System

Abstract

A system is provided.SOLUTION: The system includes a means for installing a high-precision camera at an intersection and monitoring a traffic amount in real time, a means for analyzing an acquired image date by a generation AI model and instructing optimum signal switching corresponding to a traffic situation, and a means for automatically controlling signal switching to a signal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] At busy intersections, conventional traffic lights are unable to respond appropriately to traffic conditions that fluctuate depending on the time of day and traffic flow, resulting in chronic congestion. For this reason, there is a need for a method that can grasp traffic flow in real time and switch traffic lights flexibly. In particular, conventional fixed signal switching is unable to provide efficient traffic control, causing major disruptions during rush hour and special events. Therefore, it is necessary to switch signals in real time according to traffic volume to achieve smooth traffic flow. [Means for solving the problem]

[0005] The present invention provides a system that installs high-precision cameras at intersections to monitor traffic volume in real time. This system uses high-precision cameras to grasp the traffic situation at intersections in real time and analyzes the acquired image data using a generative AI model. The generative AI model takes into account traffic volume, vehicle direction, vehicle speed, etc. to calculate the optimal signal switching timing. The system also includes a means for automatically instructing traffic lights to switch signals based on the analysis results.

[0006] Furthermore, the system flexibly responds to time-of-day and daily fluctuations, achieving optimal signal control according to ever-changing traffic conditions. Specifically, the generative AI model updates its analysis results in real time and continuously adjusts signal switching instructions based on traffic volume and vehicle flow. This helps alleviate chronic congestion at intersections and smooth traffic flow.

[0007] A "high-precision camera" is a high-resolution imaging device that can capture traffic conditions in real time and in detail.

[0008] "Real-time" refers to instantly understanding the current situation and processing information in a timely manner.

[0009] "Traffic volume" refers to the number and flow of vehicles passing through an intersection during a particular time period.

[0010] A "generative AI model" is an artificial intelligence algorithm that analyzes traffic data and calculates the optimal timing for switching traffic lights.

[0011] "Analysis" refers to the process of examining collected data in detail and evaluating traffic volume and vehicle flow.

[0012] "Signal change instructions" refer to specific commands to adjust the color or display of traffic lights at an intersection.

[0013] "Traffic light control" refers to the management and operation of traffic light display status (red, yellow, green).

[0014] "Time of day" refers to a specific time range within a day, and is one of the factors that affect traffic patterns.

[0015] "Daily fluctuations" refers to differences in traffic conditions that change depending on specific days of the week or events.

[0016] "Traffic flow" refers to the pattern of how vehicles move through and through an intersection. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, analyzes it with a generative AI model, and issues instructions to traffic lights to achieve optimal signal switching. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[0039] Server Roles and Operations

[0040] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[0041] 1. Receiving image data

[0042] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[0043] 2. Image data preprocessing

[0044] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[0045] 3. Analysis using generative AI models

[0046] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[0047] 4. Creating signal switching instructions

[0048] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[0049] 5. Sending instructions to traffic lights

[0050] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[0051] Terminal roles and processing

[0052] The terminal is responsible for directly controlling the traffic lights.

[0053] 1. Receiving Instructions

[0054] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[0055] 2. Traffic light control

[0056] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[0057] 3. Feedback of results

[0058] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[0059] User roles and processes (for road users)

[0060] Users benefit from a real-time optimized signaling system.

[0061] 1. Check traffic light information

[0062] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[0063] 2. Passing through an intersection

[0064] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[0065] 3. Avoiding traffic jams

[0066] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[0067] Specific examples

[0068] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[0069] Server Processing

[0070] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[0071] Terminal handling

[0072] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[0073] User Action

[0074] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[0075] The above is a specific embodiment of the present invention and the flow of the entire system.

[0076] The processing flow will be explained below.

[0077] Server Processing

[0078] Step 1:

[0079] The server receives image data in real time from cameras installed at intersections.

[0080] The server connects to the camera's data stream and continuously captures video data.

[0081] Step 2:

[0082] The server performs preprocessing on the received image data.

[0083] Noise removal and resolution adjustment are performed, and the target area is cropped as necessary.

[0084] Step 3:

[0085] The server inputs the preprocessed image data into the generative AI model.

[0086] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[0087] Step 4:

[0088] Based on the analysis results, the server creates signal switching instructions to perform signal optimization.

[0089] For example, if there are many vehicles heading north, the traffic light in that direction is set to stay green for a longer period of time.

[0090] Step 5:

[0091] The server transmits a signal switching instruction to the traffic light control server.

[0092] Send instructions including specific control timing for traffic lights.

[0093] Terminal handling

[0094] Step 1:

[0095] The terminal receives a signal switching instruction from the server.

[0096] The received information includes the timing and direction of signal switching.

[0097] Step 2:

[0098] The terminal controls the traffic lights based on the instructions received.

[0099] For example, set the northbound traffic light to green and the eastbound traffic light to red.

[0100] Step 3:

[0101] The terminal checks the execution status of the signal switching and sends feedback to the server.

[0102] The feedback includes the successful completion of the signal switch.

[0103] User processing (for road users)

[0104] Step 1:

[0105] When a user approaches an intersection, the user visually checks the traffic light display.

[0106] Check the traffic light indications to prepare to pass through the intersection smoothly.

[0107] Step 2:

[0108] The user passes through the intersection following the traffic lights.

[0109] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[0110] Step 3:

[0111] To enable a user to smoothly pass through an intersection and avoid congestion.

[0112] Traffic flows more smoothly and you can reach your destination faster.

[0113] Example 1

[0114] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0115] Current traffic signal systems operate based on fixed patterns, and one issue is that they are unable to flexibly control traffic in response to real-time traffic conditions. This results in frequent traffic congestion and delays, making efficient traffic management difficult. Furthermore, there is a lack of means to accumulate and analyze the data necessary for signal control, making it impossible to achieve optimal signal control based on fluctuations and predictions of traffic volume. Furthermore, this increases the risk of traffic accidents and causes frequent inconvenience to drivers and pedestrians.

[0116] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0117] In this invention, the server includes means for receiving image data in real time from high-precision cameras installed at intersections, means for preprocessing the received image data to remove noise and adjust resolution, means for inputting the preprocessed image data into a generative AI model and analyzing traffic volume, vehicle direction, and vehicle speed, means for calculating the next signal switch timing based on the analysis results and generating specific control instructions for the traffic lights, means for transmitting the generated signal switch instructions to a traffic light control system, means for automatically controlling the signal switch of the traffic lights by the traffic light control system, and means for confirming whether the traffic light switch was performed normally and feeding back the result. This enables flexible and optimal signal control that responds to real-time traffic conditions.

[0118] A "high-precision camera" is a device that can capture the entire intersection in high resolution and provide accurate image data in real time.

[0119] "Real-time" refers to a processing method that can instantly grasp the current traffic situation and reflect it immediately.

[0120] "Traffic volume" is the number of vehicles and pedestrians passing through a particular road within a certain period of time.

[0121] "Monitoring" refers to the act of continuously observing traffic conditions at an intersection and acquiring necessary data.

[0122] "Image data" refers to visual information captured by a camera that is represented in digital form.

[0123] "Preprocessing" is a process in which acquired image data is processed, such as by removing noise and adjusting resolution, to improve the accuracy of analysis.

[0124] A "generative AI model" is an artificial intelligence program that is trained to analyze traffic situations using machine learning algorithms.

[0125] "Analysis" is the process of evaluating the acquired data in detail and extracting specific information such as traffic volume, vehicle direction, and vehicle speed.

[0126] The "signal switching instruction" is data generated as a specific operation instruction by determining the state of the next signal based on the analysis result.

[0127] "Traffic light control system" is a general term for hardware and software that receives instructions from a server and directly operates traffic lights.

[0128] "Feedback" is the process of checking the results after switching signals and reporting them to the server.

[0129] "Optimization" refers to adjusting traffic signals to control them most efficiently according to traffic volume and time of day.

[0130] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, and generates optimal switching instructions for traffic lights by analyzing the data using a generative AI model, thereby controlling traffic signals flexibly and efficiently. Below, we will explain how to specifically implement this system.

[0131] Hardware and Software Configuration

[0132] server

[0133] The server is the core of this system and uses the following hardware and software in combination:

[0134] Hardware: High-performance processor (e.g., Intel Xeon processor), large memory capacity (e.g., 32GB RAM), SSD storage (e.g., 1TB SSD)

[0135] Software: Ubuntu OS, image processing libraries (e.g., OpenCV), machine learning frameworks (e.g., TensorFlow, YOLOv5)

[0136] Terminal (traffic signal control device)

[0137] The terminal receives instructions from the server and directly controls the traffic lights. The following hardware and software are used:

[0138] Hardware: Microcontroller (e.g. Raspberry Pi), GPIO pins, relay control board

[0139] Software: Raspbian OS, HTTP communication library, GPIO control library

[0140] User

[0141] The user is a road user who checks traffic light information and benefits from an optimized traffic light system.

[0142] Data processing and calculation procedures

[0143] The server receives image data in real time from a high-precision camera (e.g., Sony Alpha series). The camera captures a panoramic view of the intersection and sends the data to the server at a rate of 30 frames per second. The server then performs noise removal and resolution adjustment on the received image data, thereby maintaining data precision and improving the accuracy of analysis. This processing is performed using the OpenCV image processing library.

[0144] The preprocessed image data is input into a generative AI model (e.g., YOLOv5). The AI ​​model is built using the Python framework TensorFlow and analyzes traffic volume, vehicle direction, and vehicle speed from the image. Based on the results of this analysis, the server calculates the next traffic light switching timing and generates specific control instructions. These instructions include the number of seconds to keep the traffic light green for each direction.

[0145] The generated signal switching instructions are sent from the server to the traffic light control system. This communication uses the HTTP protocol, and the instructions are sent in JSON format. The traffic light control system automatically controls the traffic lights based on the instructions received from the server. Specifically, it switches the LED display of the traffic lights using GPIO pins.

[0146] The system checks whether the traffic light control was successful and sends the result back to the server. This is done again using HTTP communication, and the result is sent to the server in JSON format. This feedback allows the server to obtain new data to generate the next instruction.

[0147] Examples of specific examples and prompts

[0148] During the 8:00 a.m. rush hour, when there are many vehicles coming from the north at intersection A, the system operates as follows:

[0149] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[0150] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[0151] The user enters intersection A from the north and can pass through the intersection smoothly because the traffic light is green for a long time, which reduces congestion and shortens commuting time.

[0152] Example prompt sentence:

[0153] Image data is input into the generative AI model, which analyzes traffic volume, vehicle direction, and speed.

[0154] Based on the analysis results, the next signal switching timing is calculated and traffic light control instructions are generated.

[0155] It sends instructions to the traffic light control system to control the traffic lights.

[0156] The above is an embodiment of the invention.

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1:

[0159] The server receives image data in real time from high-definition cameras installed at intersections. As input, it receives image data from the cameras in JPEG or H.264 format. The output is raw image data stored in the server's memory. Specifically, the server receives data from the cameras at a rate of 30 frames per second and prepares it for the next processing step.

[0160] Step 2:

[0161] The server performs preprocessing on the received image data. The input is the raw image data received in step 1. The data is processed using the image processing library OpenCV to remove noise (Gaussian filter) and adjust the resolution. The output is clean image data after preprocessing. Specifically, the server performs the following operations:

[0162] Apply a Gaussian filter to remove noise

[0163] Resize the image resolution to 640x480

[0164] Step 3:

[0165] The server inputs the preprocessed image data into the generative AI model for analysis. The input is the clean image data preprocessed in step 2. The generative AI model (e.g., YOLOv5, TensorFlow) analyzes traffic volume, vehicle direction, and vehicle speed from the input image data. The output is analysis result data (JSON format) showing traffic conditions. Specifically, the server performs the following operations:

[0166] Initialize the generative AI model

[0167] Input image data into the model and generate analysis results

[0168] Step 4:

[0169] The server generates signal switching instructions based on the analysis results. The input is the analysis result data obtained in step 3. For data processing, the server analyzes the analysis results and calculates the next signal switching timing and the signal status for each direction. The output is specific signal switching instructions (JSON format). Specifically, the server performs the following operations:

[0170] Analyze the analysis results and understand the traffic situation

[0171] Calculates the timing of traffic lights switching for each direction and generates specific instructions

[0172] Step 5:

[0173] The server sends the generated signal change instruction to the traffic light control system. The input is the signal change instruction (JSON format) generated in step 4. The output is the acknowledgment (HTTP response) received by the traffic light control system. Specifically, the server performs the following operations:

[0174] Send a signal switching command using the HTTP POST method

[0175] Obtaining acknowledgement from the traffic light control system

[0176] Step 6:

[0177] The terminal receives a signal switching instruction sent from the server. The input is the signal switching instruction (JSON format) from the server. The output is the signal switching instruction data stored on the terminal. In concrete terms, the terminal receives the instruction from the server via HTTP communication and prepares for the next processing step.

[0178] Step 7:

[0179] The terminal controls the traffic light based on the received signal switching instruction. The input is the signal switching instruction data received in step 6. The output is the change in the LED display of the traffic light. Specifically, the terminal performs the following operations:

[0180] Controlling traffic light LEDs using GPIO pins

[0181] Turning the traffic light green in one direction and red in another

[0182] Step 8:

[0183] The device checks whether the traffic light switch was successful and feeds the result back to the server. The input is the current state of the traffic light. The output is feedback data (in JSON format) to the server. Specifically, the device performs the following operations:

[0184] Check the traffic light status

[0185] Generate feedback data and send it to the server using the HTTP POST method

[0186] Step 9:

[0187] When approaching an intersection, the user checks the traffic light information. The input is the current road condition and the traffic light status. The output is information that allows the user to pass through the intersection safely. Specifically, the user checks the traffic light status using the navigation system or visually and performs driving operations.

[0188] Step 10:

[0189] The user passes through the intersection according to the optimized signal pattern. The input is the status of the traffic lights and the current road conditions. The output is the reduction of congestion and safe driving. As a specific action, the user passes through the intersection while the signal is green and can drive safely.

[0190] Step 11:

[0191] The user reaches their destination quickly as a result of smooth traffic flow and avoidance of congestion. The input is smooth traffic flow due to optimal control of traffic lights. The output is a state in which the user can reach their destination quickly and safely. In concrete terms, the user can reach their destination without stress.

[0192] (Application example 1)

[0193] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0194] In modern traffic systems, traffic signals at intersections are controlled in a fixed manner and are unable to respond to fluctuations in traffic volume, resulting in frequent traffic congestion. Furthermore, with the spread of autonomous vehicles, real-time traffic signal information is required, but current systems lack the mechanisms to accommodate this. Therefore, it is necessary to optimize traffic signal switching and provide traffic signal information to autonomous vehicles.

[0195] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0196] In this invention, the server includes means for installing high-precision cameras at intersections and monitoring traffic volume in real time, means for analyzing the acquired image data with a generative AI model and instructing optimal signal switching according to traffic conditions, means for automatically controlling signal switching at traffic lights, and means for providing real-time signal information to the navigation system of autonomous vehicles. This optimizes signal switching according to traffic volume, alleviating traffic congestion and enabling autonomous vehicles to pass through intersections efficiently.

[0197] A "high-precision camera" is a camera device that can capture the entire intersection in real time with high resolution, capturing detailed traffic conditions.

[0198] "Means for monitoring traffic volume in real time" refers to technology that uses high-precision cameras to instantly monitor current traffic volume and vehicle movements and acquire that data.

