for this process. Based on the calculated risk assessment, the traffic signal control system adjusts the signal timing. For example, if there are many children crossing during school hours, the signal may be held on for a longer period to enhance safety.

[0682] Furthermore, the user terminal incorporates an emotion engine that utilizes voice analysis and facial recognition technology. This terminal analyzes the emotional state of the driver and passengers in real time and, if necessary, plays relaxing music or suggests taking a break. The analyzed emotion data is sent to a server, and any necessary warnings or suggestions are displayed on the user terminal.

[0683] For example, when a family is on a long road trip, if the emotion engine determines that the children are bored, it will play their favorite music and suggest taking a break at a park along the way. An example of a prompt sentence to provide to the generative AI model might be, "The passengers in the car seem a little worried. Please suggest ways to help them relax."

[0684] By integrating these elements, a multifaceted system can be realized to provide a sophisticated and safe transportation environment.

[0685] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0686] Step 1:

[0687] The data collection device uses cameras and audio sensors installed at intersections to acquire real-time information on the movement of vehicles and pedestrians. It receives video and audio from the environment as input, converts this into digital data, and transmits it to a server. The output is data on the position and speed of vehicles and pedestrians.

[0688] Step 2:

[0689] The server inputs the received movement information into an AI algorithm to calculate accident risk. TensorFlow is used to analyze image and audio data and perform accident risk assessment. The analysis outputs the probability of an accident occurring within a specific time window. This output is an accident risk score used to configure the signal control device.

[0690] Step 3:

[0691] The server controls the signal control device to optimize the timing of signal display based on the calculated accident risk. The input is an accident risk score, which is used to calculate the signal change time. Specifically, if the accident risk is high, adjustments are made, such as extending the time the signal is displayed in blue. The output is the adjusted signal display schedule.

[0692] Step 4:

[0693] The user terminal uses emotion recognition to analyze the emotional state of passengers and drivers and sends the results to the server. Input data consists of facial images and audio obtained from the camera and microphone, which are used for facial recognition and voice tone analysis. The output is an assessment of the passengers' stress and relaxation levels.

[0694] Step 5:

[0695] The server uses the received emotional data to send appropriate warnings and suggestions to the user's terminal. Taking an emotional state assessment as input, if the user is experiencing stress, it outputs instructions to play relaxing music and, in some cases, suggests a rest stop. Outputs include music playback instructions and route change suggestions.

[0696] Step 6:

[0697] Users can receive suggestions from their devices and respond to them to maintain a comfortable in-car environment. Ultimately, passengers and drivers receive an improved travel experience and a sense of security.

[0698] 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.

[0699] 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.

[0700] 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 robot 414.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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."

[0707] 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.

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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 as being incorporated by reference.

[0719] The following is further disclosed regarding the embodiments described above.

[0720] (Claim 1)

[0721] A means for acquiring vehicle and pedestrian movement information in an intersection area using a data collection device,

[0722] A means for calculating the risk of accidents at intersections using a prediction function based on acquired movement information,

[0723] A means for adjusting the signal control device near the intersection based on the calculated accident risk,

[0724] A means of displaying a warning to the user's terminal,

[0725] A system that includes this.

[0726] (Claim 2)

[0727] The system according to claim 1, wherein the data acquisition device is a sensor that acquires image data and audio data.

[0728] (Claim 3)

[0729] The system according to claim 1, wherein the signal control device adjusts the display timing of the traffic signals according to the calculated accident risk.

[0730] "Example 1"

[0731] (Claim 1)

[0732] A means for acquiring vehicle and pedestrian movement information in the intersection area using a data collection device,

[0733] A means of calculating accident risk by combining historical statistical information and current situational information using acquired movement information via a computer,

[0734] A means for dynamically adjusting the signal display pattern by a signal control device when the calculated accident risk exceeds a predetermined standard,

[0735] A means of displaying analysis results and warnings on the user's device to draw their attention,

[0736] A means of collecting feedback data and improving the accuracy of the analysis,

[0737] A system that includes this.

[0738] (Claim 2)

[0739] The system according to claim 1, which is a device for acquiring image data and velocity data.

[0740] (Claim 3)

[0741] The system according to claim 1, wherein the signal control device changes the display time of the signal device based on the calculated accident risk.

[0742] "Application Example 1"

[0743] (Claim 1)

[0744] A means for acquiring movement information of moving objects and people in an intersection area using a data collection device,

[0745] A means for calculating the risk of accidents at intersections using a prediction function based on acquired movement information,

[0746] A means for adjusting the signal control device near the intersection based on the calculated accident risk,

[0747] A means of displaying a warning to the user's terminal,

[0748] A means of providing signal information and accident risk information to autonomous driving equipment to support safe driving,

[0749] A system that includes this.

[0750] (Claim 2)

[0751] The system according to claim 1, wherein the data collection device is a measuring device that acquires image data and audio data.

[0752] (Claim 3)

[0753] The system according to claim 1, wherein the signal control device adjusts the display timing of the signal display device according to the calculated accident risk.

[0754] "Example 2 of combining an emotion engine"

[0755] (Claim 1)

[0756] Information acquisition means for obtaining information on the movement of vehicles and pedestrians in an intersection area,

[0757] A prediction means for calculating the accident risk at intersections using acquired movement information,

[0758] A signal adjustment means for adjusting the timing of traffic light displays based on the calculated accident risk,

[0759] An emotion recognition and warning presentation means for recognizing the user's emotional state and presenting appropriate warnings based on that information,

[0760] A system that includes this.

[0761] (Claim 2)

[0762] The system according to claim 1, wherein the information acquisition means is a sensor device for acquiring image data and audio data.

[0763] (Claim 3)

[0764] The system according to claim 1, wherein the signal adjustment means adjusts the display timing of the traffic light according to the calculated accident risk and the emotional state of the user.

[0765] "Application example 2 of combining emotional engines"

[0766] (Claim 1)

[0767] A means for acquiring vehicle and pedestrian movement information in an intersection area using a data collection device,

[0768] A means for calculating the risk of accidents at intersections using a prediction function based on acquired movement information,

[0769] A means for adjusting the signal control device near the intersection based on the calculated accident risk,

[0770] A means of analyzing the psychological state of passengers using emotion recognition functions and presenting appropriate audio content and travel routes,

[0771] A means of displaying a warning to the user's terminal,

[0772] A system that includes this.

[0773] (Claim 2)

[0774] The system according to claim 1, wherein the data collection device is a sensor that acquires image data and audio data, and further analyzes the facial expressions and voices of passengers.

[0775] (Claim 3)

[0776] The system according to claim 1, wherein the signal control device adjusts the timing of the signal display according to the calculated accident risk and controls the progress of the vehicle based on the psychological state of the passengers. [Explanation of Symbols]

[0777] 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 acquiring vehicle and pedestrian movement information in an intersection area using a data collection device, A means for calculating the risk of accidents at intersections using a prediction function based on acquired movement information, A means for adjusting the signal control device near the intersection based on the calculated accident risk, A means of displaying a warning to the user's terminal, A system that includes this.

2. The system according to claim 1, wherein the data acquisition device is a sensor that acquires image data and audio data.

3. The system according to claim 1, wherein the signal control device adjusts the display timing of the traffic signals according to the calculated accident risk.

Images