[0199] "Means of analyzing acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions" refers to a technology in which image data acquired from a camera is input into a generative AI model for analysis, and based on the results, optimal switching instructions are given to traffic lights.

[0200] "Means for automatically controlling signal switching for traffic lights" refers to technology that automatically adjusts the color and timing of traffic lights based on the analysis results of a generative AI model.

[0201] "Means for providing real-time traffic light information to the navigation system of an autonomous vehicle" refers to technology that provides real-time information such as the current status of traffic lights and the timing of the next change of traffic lights to the navigation system of an autonomous vehicle.

[0202] "Means to optimize signal control in response to time-of-day and daily fluctuations" refers to technology that takes into account daily and time-of-day fluctuations in traffic volume and performs optimal signal switching.

[0203] "Means that take into account traffic volume in each direction, vehicle direction of travel, and vehicle speed" refers to technology that analyzes in detail the traffic volume and vehicle movement from each direction at a specific intersection and controls traffic signals based on that information.

[0204] In this invention, a high-precision camera, a generative AI model, a traffic light control server, and a navigation system for autonomous vehicles are combined to realize a traffic light control system that utilizes real-time monitoring of traffic volume and a generative AI model. Specific embodiments of the system are described below from the perspectives of the server, terminal, and user.

[0205] Server Roles and Operations

[0206] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[0207] 1. Receiving image data

[0208] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[0209] 2. Image data preprocessing

[0210] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[0211] 3. Analysis using generative AI models

[0212] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[0213] 4. Creating signal switching instructions

[0214] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[0215] 5. Sending instructions to traffic lights

[0216] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[0217] 6. Providing information to autonomous vehicles

[0218] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the timing of the next traffic light change and the current traffic light status.

[0219] Terminal roles and processing

[0220] The terminal is responsible for directly controlling the traffic lights.

[0221] 1. Receiving Instructions

[0222] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[0223] 2. Traffic light control

[0224] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[0225] 3. Feedback of results

[0226] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[0227] User roles and processes (for road users)

[0228] Users benefit from a real-time optimized signaling system.

[0229] 1. Check traffic light information

[0230] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[0231] 2. Passing through an intersection

[0232] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[0233] 3. Avoiding traffic jams

[0234] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[0235] Specific examples

[0236] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[0237] Server Processing

[0238] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[0239] Terminal handling

[0240] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[0241] User Action

[0242] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[0243] Prompt Sentence Examples

[0244] "A high-precision camera system that uses generative AI models to analyze intersection traffic volume in real time and optimize traffic light switching. We want to create an application that provides real-time traffic light switching information to autonomous vehicles and navigation systems."

[0245] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0246] Step 1:

[0247] Receiving image data

[0248] The server receives image data in real time from a high-definition camera. The camera constantly captures the entire intersection and sends the data to the server via the Internet. The input is image data from the high-definition camera, and the output is image data stored on the server.

[0249] Step 2:

[0250] Image data preprocessing

[0251] The server performs noise reduction and resolution adjustment on the received image data. For this, it uses an image processing library (e.g., OpenCV). Preprocessing removes unnecessary noise in the image and optimizes the resolution for analysis. The input is image data from a high-precision camera, and the output is preprocessed image data.

[0252] Step 3:

[0253] Analysis using generative AI models

[0254] The server inputs the preprocessed image data into a generative AI model (e.g., TensorFlow or PyTorch) to analyze traffic conditions such as traffic volume, vehicle direction, and vehicle speed. The generative AI model analyzes the acquired data and quantifies and evaluates the traffic conditions. The input is the preprocessed image data, and the output is the analysis results of the traffic conditions.

[0255] Step 4:

[0256] Creating signal switching instructions

[0257] The server calculates the next signal switching timing based on the analysis results. Specifically, it generates instructions such as which direction the signal should be green for and for how long. The signal switching timing is determined based on the evaluation results of the generative AI model. The input is the analysis result of the traffic situation, and the output is the signal switching instruction.

[0258] Step 5:

[0259] Sending instructions to traffic lights

[0260] The server sends the created signal switching instruction to the traffic light control server. This gives specific control instructions to the traffic lights. The input is the signal switching instruction, and the output is the control instruction sent to the traffic light control server.

[0261] Step 6:

[0262] Providing information to autonomous vehicles

[0263] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the next traffic light switch timing and the current traffic light status. The input is a traffic light switch instruction, and the output is real-time traffic light information provided to the autonomous vehicle's navigation system.

[0264] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0265] This invention optimizes traffic signal control at intersections and smooths traffic flow through a system that combines a high-precision camera, a generative AI model, and an emotion engine that recognizes user emotions. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[0266] Server Roles and Operations

[0267] The server is the center of the system, responsible for analyzing traffic conditions, generating signal control instructions, and processing user emotion data.

[0268] 1. Receiving image data

[0269] The server receives real-time image data from high-precision cameras installed at intersections, which monitor the entire intersection and continuously transmit video data to the server.

[0270] 2. Image data preprocessing

[0271] The server removes noise from the received image data, adjusts the resolution, and also crops the target area to maintain data accuracy.

[0272] 3. Analysis of Traffic Conditions Using Generative AI Models

[0273] The pre-processed image data is input into a generative AI model to analyze traffic volume, vehicle direction, vehicle speed, etc. This allows for a detailed assessment of the current state of the intersection.

[0274] 4. Analysis of user emotion data using emotion engine

[0275] The server collects emotional data from the user's voice and facial expressions through an emotion engine, and detects stress levels in particular. For example, it analyzes the driver's facial expressions and the voices inside the car to determine the current emotional state.

[0276] 5. Signal switching instruction generation

[0277] Based on traffic conditions and user emotion data, the server calculates the next traffic light change timing. For example, if the user's stress level is high, the server selects a setting that switches the traffic light more smoothly.

[0278] 6. Sending instructions to traffic lights

[0279] The created signal switching instruction is sent to the traffic light control server. The instruction contains specific information such as which direction the signal should be green for and for how long.

[0280] Terminal roles and processing

[0281] The terminal is responsible for directly controlling the traffic lights at the intersection.

[0282] 1. Receiving Instructions

[0283] The terminal receives traffic light switching instructions from the server, which include the specific timing and direction of the traffic light switching.

[0284] 2. Traffic light control

[0285] Based on the received instructions, the device controls the traffic lights, for example, setting the northbound traffic light to green and the eastbound traffic light to red.

[0286] 3. Feedback of results

[0287] It checks whether the signal switching was successful and reports the result to the server. The feedback information is used to instruct the next signal switching.

[0288] User roles and processes (for road users)

[0289] Users benefit from real-time optimized signal control.

[0290] 1. Check traffic light information

[0291] As a user approaches an intersection, they check the traffic light indications visually or through their in-car navigation system.

[0292] 2. Passing through an intersection

[0293] Users can smoothly navigate through intersections by following optimized traffic light patterns. For example, the northbound traffic light will stay green longer, allowing vehicles coming from the north to proceed smoothly.

[0294] 3. Reflecting emotions

[0295] Traffic light control that reflects the user's emotions reduces stress and provides a comfortable driving environment. For example, if the emotion engine detects high stress levels in the user, it will quickly switch traffic lights to alleviate traffic congestion, which causes stress.

[0296] Specific examples

[0297] Let's take the 5:00 PM rush hour as an example. At intersection B, there is a significant increase in vehicles coming from the east.

[0298] Server Processing

[0299] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[0300] Terminal handling

[0301] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[0302] User Action

[0303] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[0304] The above is a specific embodiment of the present invention and the flow of the entire system.

[0305] The processing flow will be explained below.

[0306] Server Processing

[0307] Step 1:

[0308] The server receives image data in real time from high-precision cameras installed at intersections.

[0309] The server connects to the camera's data stream and continuously captures the video data.

[0310] Step 2:

[0311] The server preprocesses the received image data.

[0312] Remove noise, adjust resolution, and crop specific areas of intersections to improve data accuracy.

[0313] Step 3:

[0314] The server inputs the preprocessed image data into the generative AI model.

[0315] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[0316] Step 4:

[0317] The server uses an emotion engine to collect the user's voice and facial expression data and analyze the user's emotions.

[0318] In particular, it analyzes the user's facial expressions and the voices inside the car to detect stress levels.

[0319] Step 5:

[0320] The server generates optimal signal switching instructions based on traffic conditions and emotion data.

[0321] For example, if the user's stress level is high, the signal may be set to switch quickly.

[0322] Step 6:

[0323] The server transmits the generated signal switching instruction to the signal control server.

[0324] Send instructions that include the specific timing and direction of switching signals.

[0325] Terminal handling

[0326] Step 1:

[0327] The terminal receives a signal switching instruction from the server.

[0328] The received information includes the specific timing and direction of traffic light changes.

[0329] Step 2:

[0330] The terminal controls the traffic lights based on the instructions received.

[0331] For example, the northbound traffic light will turn green and the eastbound traffic light will turn red.

[0332] Step 3:

[0333] The terminal checks the execution status of the signal switching and sends feedback to the server.

[0334] The feedback includes successful completion of the signal switch.

[0335] User processing (for road users)

[0336] Step 1:

[0337] When a user approaches an intersection, the user checks the traffic light display visually or through the in-car navigation system.

[0338] Check the traffic light status, which is updated in real time, and prepare to pass through the intersection.

[0339] Step 2:

[0340] The user follows the traffic lights and passes through the intersection.

[0341] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[0342] Step 3:

[0343] Traffic light control that reflects the user's emotions reduces stress.

[0344] If the emotion engine detects high stress in the user, the traffic lights will switch quickly to ease traffic congestion, thereby reducing the user's stress.

[0345] Example 2

[0346] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0347] Conventional traffic signal control systems are often limited to monitoring traffic volume and controlling signal switching, and are unable to consider real-time changes in traffic conditions or the emotional state of users. This has resulted in problems such as congestion and a lack of reduction in user stress. The present invention aims to solve these problems and optimize traffic flow while also reducing user stress.

[0348] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0349] In this invention, the server includes a means for installing high-precision camera devices at road intersections and monitoring traffic volume in real time, a means for analyzing acquired video data using a generative AI model and optimizing traffic light switching based on traffic conditions and vehicle speed and direction, a means for adjusting traffic light switching based on an emotion analysis engine for grasping the emotional state of users, and a means for automatically controlling traffic lights to switch signals, thereby enabling real-time response to changes in traffic conditions and reducing user stress.

[0350] A "high-precision imaging device" is a device that captures high-resolution images of specific areas, such as intersections, in real time.

[0351] "Real-time" means that data is collected and processed in accordance with the current moment.

[0352] "Traffic volume" refers to the number of vehicles passing through a particular road or intersection.

[0353] A "generative AI model" refers to a model that uses machine learning algorithms to analyze data and make predictions.

[0354] "Traffic conditions" refers to the state of traffic flow and congestion at the current time.

[0355] "Vehicle speed" is a measurement of how fast a particular vehicle is traveling.

[0356] "Heading" refers to the direction in which a vehicle is moving.

[0357] "Switching lights" means that the color of a traffic light is changed.

[0358] An "emotion analysis engine" is a system that analyzes and evaluates a user's emotional state from data such as audio and video.

[0359] "Automatically" means that the system completes the action by itself without human intervention.

[0360] A "traffic light" is a device installed on a road to direct traffic.

[0361] "Users" refers to drivers and pedestrians who use the system.

[0362] "Stress" refers to a state of psychological and physiological tension caused by external stimuli or stress.

[0363] The present invention is a traffic light control system that uses a high-precision imaging device, a generative AI model, and an emotion analysis engine. Specific embodiments will be described below from the perspectives of the server, terminal, and user.

[0364] Server Roles and Operations

[0365] The server plays a central role in the system and performs the following processes:

[0366] 1. Receiving image data

[0367] The server receives real-time video data from high-definition cameras installed at intersections, which transmit the video at 1080p resolution at 30 frames per second via RTSP (Real-Time Streaming Protocol).

[0368] 2. Image data preprocessing

[0369] The server uses image processing libraries such as OpenCV to remove noise, adjust resolution, and crop the target area from the received video data, maintaining data accuracy.

[0370] 3. Analysis of Traffic Conditions Using Generative AI Models

[0371] The server inputs the preprocessed video data into a generative AI model (such as YOLO) to analyze traffic volume, vehicle direction, and vehicle speed, thereby obtaining a detailed understanding of the current situation at the intersection.

[0372] 4. Analysis of user emotion data using emotion engine

[0373] The server analyzes voice and facial expression data acquired from the in-car microphone and dashboard camera to assess the user's emotional state, particularly their stress level.

[0374] 5. Signal switching instruction generation

[0375] The server calculates the timing of the next traffic light switch based on traffic conditions and user emotion data, generates specific instructions such as which direction the signal should be green for and for how long, and sends these to the traffic light control server.

[0376] Terminal roles and processing

[0377] The terminal (traffic light control device) performs the following processing.

[0378] 1. Receiving Instructions

[0379] The terminal receives signal switching instructions from the server via the REST API.

[0380] 2. Traffic light control

[0381] The device controls the traffic lights based on the received instructions, for example, setting the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[0382] 3. Feedback of results

[0383] The device checks whether the signal switching was performed correctly using its built-in sensors and camera, and reports the results to the server.

[0384] User roles and processes (for road users)

[0385] Users benefit from the system in the following ways:

[0386] 1. Check traffic light information

[0387] When a user approaches an intersection, they check the traffic light indications visually or through the in-car navigation system.

[0388] 2. Passing through an intersection

[0389] The user follows the optimized signal pattern and passes through the intersection smoothly.

[0390] 3. Reflecting emotions

[0391] By reflecting the user's emotions in the system, stress is reduced and a comfortable driving environment is provided.

[0392] Specific examples

[0393] Let's take the 5 PM rush hour as an example. If there is a significant increase in vehicles coming from the east at intersection B, the following process will be performed.

[0394] Server Processing

[0395] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[0396] Terminal handling

[0397] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[0398] User Action

[0399] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[0400] Prompt Sentence Examples

[0401] "Analyze traffic flow at intersection B during the 5 PM rush hour, and generate signal switching instructions to accommodate the increase in vehicles coming from the east. Also, include measures to be taken when users' stress levels are high."

[0402] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0403] Step 1:

[0404] The server receives video data in real time from high-precision cameras installed at intersections.

[0405] How it works: The high-definition camera captures video at 1080p resolution at 30 frames per second and sends the data to a server using RTSP (Real-Time Streaming Protocol).

[0406] Input: Video data from an intersection.

[0407] Output: Real-time video data stored on the server.

[0408] Step 2:

[0409] The server performs pre-processing on the received video data.

[0410] Specific operations: Use image processing libraries such as OpenCV to remove noise (e.g., apply a Gaussian filter), adjust resolution (e.g., convert from Full HD to HD), and crop the target area.

[0411] Input: Real-time video data.

[0412] Output: Preprocessed video data.

[0413] Step 3:

[0414] The server inputs the preprocessed video data into a generative AI model to analyze traffic conditions.

[0415] How it works: It uses object detection models such as YOLO to analyze traffic volume, vehicle direction, and vehicle speed. For example, the model recognizes eight vehicles in an image and calculates their direction and speed.

[0416] Input: Preprocessed video data.

[0417] Output: Analysis results: traffic volume, vehicle direction, and vehicle speed.

[0418] Step 4:

[0419] The server analyzes the user's emotion data using an emotion engine.

[0420] Specific operation: Analyzes voice data collected from an in-car microphone and facial expression data acquired from a dashboard camera to assess the user's stress level. For example, stress is determined based on voice tone analysis and changes in facial expressions.

[0421] Input: speech and facial expression data.

[0422] Output: User's emotional assessment results (especially stress level).

[0423] Step 5:

[0424] The server generates a signal switching instruction based on the analysis result.

[0425] Specific operation: The system calculates the next traffic light switching timing by combining traffic conditions and user emotion data. For example, if traffic volume is heavy and the user's stress level is high, it generates a setting that shortens the waiting time at the traffic light.

[0426] Input: Traffic situation analysis results and user sentiment evaluation results.

[0427] Output: Signal switching instructions (e.g., set eastbound signal green for 90 seconds, other directions red for 30 seconds).

[0428] Step 6:

[0429] The server transmits the generated signal switching instruction to the signal control server.

[0430] Specific operation: Sends signal switching instructions securely and reliably using communication protocols such as REST API.

[0431] Input: Signal switching instruction.

[0432] Output: Instruction sent to traffic light control server completed.

[0433] Step 7:

[0434] The terminal receives signal switching instructions from the server and controls the traffic lights.

[0435] Specific behavior: For example, set the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[0436] Input: Signal switching instruction from the server.

[0437] Output: The set traffic light state.

[0438] Step 8:

[0439] The terminal checks whether the signal switching was performed correctly and feeds the result back to the server.

[0440] What it does: It uses built-in sensors and cameras to monitor traffic light status and ensures that the switch is operating correctly.

[0441] Input: Traffic light status data.

[0442] Output: Signal switching feedback information.

[0443] (Application example 2)

[0444] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0445] Conventional traffic light control systems only considered traffic volume, vehicle direction, and speed when switching signals, which did not adequately reduce the stress of drivers and passengers. Furthermore, because signal control depended solely on traffic flow conditions, it was difficult to quickly alleviate traffic congestion, especially during rush hour or specific time periods. With the widespread adoption of autonomous vehicles, there is a demand for more precise signal control while also improving the comfort of passengers inside the vehicle.

[0446] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0447] In this invention, the server includes a means for installing high-precision cameras at intersections and monitoring traffic volume in real time, a means for analyzing the acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions, a means for collecting user emotion data using an emotion engine and reflecting it in signal control, a means for automatically controlling signal switching at traffic lights, and a means for detecting stress levels using an emotion engine installed in the vehicle and reflecting it in signal switching. This enables highly accurate analysis of traffic conditions at intersections and signal control that takes the user's emotional state into consideration. As a result, stress caused by waiting at traffic lights can be reduced and traffic flow can be maintained smoothly.

[0448] A "high-precision camera" is a camera that can capture traffic conditions in real time with high resolution and accuracy.

[0449] A "generative AI model" is an artificial intelligence model that analyzes acquired image data, extracts information such as traffic volume, vehicle direction and speed, and performs optimal signal control according to the system.

[0450] The "emotion engine" is an analysis engine that collects emotional data from the user's voice and facial expressions, and in particular detects stress levels.

[0451] A "traffic signal control server" is a server that generates instructions to control traffic lights installed at intersections and automatically switches between traffic lights.

[0452] The "in-vehicle emotion engine" is a system that is installed inside an autonomous vehicle to collect and analyze emotional data from passengers in real time.

[0453] "Signal switch instructions" are instructions that specify the timing and direction of traffic light switch based on data analyzed by the generative AI model and emotion engine.

[0454] "Traffic conditions" refers to detailed information such as traffic flow at intersections, vehicle direction, speed, and congestion status.

[0455] "User emotional data" is data relating to a user's emotional state, particularly stress level, that is collected using the emotion engine.

[0456] This invention is a system that analyzes traffic conditions and the emotional state of the user in real time to achieve optimal signal control so that autonomous vehicles can pass through intersections smoothly. Below, we will explain in detail the processing, hardware, and software from the perspectives of the server, terminal, and user.

[0457] Server Roles and Operations

[0458] The server is the center of the system and is responsible for analyzing traffic conditions, generating signal control instructions, processing user emotion data, etc. The server uses the following hardware and software:

[0459] High-precision cameras: Capture high-precision images of traffic conditions in real time.

[0460] Generative AI model: Analyzes acquired image data and generates detailed traffic data for signal control.

[0461] Emotion engine: Collects emotional data from the user's voice and facial expressions, particularly to detect stress levels.

[0462] Server system: Receives data, analyzes it, generates instructions, and sends them.

[0463] Specifically, the server first receives image data in real time from high-precision cameras installed at intersections. The image data is then analyzed using a generative AI model to extract information such as traffic volume, vehicle direction, and vehicle speed. Furthermore, the emotion engine receives user emotion data from an emotion engine installed inside the vehicle, identifying stress levels in particular. Based on this data, optimal signal switching instructions are generated and sent to the traffic light control server.

[0464] Terminal roles and processing

[0465] The terminal is responsible for directly controlling the traffic lights at the intersection. The terminal uses the following hardware and software:

[0466] Traffic light control system: Controls traffic lights based on instructions from the server.

[0467] Communication module: Receives signal switching instructions from the server and transmits them to the traffic light control system.

[0468] Specifically, the device receives traffic light switching instructions from the server in real time and controls the traffic lights based on those instructions. For example, it may receive an instruction such as "set the northbound traffic light to green for 90 seconds and the eastbound traffic light to red for 30 seconds." It then sends feedback to the server that the traffic light switching has been successfully completed.

[0469] User Roles and Actions

[0470] The user is responsible for operating the autonomous vehicle and generating emotion data. The following hardware and software are installed in the user's vehicle:

[0471] In-car camera and microphone: Devices for collecting the user's facial expressions and voice.

[0472] In-car emotion engine: Analyzes collected data and identifies the user's emotional state.

[0473] Specifically, the user drives the vehicle in a relaxed state. The in-vehicle camera and microphone collect the user's facial expressions and voice in real time, and the emotion engine analyzes the user's stress level. The analyzed data is sent to a server and used to generate traffic light control instructions.

[0474] Specific examples

[0475] For example, during the 5:00 PM rush hour, there is a significant increase in vehicles traveling east at Intersection B. The server analyzes camera images and confirms that there is an increase in vehicles traveling east. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to set the eastbound traffic light to green for 90 seconds and the north-southbound traffic light to red for 30 seconds, and sends these instructions to the traffic light control server. As a result, users traveling east toward Intersection B can pass through the intersection smoothly and without stress.

[0476] Prompt Sentence Examples

[0477] As an example of a specific prompt sentence for a generative AI model, enter the following:

[0478] "Provide an image of the intersection and analyze traffic volume, vehicle direction, and speed. Return the following data:

[0479] Total number of vehicles

[0480] Number of vehicles in each direction (north, south, east, west)

[0481] Average vehicle speed

[0482] Direction of traffic congestion (presence or absence)

[0483] In this way, traffic conditions at intersections can be analyzed with high accuracy and in real time, enabling optimal signal control that reflects the user's emotional state.

[0484] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0485] Step 1:

[0486] The server receives image data in real time from high-precision cameras installed at intersections.

[0487] Input: Live video from high-definition cameras at the intersection

[0488] Output: Real-time image data

[0489] The server uses this image data to prepare for the next step.

[0490] Step 2:

[0491] The server performs preprocessing on the received image data, specifically noise removal and resolution adjustment.

[0492] Input: Real-time image data

[0493] Output: Preprocessed image data

[0494] The server uses the OpenCV library to perform Gaussian blurring to remove noise and adjust the resolution of the data.

[0495] Step 3:

[0496] The server inputs the preprocessed image data into a generative AI model to analyze traffic conditions.

[0497] Input: Preprocessed image data

[0498] Output: Analysis data such as traffic volume, vehicle direction, and vehicle speed

[0499] The server uses a generative AI model to extract from the image data the total number of vehicles, the number of vehicles in each direction, the average vehicle speed, and the direction of traffic congestion.

[0500] Step 4:

[0501] The server collects the user's emotional data from an emotion engine installed in the vehicle, and detects the user's stress level in particular.

[0502] Input: Audio and image data from the in-car camera and microphone

[0503] Output: User's emotional data (e.g., stress level)

[0504] The emotion engine analyzes the user's voice and facial expressions, and in particular quantifies their stress level and sends it to the server.

[0505] Step 5:

[0506] The server generates optimal signal switching instructions based on traffic data and emotion data.

[0507] Input: Traffic data, emotion data

[0508] Output: Signal switching instruction

[0509] The server generates specific instructions, including the timing and direction of traffic light changes, based on data obtained from the generative AI model and emotion engine.

[0510] Step 6:

[0511] The server transmits the generated signal switching instruction to the signal control server.

[0512] Input: Signal switching instruction

[0513] Output: Send instructions to the signal control server

[0514] The instructions include specifics such as "set the northbound traffic light green for 90 seconds and the eastbound traffic light red for 30 seconds."

[0515] Step 7:

[0516] The terminal receives signal switching instructions from the server and controls the traffic lights based on the instructions.

[0517] Input: Signal switching instruction

[0518] Output: Traffic light operation (switching between green and red lights)

[0519] The device follows the instructions to change the status of the traffic lights and control traffic within the intersection.

[0520] Step 8:

[0521] The terminal will then provide feedback to the server that the signal switch has been successfully completed.

[0522] Input: Traffic light status data

[0523] Output: Signal switching completion confirmation data

[0524] The terminal checks the result of the signal switching and sends it as feedback to the server.

[0525] Step 9:

[0526] The user follows the optimized signal pattern and passes through the intersection smoothly.

[0527] Input: Traffic light display status

[0528] Output: Smooth passage through intersections

[0529] Users can check the status of traffic lights and pass through intersections with less stress.

[0530] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0531] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0532] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0533] [Second embodiment]

[0534] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0535] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0536] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0537] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0538] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0539] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0540] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0541] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0542] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0543] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0544] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0545] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0546] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, analyzes it with a generative AI model, and issues instructions to traffic lights to achieve optimal signal switching. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[0547] Server Roles and Operations

[0548] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[0549] 1. Receiving image data

[0550] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[0551] 2. Image data preprocessing

[0552] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[0553] 3. Analysis using generative AI models

[0554] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[0555] 4. Creating signal switching instructions

[0556] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[0557] 5. Sending instructions to traffic lights

[0558] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[0559] Terminal roles and processing

[0560] The terminal is responsible for directly controlling the traffic lights.

[0561] 1. Receiving Instructions

[0562] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[0563] 2. Traffic light control

[0564] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[0565] 3. Feedback of results

[0566] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[0567] User roles and processes (for road users)

[0568] Users benefit from a real-time optimized signaling system.

[0569] 1. Check traffic light information

[0570] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[0571] 2. Passing through an intersection

[0572] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[0573] 3. Avoiding traffic jams

[0574] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[0575] Specific examples

[0576] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[0577] Server Processing

[0578] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[0579] Terminal handling

[0580] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[0581] User Action

[0582] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[0583] The above is a specific embodiment of the present invention and the flow of the entire system.

[0584] The processing flow will be explained below.

[0585] Server Processing

[0586] Step 1:

[0587] The server receives image data in real time from cameras installed at intersections.

[0588] The server connects to the camera's data stream and continuously captures video data.

[0589] Step 2:

[0590] The server performs preprocessing on the received image data.

[0591] Noise removal and resolution adjustment are performed, and the target area is cropped as necessary.

[0592] Step 3:

[0593] The server inputs the preprocessed image data into the generative AI model.

[0594] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[0595] Step 4:

[0596] Based on the analysis results, the server creates signal switching instructions to perform signal optimization.

[0597] For example, if there are many vehicles heading north, the traffic light in that direction is set to stay green for a longer period of time.

[0598] Step 5:

[0599] The server transmits a signal switching instruction to the traffic light control server.

[0600] Send instructions including specific control timing for traffic lights.

[0601] Terminal handling

[0602] Step 1:

[0603] The terminal receives a signal switching instruction from the server.

[0604] The received information includes the timing and direction of signal switching.

[0605] Step 2:

[0606] The terminal controls the traffic lights based on the instructions received.

[0607] For example, set the northbound traffic light to green and the eastbound traffic light to red.

[0608] Step 3:

[0609] The terminal checks the execution status of the signal switching and sends feedback to the server.

[0610] The feedback includes the successful completion of the signal switch.

[0611] User processing (for road users)

[0612] Step 1:

[0613] When a user approaches an intersection, the user visually checks the traffic light display.

[0614] Check the traffic light indications to prepare to pass through the intersection smoothly.

[0615] Step 2:

[0616] The user passes through the intersection following the traffic lights.

[0617] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[0618] Step 3:

[0619] To enable a user to smoothly pass through an intersection and avoid congestion.

[0620] Traffic flows more smoothly and you can reach your destination faster.

[0621] Example 1

[0622] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0623] Current traffic signal systems operate based on fixed patterns, and one issue is that they are unable to flexibly control traffic in response to real-time traffic conditions. This results in frequent traffic congestion and delays, making efficient traffic management difficult. Furthermore, there is a lack of means to accumulate and analyze the data necessary for signal control, making it impossible to achieve optimal signal control based on fluctuations and predictions of traffic volume. Furthermore, this increases the risk of traffic accidents and causes frequent inconvenience to drivers and pedestrians.

[0624] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0625] In this invention, the server includes means for receiving image data in real time from high-precision cameras installed at intersections, means for preprocessing the received image data to remove noise and adjust resolution, means for inputting the preprocessed image data into a generative AI model and analyzing traffic volume, vehicle direction, and vehicle speed, means for calculating the next signal switch timing based on the analysis results and generating specific control instructions for the traffic lights, means for transmitting the generated signal switch instructions to a traffic light control system, means for automatically controlling the signal switch of the traffic lights by the traffic light control system, and means for confirming whether the traffic light switch was performed normally and feeding back the result. This enables flexible and optimal signal control that responds to real-time traffic conditions.

[0626] A "high-precision camera" is a device that can capture the entire intersection in high resolution and provide accurate image data in real time.

[0627] "Real-time" refers to a processing method that can instantly grasp the current traffic situation and reflect it immediately.

[0628] "Traffic volume" is the number of vehicles and pedestrians passing through a particular road within a certain period of time.

[0629] "Monitoring" refers to the act of continuously observing traffic conditions at an intersection and acquiring necessary data.

[0630] "Image data" refers to visual information captured by a camera that is represented in digital form.

[0631] "Preprocessing" is a process in which acquired image data is processed, such as by removing noise and adjusting resolution, to improve the accuracy of analysis.

[0632] A "generative AI model" is an artificial intelligence program that is trained to analyze traffic situations using machine learning algorithms.

[0633] "Analysis" is the process of evaluating the acquired data in detail and extracting specific information such as traffic volume, vehicle direction, and vehicle speed.

[0634] The "signal switching instruction" is data generated as a specific operation instruction by determining the state of the next signal based on the analysis result.

[0635] "Traffic light control system" is a general term for hardware and software that receives instructions from a server and directly operates traffic lights.

[0636] "Feedback" is the process of checking the results after switching signals and reporting them to the server.

[0637] "Optimization" refers to adjusting traffic signals to control them most efficiently according to traffic volume and time of day.

[0638] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, and generates optimal switching instructions for traffic lights by analyzing the data using a generative AI model, thereby controlling traffic signals flexibly and efficiently. Below, we will explain how to specifically implement this system.

[0639] Hardware and Software Configuration

[0640] server

[0641] The server is the core of this system and uses the following hardware and software in combination:

[0642] Hardware: High-performance processor (e.g., Intel Xeon processor), large memory capacity (e.g., 32GB RAM), SSD storage (e.g., 1TB SSD)

[0643] Software: Ubuntu OS, image processing libraries (e.g., OpenCV), machine learning frameworks (e.g., TensorFlow, YOLOv5)

[0644] Terminal (traffic signal control device)

[0645] The terminal receives instructions from the server and directly controls the traffic lights. The following hardware and software are used:

[0646] Hardware: Microcontroller (e.g. Raspberry Pi), GPIO pins, relay control board

[0647] Software: Raspbian OS, HTTP communication library, GPIO control library

[0648] User

[0649] The user is a road user who checks traffic light information and benefits from an optimized traffic light system.

[0650] Data processing and calculation procedures

[0651] The server receives image data in real time from a high-precision camera (e.g., Sony Alpha series). The camera captures a panoramic view of the intersection and sends the data to the server at a rate of 30 frames per second. The server then performs noise removal and resolution adjustment on the received image data, thereby maintaining data precision and improving the accuracy of analysis. This processing is performed using the OpenCV image processing library.

[0652] The preprocessed image data is input into a generative AI model (e.g., YOLOv5). The AI ​​model is built using the Python framework TensorFlow and analyzes traffic volume, vehicle direction, and vehicle speed from the image. Based on the results of this analysis, the server calculates the next traffic light switching timing and generates specific control instructions. These instructions include the number of seconds to keep the traffic light green for each direction.

[0653] The generated signal switching instructions are sent from the server to the traffic light control system. This communication uses the HTTP protocol, and the instructions are sent in JSON format. The traffic light control system automatically controls the traffic lights based on the instructions received from the server. Specifically, it switches the LED display of the traffic lights using GPIO pins.

[0654] The system checks whether the traffic light control was successful and sends the result back to the server. This is done again using HTTP communication, and the result is sent to the server in JSON format. This feedback allows the server to obtain new data to generate the next instruction.

[0655] Examples of specific examples and prompts

[0656] During the 8:00 a.m. rush hour, when there are many vehicles coming from the north at intersection A, the system operates as follows:

[0657] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[0658] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[0659] The user enters intersection A from the north and can pass through the intersection smoothly because the traffic light is green for a long time, which reduces congestion and shortens commuting time.

[0660] Example prompt sentence:

[0661] Image data is input into the generative AI model, which analyzes traffic volume, vehicle direction, and speed.

[0662] Based on the analysis results, the next signal switching timing is calculated and traffic light control instructions are generated.

[0663] It sends instructions to the traffic light control system to control the traffic lights.

[0664] The above is an embodiment of the invention.

[0665] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0666] Step 1:

[0667] The server receives image data in real time from high-definition cameras installed at intersections. As input, it receives image data from the cameras in JPEG or H.264 format. The output is raw image data stored in the server's memory. Specifically, the server receives data from the cameras at a rate of 30 frames per second and prepares it for the next processing step.

[0668] Step 2:

[0669] The server performs preprocessing on the received image data. The input is the raw image data received in step 1. The data is processed using the image processing library OpenCV to remove noise (Gaussian filter) and adjust the resolution. The output is clean image data after preprocessing. Specifically, the server performs the following operations:

[0670] Apply a Gaussian filter to remove noise

[0671] Resize the image resolution to 640x480

[0672] Step 3:

[0673] The server inputs the preprocessed image data into the generative AI model for analysis. The input is the clean image data preprocessed in step 2. The generative AI model (e.g., YOLOv5, TensorFlow) analyzes traffic volume, vehicle direction, and vehicle speed from the input image data. The output is analysis result data (JSON format) showing traffic conditions. Specifically, the server performs the following operations:

[0674] Initialize the generative AI model

[0675] Input image data into the model and generate analysis results

[0676] Step 4:

[0677] The server generates signal switching instructions based on the analysis results. The input is the analysis result data obtained in step 3. For data processing, the server analyzes the analysis results and calculates the next signal switching timing and the signal status for each direction. The output is specific signal switching instructions (JSON format). Specifically, the server performs the following operations:

[0678] Analyze the analysis results and understand the traffic situation

[0679] Calculates the timing of traffic lights switching for each direction and generates specific instructions

[0680] Step 5:

[0681] The server sends the generated signal change instruction to the traffic light control system. The input is the signal change instruction (JSON format) generated in step 4. The output is the acknowledgment (HTTP response) received by the traffic light control system. Specifically, the server performs the following operations:

[0682] Send a signal switching command using the HTTP POST method

[0683] Obtaining acknowledgement from the traffic light control system

[0684] Step 6:

[0685] The terminal receives a signal switching instruction sent from the server. The input is the signal switching instruction (JSON format) from the server. The output is the signal switching instruction data stored on the terminal. In concrete terms, the terminal receives the instruction from the server via HTTP communication and prepares for the next processing step.

[0686] Step 7:

[0687] The terminal controls the traffic light based on the received signal switching instruction. The input is the signal switching instruction data received in step 6. The output is the change in the LED display of the traffic light. Specifically, the terminal performs the following operations:

[0688] Controlling traffic light LEDs using GPIO pins

[0689] Turning the traffic light green in one direction and red in another

[0690] Step 8:

[0691] The device checks whether the traffic light switch was successful and feeds the result back to the server. The input is the current state of the traffic light. The output is feedback data (in JSON format) to the server. Specifically, the device performs the following operations:

[0692] Check the traffic light status

[0693] Generate feedback data and send it to the server using the HTTP POST method

[0694] Step 9:

[0695] When approaching an intersection, the user checks the traffic light information. The input is the current road condition and the traffic light status. The output is information that allows the user to pass through the intersection safely. Specifically, the user checks the traffic light status using the navigation system or visually and performs driving operations.

[0696] Step 10:

[0697] The user passes through the intersection according to the optimized signal pattern. The input is the status of the traffic lights and the current road conditions. The output is the reduction of congestion and safe driving. As a specific action, the user passes through the intersection while the signal is green and can drive safely.

[0698] Step 11:

[0699] The user reaches their destination quickly as a result of smooth traffic flow and avoidance of congestion. The input is smooth traffic flow due to optimal control of traffic lights. The output is a state in which the user can reach their destination quickly and safely. In concrete terms, the user can reach their destination without stress.

[0700] (Application example 1)

[0701] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0702] In modern traffic systems, traffic signals at intersections are controlled in a fixed manner and are unable to respond to fluctuations in traffic volume, resulting in frequent traffic congestion. Furthermore, with the spread of autonomous vehicles, real-time traffic signal information is required, but current systems lack the mechanisms to accommodate this. Therefore, it is necessary to optimize traffic signal switching and provide traffic signal information to autonomous vehicles.

[0703] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0704] In this invention, the server includes means for installing high-precision cameras at intersections and monitoring traffic volume in real time, means for analyzing the acquired image data with a generative AI model and instructing optimal signal switching according to traffic conditions, means for automatically controlling signal switching at traffic lights, and means for providing real-time signal information to the navigation system of autonomous vehicles. This optimizes signal switching according to traffic volume, alleviating traffic congestion and enabling autonomous vehicles to pass through intersections efficiently.

[0705] A "high-precision camera" is a camera device that can capture the entire intersection in real time with high resolution, capturing detailed traffic conditions.

[0706] "Means for monitoring traffic volume in real time" refers to technology that uses high-precision cameras to instantly monitor current traffic volume and vehicle movements and acquire that data.

[0707] "Means of analyzing acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions" refers to a technology in which image data acquired from a camera is input into a generative AI model for analysis, and based on the results, optimal switching instructions are given to traffic lights.

[0708] "Means for automatically controlling signal switching for traffic lights" refers to technology that automatically adjusts the color and timing of traffic lights based on the analysis results of a generative AI model.

[0709] "Means for providing real-time traffic light information to the navigation system of an autonomous vehicle" refers to technology that provides real-time information such as the current status of traffic lights and the timing of the next change of traffic lights to the navigation system of an autonomous vehicle.

[0710] "Means to optimize signal control in response to time-of-day and daily fluctuations" refers to technology that takes into account daily and time-of-day fluctuations in traffic volume and performs optimal signal switching.

[0711] "Means that take into account traffic volume in each direction, vehicle direction of travel, and vehicle speed" refers to technology that analyzes in detail the traffic volume and vehicle movement from each direction at a specific intersection and controls traffic signals based on that information.

[0712] In this invention, a high-precision camera, a generative AI model, a traffic light control server, and a navigation system for autonomous vehicles are combined to realize a traffic light control system that utilizes real-time monitoring of traffic volume and a generative AI model. Specific embodiments of the system are described below from the perspectives of the server, terminal, and user.

[0713] Server Roles and Operations

[0714] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[0715] 1. Receiving image data

[0716] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[0717] 2. Image data preprocessing

[0718] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[0719] 3. Analysis using generative AI models

[0720] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[0721] 4. Creating signal switching instructions

[0722] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[0723] 5. Sending instructions to traffic lights

[0724] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[0725] 6. Providing information to autonomous vehicles

[0726] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the timing of the next traffic light change and the current traffic light status.

[0727] Terminal roles and processing

[0728] The terminal is responsible for directly controlling the traffic lights.

[0729] 1. Receiving Instructions

[0730] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[0731] 2. Traffic light control

[0732] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[0733] 3. Feedback of results

[0734] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[0735] User roles and processes (for road users)

[0736] Users benefit from a real-time optimized signaling system.

[0737] 1. Check traffic light information

[0738] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[0739] 2. Passing through an intersection

[0740] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[0741] 3. Avoiding traffic jams

[0742] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[0743] Specific examples

[0744] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[0745] Server Processing

[0746] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[0747] Terminal handling

[0748] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[0749] User Action

[0750] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[0751] Prompt Sentence Examples

[0752] "A high-precision camera system that uses generative AI models to analyze intersection traffic volume in real time and optimize traffic light switching. We want to create an application that provides real-time traffic light switching information to autonomous vehicles and navigation systems."

[0753] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0754] Step 1:

[0755] Receiving image data

[0756] The server receives image data in real time from a high-definition camera. The camera constantly captures the entire intersection and sends the data to the server via the Internet. The input is image data from the high-definition camera, and the output is image data stored on the server.

[0757] Step 2:

[0758] Image data preprocessing

[0759] The server performs noise reduction and resolution adjustment on the received image data. For this, it uses an image processing library (e.g., OpenCV). Preprocessing removes unnecessary noise in the image and optimizes the resolution for analysis. The input is image data from a high-precision camera, and the output is preprocessed image data.

[0760] Step 3:

[0761] Analysis using generative AI models

[0762] The server inputs the preprocessed image data into a generative AI model (e.g., TensorFlow or PyTorch) to analyze traffic conditions such as traffic volume, vehicle direction, and vehicle speed. The generative AI model analyzes the acquired data and quantifies and evaluates the traffic conditions. The input is the preprocessed image data, and the output is the analysis results of the traffic conditions.

[0763] Step 4:

[0764] Creating signal switching instructions

[0765] The server calculates the next signal switching timing based on the analysis results. Specifically, it generates instructions such as which direction the signal should be green for and for how long. The signal switching timing is determined based on the evaluation results of the generative AI model. The input is the analysis result of the traffic situation, and the output is the signal switching instruction.

[0766] Step 5:

[0767] Sending instructions to traffic lights

[0768] The server sends the created signal switching instruction to the traffic light control server. This gives specific control instructions to the traffic lights. The input is the signal switching instruction, and the output is the control instruction sent to the traffic light control server.

[0769] Step 6:

[0770] Providing information to autonomous vehicles

[0771] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the next traffic light switch timing and the current traffic light status. The input is a traffic light switch instruction, and the output is real-time traffic light information provided to the autonomous vehicle's navigation system.

[0772] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0773] This invention optimizes traffic signal control at intersections and smooths traffic flow through a system that combines a high-precision camera, a generative AI model, and an emotion engine that recognizes user emotions. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[0774] Server Roles and Operations

[0775] The server is the center of the system, responsible for analyzing traffic conditions, generating signal control instructions, and processing user emotion data.

[0776] 1. Receiving image data

[0777] The server receives real-time image data from high-precision cameras installed at intersections, which monitor the entire intersection and continuously transmit video data to the server.

[0778] 2. Image data preprocessing

[0779] The server removes noise from the received image data, adjusts the resolution, and also crops the target area to maintain data accuracy.

[0780] 3. Analysis of Traffic Conditions Using Generative AI Models

[0781] The pre-processed image data is input into a generative AI model to analyze traffic volume, vehicle direction, vehicle speed, etc. This allows for a detailed assessment of the current state of the intersection.

[0782] 4. Analysis of user emotion data using emotion engine

[0783] The server collects emotional data from the user's voice and facial expressions through an emotion engine, and detects stress levels in particular. For example, it analyzes the driver's facial expressions and the voices inside the car to determine the current emotional state.

[0784] 5. Signal switching instruction generation

[0785] Based on traffic conditions and user emotion data, the server calculates the next traffic light change timing. For example, if the user's stress level is high, the server selects a setting that switches the traffic light more smoothly.

[0786] 6. Sending instructions to traffic lights

[0787] The created signal switching instruction is sent to the traffic light control server. The instruction contains specific information such as which direction the signal should be green for and for how long.

[0788] Terminal roles and processing

[0789] The terminal is responsible for directly controlling the traffic lights at the intersection.

[0790] 1. Receiving Instructions

[0791] The terminal receives traffic light switching instructions from the server, which include the specific timing and direction of the traffic light switching.

[0792] 2. Traffic light control

[0793] Based on the received instructions, the device controls the traffic lights, for example, setting the northbound traffic light to green and the eastbound traffic light to red.

[0794] 3. Feedback of results

[0795] It checks whether the signal switching was successful and reports the result to the server. The feedback information is used to instruct the next signal switching.

[0796] User roles and processes (for road users)

[0797] Users benefit from real-time optimized signal control.

[0798] 1. Check traffic light information

[0799] As a user approaches an intersection, they check the traffic light indications visually or through their in-car navigation system.

[0800] 2. Passing through an intersection

[0801] Users can smoothly navigate through intersections by following optimized traffic light patterns. For example, the northbound traffic light will stay green longer, allowing vehicles coming from the north to proceed smoothly.

[0802] 3. Reflecting emotions

[0803] Traffic light control that reflects the user's emotions reduces stress and provides a comfortable driving environment. For example, if the emotion engine detects high stress levels in the user, it will quickly switch traffic lights to alleviate traffic congestion, which causes stress.

[0804] Specific examples

[0805] Let's take the 5:00 PM rush hour as an example. At intersection B, there is a significant increase in vehicles coming from the east.

[0806] Server Processing

[0807] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[0808] Terminal handling

[0809] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[0810] User Action

[0811] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[0812] The above is a specific embodiment of the present invention and the flow of the entire system.

[0813] The processing flow will be explained below.

[0814] Server Processing

[0815] Step 1:

[0816] The server receives image data in real time from high-precision cameras installed at intersections.

[0817] The server connects to the camera's data stream and continuously captures the video data.

[0818] Step 2:

[0819] The server preprocesses the received image data.

[0820] Remove noise, adjust resolution, and crop specific areas of intersections to improve data accuracy.

[0821] Step 3:

[0822] The server inputs the preprocessed image data into the generative AI model.

[0823] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[0824] Step 4:

[0825] The server uses an emotion engine to collect the user's voice and facial expression data and analyze the user's emotions.

[0826] In particular, it analyzes the user's facial expressions and the voices inside the car to detect stress levels.

[0827] Step 5:

[0828] The server generates optimal signal switching instructions based on traffic conditions and emotion data.

[0829] For example, if the user's stress level is high, the signal may be set to switch quickly.

[0830] Step 6:

[0831] The server transmits the generated signal switching instruction to the signal control server.

[0832] Send instructions that include the specific timing and direction of switching signals.

[0833] Terminal handling

[0834] Step 1:

[0835] The terminal receives a signal switching instruction from the server.

[0836] The received information includes the specific timing and direction of traffic light changes.

[0837] Step 2:

[0838] The terminal controls the traffic lights based on the instructions received.

[0839] For example, the northbound traffic light will turn green and the eastbound traffic light will turn red.

[0840] Step 3:

[0841] The terminal checks the execution status of the signal switching and sends feedback to the server.

[0842] The feedback includes successful completion of the signal switch.

[0843] User processing (for road users)

[0844] Step 1:

[0845] When a user approaches an intersection, the user checks the traffic light display visually or through the in-car navigation system.

[0846] Check the traffic light status, which is updated in real time, and prepare to pass through the intersection.

[0847] Step 2:

[0848] The user follows the traffic lights and passes through the intersection.

[0849] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[0850] Step 3:

[0851] Traffic light control that reflects the user's emotions reduces stress.

[0852] If the emotion engine detects high stress in the user, the traffic lights will switch quickly to ease traffic congestion, thereby reducing the user's stress.

[0853] Example 2

[0854] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0855] Conventional traffic signal control systems are often limited to monitoring traffic volume and controlling signal switching, and are unable to consider real-time changes in traffic conditions or the emotional state of users. This has resulted in problems such as congestion and a lack of reduction in user stress. The present invention aims to solve these problems and optimize traffic flow while also reducing user stress.

[0856] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0857] In this invention, the server includes a means for installing high-precision camera devices at road intersections and monitoring traffic volume in real time, a means for analyzing acquired video data using a generative AI model and optimizing traffic light switching based on traffic conditions and vehicle speed and direction, a means for adjusting traffic light switching based on an emotion analysis engine for grasping the emotional state of users, and a means for automatically controlling traffic lights to switch signals, thereby enabling real-time response to changes in traffic conditions and reducing user stress.

[0858] A "high-precision imaging device" is a device that captures high-resolution images of specific areas, such as intersections, in real time.

[0859] "Real-time" means that data is collected and processed in accordance with the current moment.

[0860] "Traffic volume" refers to the number of vehicles passing through a particular road or intersection.

[0861] A "generative AI model" refers to a model that uses machine learning algorithms to analyze data and make predictions.

[0862] "Traffic conditions" refers to the state of traffic flow and congestion at the current time.

[0863] "Vehicle speed" is a measurement of how fast a particular vehicle is traveling.

[0864] "Heading" refers to the direction in which a vehicle is moving.

[0865] "Switching lights" means that the color of a traffic light is changed.

[0866] An "emotion analysis engine" is a system that analyzes and evaluates a user's emotional state from data such as audio and video.

[0867] "Automatically" means that the system completes the action by itself without human intervention.

[0868] A "traffic light" is a device installed on a road to direct traffic.

[0869] "Users" refers to drivers and pedestrians who use the system.

[0870] "Stress" refers to a state of psychological and physiological tension caused by external stimuli or stress.

[0871] The present invention is a traffic light control system that uses a high-precision imaging device, a generative AI model, and an emotion analysis engine. Specific embodiments will be described below from the perspectives of the server, terminal, and user.

[0872] Server Roles and Operations

[0873] The server plays a central role in the system and performs the following processes:

[0874] 1. Receiving image data

[0875] The server receives real-time video data from high-definition cameras installed at intersections, which transmit the video at 1080p resolution at 30 frames per second via RTSP (Real-Time Streaming Protocol).

[0876] 2. Image data preprocessing

[0877] The server uses image processing libraries such as OpenCV to remove noise, adjust resolution, and crop the target area from the received video data, maintaining data accuracy.

[0878] 3. Analysis of Traffic Conditions Using Generative AI Models

[0879] The server inputs the preprocessed video data into a generative AI model (such as YOLO) to analyze traffic volume, vehicle direction, and vehicle speed, thereby obtaining a detailed understanding of the current situation at the intersection.

[0880] 4. Analysis of user emotion data using emotion engine

[0881] The server analyzes voice and facial expression data acquired from the in-car microphone and dashboard camera to assess the user's emotional state, particularly their stress level.

[0882] 5. Signal switching instruction generation

[0883] The server calculates the timing of the next traffic light switch based on traffic conditions and user emotion data, generates specific instructions such as which direction the signal should be green for and for how long, and sends these to the traffic light control server.

[0884] Terminal roles and processing

[0885] The terminal (traffic light control device) performs the following processing.

[0886] 1. Receiving Instructions

[0887] The terminal receives signal switching instructions from the server via the REST API.

[0888] 2. Traffic light control

[0889] The device controls the traffic lights based on the received instructions, for example, setting the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[0890] 3. Feedback of results

[0891] The device checks whether the signal switching was performed correctly using its built-in sensors and camera, and reports the results to the server.

[0892] User roles and processes (for road users)

[0893] Users benefit from the system in the following ways:

[0894] 1. Check traffic light information

[0895] When a user approaches an intersection, they check the traffic light indications visually or through the in-car navigation system.

[0896] 2. Passing through an intersection

[0897] The user follows the optimized signal pattern and passes through the intersection smoothly.

[0898] 3. Reflecting emotions

[0899] By reflecting the user's emotions in the system, stress is reduced and a comfortable driving environment is provided.

[0900] Specific examples

[0901] Let's take the 5 PM rush hour as an example. If there is a significant increase in vehicles coming from the east at intersection B, the following process will be performed.

[0902] Server Processing

[0903] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[0904] Terminal handling

[0905] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[0906] User Action

[0907] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[0908] Prompt Sentence Examples

[0909] "Analyze traffic flow at intersection B during the 5 PM rush hour, and generate signal switching instructions to accommodate the increase in vehicles coming from the east. Also, include measures to be taken when users' stress levels are high."

[0910] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0911] Step 1:

[0912] The server receives video data in real time from high-precision cameras installed at intersections.

[0913] How it works: The high-definition camera captures video at 1080p resolution at 30 frames per second and sends the data to a server using RTSP (Real-Time Streaming Protocol).

[0914] Input: Video data from an intersection.

[0915] Output: Real-time video data stored on the server.

[0916] Step 2:

[0917] The server performs pre-processing on the received video data.

[0918] Specific operations: Use image processing libraries such as OpenCV to remove noise (e.g., apply a Gaussian filter), adjust resolution (e.g., convert from Full HD to HD), and crop the target area.

[0919] Input: Real-time video data.

[0920] Output: Preprocessed video data.

[0921] Step 3:

[0922] The server inputs the preprocessed video data into a generative AI model to analyze traffic conditions.

[0923] How it works: It uses object detection models such as YOLO to analyze traffic volume, vehicle direction, and vehicle speed. For example, the model recognizes eight vehicles in an image and calculates their direction and speed.

[0924] Input: Preprocessed video data.

[0925] Output: Analysis results: traffic volume, vehicle direction, and vehicle speed.

[0926] Step 4:

[0927] The server analyzes the user's emotion data using an emotion engine.

[0928] Specific operation: Analyzes voice data collected from an in-car microphone and facial expression data acquired from a dashboard camera to assess the user's stress level. For example, stress is determined based on voice tone analysis and changes in facial expressions.

[0929] Input: speech and facial expression data.

[0930] Output: User's emotional assessment results (especially stress level).

[0931] Step 5:

[0932] The server generates a signal switching instruction based on the analysis result.

[0933] Specific operation: The system calculates the next traffic light switching timing by combining traffic conditions and user emotion data. For example, if traffic volume is heavy and the user's stress level is high, it generates a setting that shortens the waiting time at the traffic light.

[0934] Input: Traffic situation analysis results and user sentiment evaluation results.

[0935] Output: Signal switching instructions (e.g., set eastbound signal green for 90 seconds, other directions red for 30 seconds).

[0936] Step 6:

[0937] The server transmits the generated signal switching instruction to the signal control server.

[0938] Specific operation: Sends signal switching instructions securely and reliably using communication protocols such as REST API.

[0939] Input: Signal switching instruction.

[0940] Output: Instruction sent to traffic light control server completed.

[0941] Step 7:

[0942] The terminal receives signal switching instructions from the server and controls the traffic lights.

[0943] Specific behavior: For example, set the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[0944] Input: Signal switching instruction from the server.

[0945] Output: The set traffic light state.

[0946] Step 8:

[0947] The terminal checks whether the signal switching was performed correctly and feeds the result back to the server.

[0948] What it does: It uses built-in sensors and cameras to monitor traffic light status and ensures that the switch is operating correctly.

[0949] Input: Traffic light status data.

[0950] Output: Signal switching feedback information.

[0951] (Application example 2)

[0952] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0953] Conventional traffic light control systems only considered traffic volume, vehicle direction, and speed when switching signals, which did not adequately reduce the stress of drivers and passengers. Furthermore, because signal control depended solely on traffic flow conditions, it was difficult to quickly alleviate traffic congestion, especially during rush hour or specific time periods. With the widespread adoption of autonomous vehicles, there is a demand for more precise signal control while also improving the comfort of passengers inside the vehicle.

[0954] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0955] In this invention, the server includes a means for installing high-precision cameras at intersections and monitoring traffic volume in real time, a means for analyzing the acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions, a means for collecting user emotion data using an emotion engine and reflecting it in signal control, a means for automatically controlling signal switching at traffic lights, and a means for detecting stress levels using an emotion engine installed in the vehicle and reflecting it in signal switching. This enables highly accurate analysis of traffic conditions at intersections and signal control that takes the user's emotional state into consideration. As a result, stress caused by waiting at traffic lights can be reduced and traffic flow can be maintained smoothly.

[0956] A "high-precision camera" is a camera that can capture traffic conditions in real time with high resolution and accuracy.

[0957] A "generative AI model" is an artificial intelligence model that analyzes acquired image data, extracts information such as traffic volume, vehicle direction and speed, and performs optimal signal control according to the system.

[0958] The "emotion engine" is an analysis engine that collects emotional data from the user's voice and facial expressions, and in particular detects stress levels.

[0959] A "traffic signal control server" is a server that generates instructions to control traffic lights installed at intersections and automatically switches between traffic lights.

[0960] The "in-vehicle emotion engine" is a system that is installed inside an autonomous vehicle to collect and analyze emotional data from passengers in real time.

[0961] "Signal switch instructions" are instructions that specify the timing and direction of traffic light switch based on data analyzed by the generative AI model and emotion engine.

[0962] "Traffic conditions" refers to detailed information such as traffic flow at intersections, vehicle direction, speed, and congestion status.

[0963] "User emotional data" is data relating to a user's emotional state, particularly stress level, that is collected using the emotion engine.

[0964] This invention is a system that analyzes traffic conditions and the emotional state of the user in real time to achieve optimal signal control so that autonomous vehicles can pass through intersections smoothly. Below, we will explain in detail the processing, hardware, and software from the perspectives of the server, terminal, and user.

[0965] Server Roles and Operations

[0966] The server is the center of the system and is responsible for analyzing traffic conditions, generating signal control instructions, processing user emotion data, etc. The server uses the following hardware and software:

[0967] High-precision cameras: Capture high-precision images of traffic conditions in real time.

[0968] Generative AI model: Analyzes acquired image data and generates detailed traffic data for signal control.

[0969] Emotion engine: Collects emotional data from the user's voice and facial expressions, particularly to detect stress levels.

[0970] Server system: Receives data, analyzes it, generates instructions, and sends them.

[0971] Specifically, the server first receives image data in real time from high-precision cameras installed at intersections. The image data is then analyzed using a generative AI model to extract information such as traffic volume, vehicle direction, and vehicle speed. Furthermore, the emotion engine receives user emotion data from an emotion engine installed inside the vehicle, identifying stress levels in particular. Based on this data, optimal signal switching instructions are generated and sent to the traffic light control server.

[0972] Terminal roles and processing

[0973] The terminal is responsible for directly controlling the traffic lights at the intersection. The terminal uses the following hardware and software:

[0974] Traffic light control system: Controls traffic lights based on instructions from the server.

[0975] Communication module: Receives signal switching instructions from the server and transmits them to the traffic light control system.

[0976] Specifically, the device receives traffic light switching instructions from the server in real time and controls the traffic lights based on those instructions. For example, it may receive an instruction such as "set the northbound traffic light to green for 90 seconds and the eastbound traffic light to red for 30 seconds." It then sends feedback to the server that the traffic light switching has been successfully completed.

[0977] User Roles and Actions

[0978] The user is responsible for operating the autonomous vehicle and generating emotion data. The following hardware and software are installed in the user's vehicle:

[0979] In-car camera and microphone: Devices for collecting the user's facial expressions and voice.

[0980] In-car emotion engine: Analyzes collected data and identifies the user's emotional state.

[0981] Specifically, the user drives the vehicle in a relaxed state. The in-vehicle camera and microphone collect the user's facial expressions and voice in real time, and the emotion engine analyzes the user's stress level. The analyzed data is sent to a server and used to generate traffic light control instructions.

[0982] Specific examples

[0983] For example, during the 5:00 PM rush hour, there is a significant increase in vehicles traveling east at Intersection B. The server analyzes camera images and confirms that there is an increase in vehicles traveling east. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to set the eastbound traffic light to green for 90 seconds and the north-southbound traffic light to red for 30 seconds, and sends these instructions to the traffic light control server. As a result, users traveling east toward Intersection B can pass through the intersection smoothly and without stress.

[0984] Prompt Sentence Examples

[0985] As an example of a specific prompt sentence for a generative AI model, enter the following:

[0986] "Provide an image of the intersection and analyze traffic volume, vehicle direction, and speed. Return the following data:

[0987] Total number of vehicles

[0988] Number of vehicles in each direction (north, south, east, west)

[0989] Average vehicle speed

[0990] Direction of traffic congestion (presence or absence)

[0991] In this way, traffic conditions at intersections can be analyzed with high accuracy and in real time, enabling optimal signal control that reflects the user's emotional state.

[0992] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0993] Step 1:

[0994] The server receives image data in real time from high-precision cameras installed at intersections.

[0995] Input: Live video from high-definition cameras at the intersection

[0996] Output: Real-time image data

[0997] The server uses this image data to prepare for the next step.

[0998] Step 2:

[0999] The server performs preprocessing on the received image data, specifically noise removal and resolution adjustment.

[1000] Input: Real-time image data

[1001] Output: Preprocessed image data

[1002] The server uses the OpenCV library to perform Gaussian blurring to remove noise and adjust the resolution of the data.

[1003] Step 3:

[1004] The server inputs the preprocessed image data into a generative AI model to analyze traffic conditions.

[1005] Input: Preprocessed image data

[1006] Output: Analysis data such as traffic volume, vehicle direction, and vehicle speed

[1007] The server uses a generative AI model to extract from the image data the total number of vehicles, the number of vehicles in each direction, the average vehicle speed, and the direction of traffic congestion.

[1008] Step 4:

[1009] The server collects the user's emotional data from an emotion engine installed in the vehicle, and detects the user's stress level in particular.

[1010] Input: Audio and image data from the in-car camera and microphone

[1011] Output: User's emotional data (e.g., stress level)

[1012] The emotion engine analyzes the user's voice and facial expressions, and in particular quantifies their stress level and sends it to the server.

[1013] Step 5:

[1014] The server generates optimal signal switching instructions based on traffic data and emotion data.

[1015] Input: Traffic data, emotion data

[1016] Output: Signal switching instruction

[1017] The server generates specific instructions, including the timing and direction of traffic light changes, based on data obtained from the generative AI model and emotion engine.

[1018] Step 6:

[1019] The server transmits the generated signal switching instruction to the signal control server.

[1020] Input: Signal switching instruction

[1021] Output: Send instructions to the signal control server

[1022] The instructions include specifics such as "set the northbound traffic light green for 90 seconds and the eastbound traffic light red for 30 seconds."

[1023] Step 7:

[1024] The terminal receives signal switching instructions from the server and controls the traffic lights based on the instructions.

[1025] Input: Signal switching instruction

[1026] Output: Traffic light operation (switching between green and red lights)

[1027] The device follows the instructions to change the status of the traffic lights and control traffic within the intersection.

[1028] Step 8:

[1029] The terminal will then provide feedback to the server that the signal switch has been successfully completed.

[1030] Input: Traffic light status data

[1031] Output: Signal switching completion confirmation data

[1032] The terminal checks the result of the signal switching and sends it as feedback to the server.

[1033] Step 9:

[1034] The user follows the optimized signal pattern and passes through the intersection smoothly.

[1035] Input: Traffic light display status

[1036] Output: Smooth passage through intersections

[1037] Users can check the status of traffic lights and pass through intersections with less stress.

[1038] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1039] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1040] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1041] [Third embodiment]

[1042] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1043] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1044] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1045] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1046] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1047] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1048] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1049] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1050] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1051] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1052] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1053] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1054] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, analyzes it with a generative AI model, and issues instructions to traffic lights to achieve optimal signal switching. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[1055] Server Roles and Operations

[1056] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[1057] 1. Receiving image data

[1058] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[1059] 2. Image data preprocessing

[1060] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[1061] 3. Analysis using generative AI models

[1062] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[1063] 4. Creating signal switching instructions

[1064] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[1065] 5. Sending instructions to traffic lights

[1066] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[1067] Terminal roles and processing

[1068] The terminal is responsible for directly controlling the traffic lights.

[1069] 1. Receiving Instructions

[1070] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[1071] 2. Traffic light control

[1072] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[1073] 3. Feedback of results

[1074] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[1075] User roles and processes (for road users)

[1076] Users benefit from a real-time optimized signaling system.

[1077] 1. Check traffic light information

[1078] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[1079] 2. Passing through an intersection

[1080] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[1081] 3. Avoiding traffic jams

[1082] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[1083] Specific examples

[1084] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[1085] Server Processing

[1086] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[1087] Terminal handling

[1088] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[1089] User Action

[1090] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[1091] The above is a specific embodiment of the present invention and the flow of the entire system.

[1092] The processing flow will be explained below.

[1093] Server Processing

[1094] Step 1:

[1095] The server receives image data in real time from cameras installed at intersections.

[1096] The server connects to the camera's data stream and continuously captures video data.

[1097] Step 2:

[1098] The server performs preprocessing on the received image data.

[1099] Noise removal and resolution adjustment are performed, and the target area is cropped as necessary.

[1100] Step 3:

[1101] The server inputs the preprocessed image data into the generative AI model.

[1102] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[1103] Step 4:

[1104] Based on the analysis results, the server creates signal switching instructions to perform signal optimization.

[1105] For example, if there are many vehicles heading north, the traffic light in that direction is set to stay green for a longer period of time.

[1106] Step 5:

[1107] The server transmits a signal switching instruction to the traffic light control server.

[1108] Send instructions including specific control timing for traffic lights.

[1109] Terminal handling

[1110] Step 1:

[1111] The terminal receives a signal switching instruction from the server.

[1112] The received information includes the timing and direction of signal switching.

[1113] Step 2:

[1114] The terminal controls the traffic lights based on the instructions received.

[1115] For example, set the northbound traffic light to green and the eastbound traffic light to red.

[1116] Step 3:

[1117] The terminal checks the execution status of the signal switching and sends feedback to the server.

[1118] The feedback includes the successful completion of the signal switch.

[1119] User processing (for road users)

[1120] Step 1:

[1121] When a user approaches an intersection, the user visually checks the traffic light display.

[1122] Check the traffic light indications to prepare to pass through the intersection smoothly.

[1123] Step 2:

[1124] The user passes through the intersection following the traffic lights.

[1125] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[1126] Step 3:

[1127] To enable a user to smoothly pass through an intersection and avoid congestion.

[1128] Traffic flows more smoothly and you can reach your destination faster.

[1129] Example 1

[1130] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1131] Current traffic signal systems operate based on fixed patterns, and one issue is that they are unable to flexibly control traffic in response to real-time traffic conditions. This results in frequent traffic congestion and delays, making efficient traffic management difficult. Furthermore, there is a lack of means to accumulate and analyze the data necessary for signal control, making it impossible to achieve optimal signal control based on fluctuations and predictions of traffic volume. Furthermore, this increases the risk of traffic accidents and causes frequent inconvenience to drivers and pedestrians.

[1132] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1133] In this invention, the server includes means for receiving image data in real time from high-precision cameras installed at intersections, means for preprocessing the received image data to remove noise and adjust resolution, means for inputting the preprocessed image data into a generative AI model and analyzing traffic volume, vehicle direction, and vehicle speed, means for calculating the next signal switch timing based on the analysis results and generating specific control instructions for the traffic lights, means for transmitting the generated signal switch instructions to a traffic light control system, means for automatically controlling the signal switch of the traffic lights by the traffic light control system, and means for confirming whether the traffic light switch was performed normally and feeding back the result. This enables flexible and optimal signal control that responds to real-time traffic conditions.

[1134] A "high-precision camera" is a device that can capture the entire intersection in high resolution and provide accurate image data in real time.

[1135] "Real-time" refers to a processing method that can instantly grasp the current traffic situation and reflect it immediately.

[1136] "Traffic volume" is the number of vehicles and pedestrians passing through a particular road within a certain period of time.

[1137] "Monitoring" refers to the act of continuously observing traffic conditions at an intersection and acquiring necessary data.

[1138] "Image data" refers to visual information captured by a camera that is represented in digital form.

[1139] "Preprocessing" is a process in which acquired image data is processed, such as by removing noise and adjusting resolution, to improve the accuracy of analysis.

[1140] A "generative AI model" is an artificial intelligence program that is trained to analyze traffic situations using machine learning algorithms.

[1141] "Analysis" is the process of evaluating the acquired data in detail and extracting specific information such as traffic volume, vehicle direction, and vehicle speed.

[1142] The "signal switching instruction" is data generated as a specific operation instruction by determining the state of the next signal based on the analysis result.

[1143] "Traffic light control system" is a general term for hardware and software that receives instructions from a server and directly operates traffic lights.

[1144] "Feedback" is the process of checking the results after switching signals and reporting them to the server.

[1145] "Optimization" refers to adjusting traffic signals to control them most efficiently according to traffic volume and time of day.

[1146] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, and generates optimal switching instructions for traffic lights by analyzing the data using a generative AI model, thereby controlling traffic signals flexibly and efficiently. Below, we will explain how to specifically implement this system.

[1147] Hardware and Software Configuration

[1148] server

[1149] The server is the core of this system and uses the following hardware and software in combination:

[1150] Hardware: High-performance processor (e.g., Intel Xeon processor), large memory capacity (e.g., 32GB RAM), SSD storage (e.g., 1TB SSD)

[1151] Software: Ubuntu OS, image processing libraries (e.g., OpenCV), machine learning frameworks (e.g., TensorFlow, YOLOv5)

[1152] Terminal (traffic signal control device)

[1153] The terminal receives instructions from the server and directly controls the traffic lights. The following hardware and software are used:

[1154] Hardware: Microcontroller (e.g. Raspberry Pi), GPIO pins, relay control board

[1155] Software: Raspbian OS, HTTP communication library, GPIO control library

[1156] User

[1157] The user is a road user who checks traffic light information and benefits from an optimized traffic light system.

[1158] Data processing and calculation procedures

[1159] The server receives image data in real time from a high-precision camera (e.g., Sony Alpha series). The camera captures a panoramic view of the intersection and sends the data to the server at a rate of 30 frames per second. The server then performs noise removal and resolution adjustment on the received image data, thereby maintaining data precision and improving the accuracy of analysis. This processing is performed using the OpenCV image processing library.

[1160] The preprocessed image data is input into a generative AI model (e.g., YOLOv5). The AI ​​model is built using the Python framework TensorFlow and analyzes traffic volume, vehicle direction, and vehicle speed from the image. Based on the results of this analysis, the server calculates the next traffic light switching timing and generates specific control instructions. These instructions include the number of seconds to keep the traffic light green for each direction.

[1161] The generated signal switching instructions are sent from the server to the traffic light control system. This communication uses the HTTP protocol, and the instructions are sent in JSON format. The traffic light control system automatically controls the traffic lights based on the instructions received from the server. Specifically, it switches the LED display of the traffic lights using GPIO pins.

[1162] The system checks whether the traffic light control was successful and sends the result back to the server. This is done again using HTTP communication, and the result is sent to the server in JSON format. This feedback allows the server to obtain new data to generate the next instruction.

[1163] Examples of specific examples and prompts

[1164] During the 8:00 a.m. rush hour, when there are many vehicles coming from the north at intersection A, the system operates as follows:

[1165] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[1166] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[1167] The user enters intersection A from the north and can pass through the intersection smoothly because the traffic light is green for a long time, which reduces congestion and shortens commuting time.

[1168] Example prompt sentence:

[1169] Image data is input into the generative AI model, which analyzes traffic volume, vehicle direction, and speed.

[1170] Based on the analysis results, the next signal switching timing is calculated and traffic light control instructions are generated.

[1171] It sends instructions to the traffic light control system to control the traffic lights.

[1172] The above is an embodiment of the invention.

[1173] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1174] Step 1:

[1175] The server receives image data in real time from high-definition cameras installed at intersections. As input, it receives image data from the cameras in JPEG or H.264 format. The output is raw image data stored in the server's memory. Specifically, the server receives data from the cameras at a rate of 30 frames per second and prepares it for the next processing step.

[1176] Step 2:

[1177] The server performs preprocessing on the received image data. The input is the raw image data received in step 1. The data is processed using the image processing library OpenCV to remove noise (Gaussian filter) and adjust the resolution. The output is clean image data after preprocessing. Specifically, the server performs the following operations:

[1178] Apply a Gaussian filter to remove noise

[1179] Resize the image resolution to 640x480

[1180] Step 3:

[1181] The server inputs the preprocessed image data into the generative AI model for analysis. The input is the clean image data preprocessed in step 2. The generative AI model (e.g., YOLOv5, TensorFlow) analyzes traffic volume, vehicle direction, and vehicle speed from the input image data. The output is analysis result data (JSON format) showing traffic conditions. Specifically, the server performs the following operations:

[1182] Initialize the generative AI model

[1183] Input image data into the model and generate analysis results

[1184] Step 4:

[1185] The server generates signal switching instructions based on the analysis results. The input is the analysis result data obtained in step 3. For data processing, the server analyzes the analysis results and calculates the next signal switching timing and the signal status for each direction. The output is specific signal switching instructions (JSON format). Specifically, the server performs the following operations:

[1186] Analyze the analysis results and understand the traffic situation

[1187] Calculates the timing of traffic lights switching for each direction and generates specific instructions

[1188] Step 5:

[1189] The server sends the generated signal change instruction to the traffic light control system. The input is the signal change instruction (JSON format) generated in step 4. The output is the acknowledgment (HTTP response) received by the traffic light control system. Specifically, the server performs the following operations:

[1190] Send a signal switching command using the HTTP POST method

[1191] Obtaining acknowledgement from the traffic light control system

[1192] Step 6:

[1193] The terminal receives a signal switching instruction sent from the server. The input is the signal switching instruction (JSON format) from the server. The output is the signal switching instruction data stored on the terminal. In concrete terms, the terminal receives the instruction from the server via HTTP communication and prepares for the next processing step.

[1194] Step 7:

[1195] The terminal controls the traffic light based on the received signal switching instruction. The input is the signal switching instruction data received in step 6. The output is the change in the LED display of the traffic light. Specifically, the terminal performs the following operations:

[1196] Controlling traffic light LEDs using GPIO pins

[1197] Turning the traffic light green in one direction and red in another

[1198] Step 8:

[1199] The device checks whether the traffic light switch was successful and feeds the result back to the server. The input is the current state of the traffic light. The output is feedback data (in JSON format) to the server. Specifically, the device performs the following operations:

[1200] Check the traffic light status

[1201] Generate feedback data and send it to the server using the HTTP POST method

[1202] Step 9:

[1203] When approaching an intersection, the user checks the traffic light information. The input is the current road condition and the traffic light status. The output is information that allows the user to pass through the intersection safely. Specifically, the user checks the traffic light status using the navigation system or visually and performs driving operations.

[1204] Step 10:

[1205] The user passes through the intersection according to the optimized signal pattern. The input is the status of the traffic lights and the current road conditions. The output is the reduction of congestion and safe driving. As a specific action, the user passes through the intersection while the signal is green and can drive safely.

[1206] Step 11:

[1207] The user reaches their destination quickly as a result of smooth traffic flow and avoidance of congestion. The input is smooth traffic flow due to optimal control of traffic lights. The output is a state in which the user can reach their destination quickly and safely. In concrete terms, the user can reach their destination without stress.

[1208] (Application example 1)

[1209] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1210] In modern traffic systems, traffic signals at intersections are controlled in a fixed manner and are unable to respond to fluctuations in traffic volume, resulting in frequent traffic congestion. Furthermore, with the spread of autonomous vehicles, real-time traffic signal information is required, but current systems lack the mechanisms to accommodate this. Therefore, it is necessary to optimize traffic signal switching and provide traffic signal information to autonomous vehicles.

[1211] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1212] In this invention, the server includes means for installing high-precision cameras at intersections and monitoring traffic volume in real time, means for analyzing the acquired image data with a generative AI model and instructing optimal signal switching according to traffic conditions, means for automatically controlling signal switching at traffic lights, and means for providing real-time signal information to the navigation system of autonomous vehicles. This optimizes signal switching according to traffic volume, alleviating traffic congestion and enabling autonomous vehicles to pass through intersections efficiently.

[1213] A "high-precision camera" is a camera device that can capture the entire intersection in real time with high resolution, capturing detailed traffic conditions.

[1214] "Means for monitoring traffic volume in real time" refers to technology that uses high-precision cameras to instantly monitor current traffic volume and vehicle movements and acquire that data.

[1215] "Means of analyzing acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions" refers to a technology in which image data acquired from a camera is input into a generative AI model for analysis, and based on the results, optimal switching instructions are given to traffic lights.

[1216] "Means for automatically controlling signal switching for traffic lights" refers to technology that automatically adjusts the color and timing of traffic lights based on the analysis results of a generative AI model.

[1217] "Means for providing real-time traffic light information to the navigation system of an autonomous vehicle" refers to technology that provides real-time information such as the current status of traffic lights and the timing of the next change of traffic lights to the navigation system of an autonomous vehicle.

[1218] "Means to optimize signal control in response to time-of-day and daily fluctuations" refers to technology that takes into account daily and time-of-day fluctuations in traffic volume and performs optimal signal switching.

[1219] "Means that take into account traffic volume in each direction, vehicle direction of travel, and vehicle speed" refers to technology that analyzes in detail the traffic volume and vehicle movement from each direction at a specific intersection and controls traffic signals based on that information.

[1220] In this invention, a high-precision camera, a generative AI model, a traffic light control server, and a navigation system for autonomous vehicles are combined to realize a traffic light control system that utilizes real-time monitoring of traffic volume and a generative AI model. Specific embodiments of the system are described below from the perspectives of the server, terminal, and user.

[1221] Server Roles and Operations

[1222] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[1223] 1. Receiving image data

[1224] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[1225] 2. Image data preprocessing

[1226] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[1227] 3. Analysis using generative AI models

[1228] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[1229] 4. Creating signal switching instructions

[1230] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[1231] 5. Sending instructions to traffic lights

[1232] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[1233] 6. Providing information to autonomous vehicles

[1234] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the timing of the next traffic light change and the current traffic light status.

[1235] Terminal roles and processing

[1236] The terminal is responsible for directly controlling the traffic lights.

[1237] 1. Receiving Instructions

[1238] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[1239] 2. Traffic light control

[1240] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[1241] 3. Feedback of results

[1242] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[1243] User roles and processes (for road users)

[1244] Users benefit from a real-time optimized signaling system.

[1245] 1. Check traffic light information

[1246] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[1247] 2. Passing through an intersection

[1248] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[1249] 3. Avoiding traffic jams

[1250] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[1251] Specific examples

[1252] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[1253] Server Processing

[1254] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[1255] Terminal handling

[1256] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[1257] User Action

[1258] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[1259] Prompt Sentence Examples

[1260] "A high-precision camera system that uses generative AI models to analyze intersection traffic volume in real time and optimize traffic light switching. We want to create an application that provides real-time traffic light switching information to autonomous vehicles and navigation systems."

[1261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1262] Step 1:

[1263] Receiving image data

[1264] The server receives image data in real time from a high-definition camera. The camera constantly captures the entire intersection and sends the data to the server via the Internet. The input is image data from the high-definition camera, and the output is image data stored on the server.

[1265] Step 2:

[1266] Image data preprocessing

[1267] The server performs noise reduction and resolution adjustment on the received image data. For this, it uses an image processing library (e.g., OpenCV). Preprocessing removes unnecessary noise in the image and optimizes the resolution for analysis. The input is image data from a high-precision camera, and the output is preprocessed image data.

[1268] Step 3:

[1269] Analysis using generative AI models

[1270] The server inputs the preprocessed image data into a generative AI model (e.g., TensorFlow or PyTorch) to analyze traffic conditions such as traffic volume, vehicle direction, and vehicle speed. The generative AI model analyzes the acquired data and quantifies and evaluates the traffic conditions. The input is the preprocessed image data, and the output is the analysis results of the traffic conditions.

[1271] Step 4:

[1272] Creating signal switching instructions

[1273] The server calculates the next signal switching timing based on the analysis results. Specifically, it generates instructions such as which direction the signal should be green for and for how long. The signal switching timing is determined based on the evaluation results of the generative AI model. The input is the analysis result of the traffic situation, and the output is the signal switching instruction.

[1274] Step 5:

[1275] Sending instructions to traffic lights

[1276] The server sends the created signal switching instruction to the traffic light control server. This gives specific control instructions to the traffic lights. The input is the signal switching instruction, and the output is the control instruction sent to the traffic light control server.

[1277] Step 6:

[1278] Providing information to autonomous vehicles

[1279] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the next traffic light switch timing and the current traffic light status. The input is a traffic light switch instruction, and the output is real-time traffic light information provided to the autonomous vehicle's navigation system.

[1280] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1281] This invention optimizes traffic signal control at intersections and smooths traffic flow through a system that combines a high-precision camera, a generative AI model, and an emotion engine that recognizes user emotions. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[1282] Server Roles and Operations

[1283] The server is the center of the system, responsible for analyzing traffic conditions, generating signal control instructions, and processing user emotion data.

[1284] 1. Receiving image data

[1285] The server receives real-time image data from high-precision cameras installed at intersections, which monitor the entire intersection and continuously transmit video data to the server.

[1286] 2. Image data preprocessing

[1287] The server removes noise from the received image data, adjusts the resolution, and also crops the target area to maintain data accuracy.

[1288] 3. Analysis of Traffic Conditions Using Generative AI Models

[1289] The pre-processed image data is input into a generative AI model to analyze traffic volume, vehicle direction, vehicle speed, etc. This allows for a detailed assessment of the current state of the intersection.

[1290] 4. Analysis of user emotion data using emotion engine

[1291] The server collects emotional data from the user's voice and facial expressions through an emotion engine, and detects stress levels in particular. For example, it analyzes the driver's facial expressions and the voices inside the car to determine the current emotional state.

[1292] 5. Signal switching instruction generation

[1293] Based on traffic conditions and user emotion data, the server calculates the next traffic light change timing. For example, if the user's stress level is high, the server selects a setting that switches the traffic light more smoothly.

[1294] 6. Sending instructions to traffic lights

[1295] The created signal switching instruction is sent to the traffic light control server. The instruction contains specific information such as which direction the signal should be green for and for how long.

[1296] Terminal roles and processing

[1297] The terminal is responsible for directly controlling the traffic lights at the intersection.

[1298] 1. Receiving Instructions

[1299] The terminal receives traffic light switching instructions from the server, which include the specific timing and direction of the traffic light switching.

[1300] 2. Traffic light control

[1301] Based on the received instructions, the device controls the traffic lights, for example, setting the northbound traffic light to green and the eastbound traffic light to red.

[1302] 3. Feedback of results

[1303] It checks whether the signal switching was successful and reports the result to the server. The feedback information is used to instruct the next signal switching.

[1304] User roles and processes (for road users)

[1305] Users benefit from real-time optimized signal control.

[1306] 1. Check traffic light information

[1307] As a user approaches an intersection, they check the traffic light indications visually or through their in-car navigation system.

[1308] 2. Passing through an intersection

[1309] Users can smoothly navigate through intersections by following optimized traffic light patterns. For example, the northbound traffic light will stay green longer, allowing vehicles coming from the north to proceed smoothly.

[1310] 3. Reflecting emotions

[1311] Traffic light control that reflects the user's emotions reduces stress and provides a comfortable driving environment. For example, if the emotion engine detects high stress levels in the user, it will quickly switch traffic lights to alleviate traffic congestion, which causes stress.

[1312] Specific examples

[1313] Let's take the 5:00 PM rush hour as an example. At intersection B, there is a significant increase in vehicles coming from the east.

[1314] Server Processing

[1315] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[1316] Terminal handling

[1317] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[1318] User Action

[1319] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[1320] The above is a specific embodiment of the present invention and the flow of the entire system.

[1321] The processing flow will be explained below.

[1322] Server Processing

[1323] Step 1:

[1324] The server receives image data in real time from high-precision cameras installed at intersections.

[1325] The server connects to the camera's data stream and continuously captures the video data.

[1326] Step 2:

[1327] The server preprocesses the received image data.

[1328] Remove noise, adjust resolution, and crop specific areas of intersections to improve data accuracy.

[1329] Step 3:

[1330] The server inputs the preprocessed image data into the generative AI model.

[1331] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[1332] Step 4:

[1333] The server uses an emotion engine to collect the user's voice and facial expression data and analyze the user's emotions.

[1334] In particular, it analyzes the user's facial expressions and the voices inside the car to detect stress levels.

[1335] Step 5:

[1336] The server generates optimal signal switching instructions based on traffic conditions and emotion data.

[1337] For example, if the user's stress level is high, the signal may be set to switch quickly.

[1338] Step 6:

[1339] The server transmits the generated signal switching instruction to the signal control server.

[1340] Send instructions that include the specific timing and direction of switching signals.

[1341] Terminal handling

[1342] Step 1:

[1343] The terminal receives a signal switching instruction from the server.

[1344] The received information includes the specific timing and direction of traffic light changes.

[1345] Step 2:

[1346] The terminal controls the traffic lights based on the instructions received.

[1347] For example, the northbound traffic light will turn green and the eastbound traffic light will turn red.

[1348] Step 3:

[1349] The terminal checks the execution status of the signal switching and sends feedback to the server.

[1350] The feedback includes successful completion of the signal switch.

[1351] User processing (for road users)

[1352] Step 1:

[1353] When a user approaches an intersection, the user checks the traffic light display visually or through the in-car navigation system.

[1354] Check the traffic light status, which is updated in real time, and prepare to pass through the intersection.

[1355] Step 2:

[1356] The user follows the traffic lights and passes through the intersection.

[1357] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[1358] Step 3:

[1359] Traffic light control that reflects the user's emotions reduces stress.

[1360] If the emotion engine detects high stress in the user, the traffic lights will switch quickly to ease traffic congestion, thereby reducing the user's stress.

[1361] Example 2

[1362] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1363] Conventional traffic signal control systems are often limited to monitoring traffic volume and controlling signal switching, and are unable to consider real-time changes in traffic conditions or the emotional state of users. This has resulted in problems such as congestion and a lack of reduction in user stress. The present invention aims to solve these problems and optimize traffic flow while also reducing user stress.

[1364] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1365] In this invention, the server includes a means for installing high-precision camera devices at road intersections and monitoring traffic volume in real time, a means for analyzing acquired video data using a generative AI model and optimizing traffic light switching based on traffic conditions and vehicle speed and direction, a means for adjusting traffic light switching based on an emotion analysis engine for grasping the emotional state of users, and a means for automatically controlling traffic lights to switch signals, thereby enabling real-time response to changes in traffic conditions and reducing user stress.

[1366] A "high-precision imaging device" is a device that captures high-resolution images of specific areas, such as intersections, in real time.

[1367] "Real-time" means that data is collected and processed in accordance with the current moment.

[1368] "Traffic volume" refers to the number of vehicles passing through a particular road or intersection.

[1369] A "generative AI model" refers to a model that uses machine learning algorithms to analyze data and make predictions.

[1370] "Traffic conditions" refers to the state of traffic flow and congestion at the current time.

[1371] "Vehicle speed" is a measurement of how fast a particular vehicle is traveling.

[1372] "Heading" refers to the direction in which a vehicle is moving.

[1373] "Switching lights" means that the color of a traffic light is changed.

[1374] An "emotion analysis engine" is a system that analyzes and evaluates a user's emotional state from data such as audio and video.

[1375] "Automatically" means that the system completes the action by itself without human intervention.

[1376] A "traffic light" is a device installed on a road to direct traffic.

[1377] "Users" refers to drivers and pedestrians who use the system.

[1378] "Stress" refers to a state of psychological and physiological tension caused by external stimuli or stress.

[1379] The present invention is a traffic light control system that uses a high-precision imaging device, a generative AI model, and an emotion analysis engine. Specific embodiments will be described below from the perspectives of the server, terminal, and user.

[1380] Server Roles and Operations

[1381] The server plays a central role in the system and performs the following processes:

[1382] 1. Receiving image data

[1383] The server receives real-time video data from high-definition cameras installed at intersections, which transmit the video at 1080p resolution at 30 frames per second via RTSP (Real-Time Streaming Protocol).

[1384] 2. Image data preprocessing

[1385] The server uses image processing libraries such as OpenCV to remove noise, adjust resolution, and crop the target area from the received video data, maintaining data accuracy.

[1386] 3. Analysis of Traffic Conditions Using Generative AI Models

[1387] The server inputs the preprocessed video data into a generative AI model (such as YOLO) to analyze traffic volume, vehicle direction, and vehicle speed, thereby obtaining a detailed understanding of the current situation at the intersection.

[1388] 4. Analysis of user emotion data using emotion engine

[1389] The server analyzes voice and facial expression data acquired from the in-car microphone and dashboard camera to assess the user's emotional state, particularly their stress level.

[1390] 5. Signal switching instruction generation

[1391] The server calculates the timing of the next traffic light switch based on traffic conditions and user emotion data, generates specific instructions such as which direction the signal should be green for and for how long, and sends these to the traffic light control server.

[1392] Terminal roles and processing

[1393] The terminal (traffic light control device) performs the following processing.

[1394] 1. Receiving Instructions

[1395] The terminal receives signal switching instructions from the server via the REST API.

[1396] 2. Traffic light control

[1397] The device controls the traffic lights based on the received instructions, for example, setting the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[1398] 3. Feedback of results

[1399] The device checks whether the signal switching was performed correctly using its built-in sensors and camera, and reports the results to the server.

[1400] User roles and processes (for road users)

[1401] Users benefit from the system in the following ways:

[1402] 1. Check traffic light information

[1403] When a user approaches an intersection, they check the traffic light indications visually or through the in-car navigation system.

[1404] 2. Passing through an intersection

[1405] The user follows the optimized signal pattern and passes through the intersection smoothly.

[1406] 3. Reflecting emotions

[1407] By reflecting the user's emotions in the system, stress is reduced and a comfortable driving environment is provided.

[1408] Specific examples

[1409] Let's take the 5 PM rush hour as an example. If there is a significant increase in vehicles coming from the east at intersection B, the following process will be performed.

[1410] Server Processing

[1411] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[1412] Terminal handling

[1413] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[1414] User Action

[1415] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[1416] Prompt Sentence Examples

[1417] "Analyze traffic flow at intersection B during the 5 PM rush hour, and generate signal switching instructions to accommodate the increase in vehicles coming from the east. Also, include measures to be taken when users' stress levels are high."

[1418] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1419] Step 1:

[1420] The server receives video data in real time from high-precision cameras installed at intersections.

[1421] How it works: The high-definition camera captures video at 1080p resolution at 30 frames per second and sends the data to a server using RTSP (Real-Time Streaming Protocol).

[1422] Input: Video data from an intersection.

[1423] Output: Real-time video data stored on the server.

[1424] Step 2:

[1425] The server performs pre-processing on the received video data.

[1426] Specific operations: Use image processing libraries such as OpenCV to remove noise (e.g., apply a Gaussian filter), adjust resolution (e.g., convert from Full HD to HD), and crop the target area.

[1427] Input: Real-time video data.

[1428] Output: Preprocessed video data.

[1429] Step 3:

[1430] The server inputs the preprocessed video data into a generative AI model to analyze traffic conditions.

[1431] How it works: It uses object detection models such as YOLO to analyze traffic volume, vehicle direction, and vehicle speed. For example, the model recognizes eight vehicles in an image and calculates their direction and speed.

[1432] Input: Preprocessed video data.

[1433] Output: Analysis results: traffic volume, vehicle direction, and vehicle speed.

[1434] Step 4:

[1435] The server analyzes the user's emotion data using an emotion engine.

[1436] Specific operation: Analyzes voice data collected from an in-car microphone and facial expression data acquired from a dashboard camera to assess the user's stress level. For example, stress is determined based on voice tone analysis and changes in facial expressions.

[1437] Input: speech and facial expression data.

[1438] Output: User's emotional assessment results (especially stress level).

[1439] Step 5:

[1440] The server generates a signal switching instruction based on the analysis result.

[1441] Specific operation: The system calculates the next traffic light switching timing by combining traffic conditions and user emotion data. For example, if traffic volume is heavy and the user's stress level is high, it generates a setting that shortens the waiting time at the traffic light.

[1442] Input: Traffic situation analysis results and user sentiment evaluation results.

[1443] Output: Signal switching instructions (e.g., set eastbound signal green for 90 seconds, other directions red for 30 seconds).

[1444] Step 6:

[1445] The server transmits the generated signal switching instruction to the signal control server.

[1446] Specific operation: Sends signal switching instructions securely and reliably using communication protocols such as REST API.

[1447] Input: Signal switching instruction.

[1448] Output: Instruction sent to traffic light control server completed.

[1449] Step 7:

[1450] The terminal receives signal switching instructions from the server and controls the traffic lights.

[1451] Specific behavior: For example, set the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[1452] Input: Signal switching instruction from the server.

[1453] Output: The set traffic light state.

[1454] Step 8:

[1455] The terminal checks whether the signal switching was performed correctly and feeds the result back to the server.

[1456] What it does: It uses built-in sensors and cameras to monitor traffic light status and ensures that the switch is operating correctly.

[1457] Input: Traffic light status data.

[1458] Output: Signal switching feedback information.

[1459] (Application example 2)

[1460] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1461] Conventional traffic light control systems only considered traffic volume, vehicle direction, and speed when switching signals, which did not adequately reduce the stress of drivers and passengers. Furthermore, because signal control depended solely on traffic flow conditions, it was difficult to quickly alleviate traffic congestion, especially during rush hour or specific time periods. With the widespread adoption of autonomous vehicles, there is a demand for more precise signal control while also improving the comfort of passengers inside the vehicle.

[1462] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1463] In this invention, the server includes a means for installing high-precision cameras at intersections and monitoring traffic volume in real time, a means for analyzing the acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions, a means for collecting user emotion data using an emotion engine and reflecting it in signal control, a means for automatically controlling signal switching at traffic lights, and a means for detecting stress levels using an emotion engine installed in the vehicle and reflecting it in signal switching. This enables highly accurate analysis of traffic conditions at intersections and signal control that takes the user's emotional state into consideration. As a result, stress caused by waiting at traffic lights can be reduced and traffic flow can be maintained smoothly.

[1464] A "high-precision camera" is a camera that can capture traffic conditions in real time with high resolution and accuracy.

[1465] A "generative AI model" is an artificial intelligence model that analyzes acquired image data, extracts information such as traffic volume, vehicle direction and speed, and performs optimal signal control according to the system.

[1466] The "emotion engine" is an analysis engine that collects emotional data from the user's voice and facial expressions, and in particular detects stress levels.

[1467] A "traffic signal control server" is a server that generates instructions to control traffic lights installed at intersections and automatically switches between traffic lights.

[1468] The "in-vehicle emotion engine" is a system that is installed inside an autonomous vehicle to collect and analyze emotional data from passengers in real time.

[1469] "Signal switch instructions" are instructions that specify the timing and direction of traffic light switch based on data analyzed by the generative AI model and emotion engine.

[1470] "Traffic conditions" refers to detailed information such as traffic flow at intersections, vehicle direction, speed, and congestion status.

[1471] "User emotional data" is data relating to a user's emotional state, particularly stress level, that is collected using the emotion engine.

[1472] This invention is a system that analyzes traffic conditions and the emotional state of the user in real time to achieve optimal signal control so that autonomous vehicles can pass through intersections smoothly. Below, we will explain in detail the processing, hardware, and software from the perspectives of the server, terminal, and user.

[1473] Server Roles and Operations

[1474] The server is the center of the system and is responsible for analyzing traffic conditions, generating signal control instructions, processing user emotion data, etc. The server uses the following hardware and software:

[1475] High-precision cameras: Capture high-precision images of traffic conditions in real time.

[1476] Generative AI model: Analyzes acquired image data and generates detailed traffic data for signal control.

[1477] Emotion engine: Collects emotional data from the user's voice and facial expressions, particularly to detect stress levels.

[1478] Server system: Receives data, analyzes it, generates instructions, and sends them.

[1479] Specifically, the server first receives image data in real time from high-precision cameras installed at intersections. The image data is then analyzed using a generative AI model to extract information such as traffic volume, vehicle direction, and vehicle speed. Furthermore, the emotion engine receives user emotion data from an emotion engine installed inside the vehicle, identifying stress levels in particular. Based on this data, optimal signal switching instructions are generated and sent to the traffic light control server.

[1480] Terminal roles and processing

[1481] The terminal is responsible for directly controlling the traffic lights at the intersection. The terminal uses the following hardware and software:

[1482] Traffic light control system: Controls traffic lights based on instructions from the server.

[1483] Communication module: Receives signal switching instructions from the server and transmits them to the traffic light control system.

[1484] Specifically, the device receives traffic light switching instructions from the server in real time and controls the traffic lights based on those instructions. For example, it may receive an instruction such as "set the northbound traffic light to green for 90 seconds and the eastbound traffic light to red for 30 seconds." It then sends feedback to the server that the traffic light switching has been successfully completed.

[1485] User Roles and Actions

[1486] The user is responsible for operating the autonomous vehicle and generating emotion data. The following hardware and software are installed in the user's vehicle:

[1487] In-car camera and microphone: Devices for collecting the user's facial expressions and voice.

[1488] In-car emotion engine: Analyzes collected data and identifies the user's emotional state.

[1489] Specifically, the user drives the vehicle in a relaxed state. The in-vehicle camera and microphone collect the user's facial expressions and voice in real time, and the emotion engine analyzes the user's stress level. The analyzed data is sent to a server and used to generate traffic light control instructions.

[1490] Specific examples

[1491] For example, during the 5:00 PM rush hour, there is a significant increase in vehicles traveling east at Intersection B. The server analyzes camera images and confirms that there is an increase in vehicles traveling east. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to set the eastbound traffic light to green for 90 seconds and the north-southbound traffic light to red for 30 seconds, and sends these instructions to the traffic light control server. As a result, users traveling east toward Intersection B can pass through the intersection smoothly and without stress.

[1492] Prompt Sentence Examples

[1493] As an example of a specific prompt sentence for a generative AI model, enter the following:

[1494] "Provide an image of the intersection and analyze traffic volume, vehicle direction, and speed. Return the following data:

[1495] Total number of vehicles

[1496] Number of vehicles in each direction (north, south, east, west)

[1497] Average vehicle speed

[1498] Direction of traffic congestion (presence or absence)

[1499] In this way, traffic conditions at intersections can be analyzed with high accuracy and in real time, enabling optimal signal control that reflects the user's emotional state.

[1500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1501] Step 1:

[1502] The server receives image data in real time from high-precision cameras installed at intersections.

[1503] Input: Live video from high-definition cameras at the intersection

[1504] Output: Real-time image data

[1505] The server uses this image data to prepare for the next step.

[1506] Step 2:

[1507] The server performs preprocessing on the received image data, specifically noise removal and resolution adjustment.

[1508] Input: Real-time image data

[1509] Output: Preprocessed image data

[1510] The server uses the OpenCV library to perform Gaussian blurring to remove noise and adjust the resolution of the data.

[1511] Step 3:

[1512] The server inputs the preprocessed image data into a generative AI model to analyze traffic conditions.

[1513] Input: Preprocessed image data

[1514] Output: Analysis data such as traffic volume, vehicle direction, and vehicle speed

[1515] The server uses a generative AI model to extract from the image data the total number of vehicles, the number of vehicles in each direction, the average vehicle speed, and the direction of traffic congestion.

[1516] Step 4:

[1517] The server collects the user's emotional data from an emotion engine installed in the vehicle, and detects the user's stress level in particular.

[1518] Input: Audio and image data from the in-car camera and microphone

[1519] Output: User's emotional data (e.g., stress level)

[1520] The emotion engine analyzes the user's voice and facial expressions, and in particular quantifies their stress level and sends it to the server.

[1521] Step 5:

[1522] The server generates optimal signal switching instructions based on traffic data and emotion data.

[1523] Input: Traffic data, emotion data

[1524] Output: Signal switching instruction

[1525] The server generates specific instructions, including the timing and direction of traffic light changes, based on data obtained from the generative AI model and emotion engine.

[1526] Step 6:

[1527] The server transmits the generated signal switching instruction to the signal control server.

[1528] Input: Signal switching instruction

[1529] Output: Send instructions to the signal control server

[1530] The instructions include specifics such as "set the northbound traffic light green for 90 seconds and the eastbound traffic light red for 30 seconds."

[1531] Step 7:

[1532] The terminal receives signal switching instructions from the server and controls the traffic lights based on the instructions.

[1533] Input: Signal switching instruction

[1534] Output: Traffic light operation (switching between green and red lights)

[1535] The device follows the instructions to change the status of the traffic lights and control traffic within the intersection.

[1536] Step 8:

[1537] The terminal will then provide feedback to the server that the signal switch has been successfully completed.

[1538] Input: Traffic light status data

[1539] Output: Signal switching completion confirmation data

[1540] The terminal checks the result of the signal switching and sends it as feedback to the server.

[1541] Step 9:

[1542] The user follows the optimized signal pattern and passes through the intersection smoothly.

[1543] Input: Traffic light display status

[1544] Output: Smooth passage through intersections

[1545] Users can check the status of traffic lights and pass through intersections with less stress.

[1546] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1547] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1548] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1549] [Fourth embodiment]

[1550] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1551] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1552] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1553] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1554] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1555] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1556] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1557] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1558] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1559] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1560] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1561] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1562] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1563] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, analyzes it with a generative AI model, and issues instructions to traffic lights to achieve optimal signal switching. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[1564] Server Roles and Operations

[1565] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[1566] 1. Receiving image data

[1567] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[1568] 2. Image data preprocessing

[1569] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[1570] 3. Analysis using generative AI models

[1571] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[1572] 4. Creating signal switching instructions

[1573] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[1574] 5. Sending instructions to traffic lights

[1575] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[1576] Terminal roles and processing

[1577] The terminal is responsible for directly controlling the traffic lights.

[1578] 1. Receiving Instructions

[1579] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[1580] 2. Traffic light control

[1581] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[1582] 3. Feedback of results

[1583] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[1584] User roles and processes (for road users)

[1585] Users benefit from a real-time optimized signaling system.

[1586] 1. Check traffic light information

[1587] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[1588] 2. Passing through an intersection

[1589] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[1590] 3. Avoiding traffic jams

[1591] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[1592] Specific examples

[1593] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[1594] Server Processing

[1595] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[1596] Terminal handling

[1597] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[1598] User Action

[1599] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[1600] The above is a specific embodiment of the present invention and the flow of the entire system.

[1601] The processing flow will be explained below.

[1602] Server Processing

[1603] Step 1:

[1604] The server receives image data in real time from cameras installed at intersections.

[1605] The server connects to the camera's data stream and continuously captures video data.

[1606] Step 2:

[1607] The server performs preprocessing on the received image data.

[1608] Noise removal and resolution adjustment are performed, and the target area is cropped as necessary.

[1609] Step 3:

[1610] The server inputs the preprocessed image data into the generative AI model.

[1611] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[1612] Step 4:

[1613] Based on the analysis results, the server creates signal switching instructions to perform signal optimization.

[1614] For example, if there are many vehicles heading north, the traffic light in that direction is set to stay green for a longer period of time.

[1615] Step 5:

[1616] The server transmits a signal switching instruction to the traffic light control server.

[1617] Send instructions including specific control timing for traffic lights.

[1618] Terminal handling

[1619] Step 1:

[1620] The terminal receives a signal switching instruction from the server.

[1621] The received information includes the timing and direction of signal switching.

[1622] Step 2:

[1623] The terminal controls the traffic lights based on the instructions received.

[1624] For example, set the northbound traffic light to green and the eastbound traffic light to red.

[1625] Step 3:

[1626] The terminal checks the execution status of the signal switching and sends feedback to the server.

[1627] The feedback includes the successful completion of the signal switch.

[1628] User processing (for road users)

[1629] Step 1:

[1630] When a user approaches an intersection, the user visually checks the traffic light display.

[1631] Check the traffic light indications to prepare to pass through the intersection smoothly.

[1632] Step 2:

[1633] The user passes through the intersection following the traffic lights.

[1634] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[1635] Step 3:

[1636] To enable a user to smoothly pass through an intersection and avoid congestion.

[1637] Traffic flows more smoothly and you can reach your destination faster.

[1638] Example 1

[1639] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1640] Current traffic signal systems operate based on fixed patterns, and one issue is that they are unable to flexibly control traffic in response to real-time traffic conditions. This results in frequent traffic congestion and delays, making efficient traffic management difficult. Furthermore, there is a lack of means to accumulate and analyze the data necessary for signal control, making it impossible to achieve optimal signal control based on fluctuations and predictions of traffic volume. Furthermore, this increases the risk of traffic accidents and causes frequent inconvenience to drivers and pedestrians.

[1641] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1642] In this invention, the server includes means for receiving image data in real time from high-precision cameras installed at intersections, means for preprocessing the received image data to remove noise and adjust resolution, means for inputting the preprocessed image data into a generative AI model and analyzing traffic volume, vehicle direction, and vehicle speed, means for calculating the next signal switch timing based on the analysis results and generating specific control instructions for the traffic lights, means for transmitting the generated signal switch instructions to a traffic light control system, means for automatically controlling the signal switch of the traffic lights by the traffic light control system, and means for confirming whether the traffic light switch was performed normally and feeding back the result. This enables flexible and optimal signal control that responds to real-time traffic conditions.

[1643] A "high-precision camera" is a device that can capture the entire intersection in high resolution and provide accurate image data in real time.

[1644] "Real-time" refers to a processing method that can instantly grasp the current traffic situation and reflect it immediately.

[1645] "Traffic volume" is the number of vehicles and pedestrians passing through a particular road within a certain period of time.

[1646] "Monitoring" refers to the act of continuously observing traffic conditions at an intersection and acquiring necessary data.

[1647] "Image data" refers to visual information captured by a camera that is represented in digital form.

[1648] "Preprocessing" is a process in which acquired image data is processed, such as by removing noise and adjusting resolution, to improve the accuracy of analysis.

[1649] A "generative AI model" is an artificial intelligence program that is trained to analyze traffic situations using machine learning algorithms.

[1650] "Analysis" is the process of evaluating the acquired data in detail and extracting specific information such as traffic volume, vehicle direction, and vehicle speed.

[1651] The "signal switching instruction" is data generated as a specific operation instruction by determining the state of the next signal based on the analysis result.

[1652] "Traffic light control system" is a general term for hardware and software that receives instructions from a server and directly operates traffic lights.

[1653] "Feedback" is the process of checking the results after switching signals and reporting them to the server.

[1654] "Optimization" refers to adjusting traffic signals to control them most efficiently according to traffic volume and time of day.

[1655] This invention is a system that installs high-precision cameras at intersections, monitors traffic volume in real time, and generates optimal switching instructions for traffic lights by analyzing the data using a generative AI model, thereby controlling traffic signals flexibly and efficiently. Below, we will explain how to specifically implement this system.

[1656] Hardware and Software Configuration

[1657] server

[1658] The server is the core of this system and uses the following hardware and software in combination:

[1659] Hardware: High-performance processor (e.g., Intel Xeon processor), large memory capacity (e.g., 32GB RAM), SSD storage (e.g., 1TB SSD)

[1660] Software: Ubuntu OS, image processing libraries (e.g., OpenCV), machine learning frameworks (e.g., TensorFlow, YOLOv5)

[1661] Terminal (traffic signal control device)

[1662] The terminal receives instructions from the server and directly controls the traffic lights. The following hardware and software are used:

[1663] Hardware: Microcontroller (e.g. Raspberry Pi), GPIO pins, relay control board

[1664] Software: Raspbian OS, HTTP communication library, GPIO control library

[1665] User

[1666] The user is a road user who checks traffic light information and benefits from an optimized traffic light system.

[1667] Data processing and calculation procedures

[1668] The server receives image data in real time from a high-precision camera (e.g., Sony Alpha series). The camera captures a panoramic view of the intersection and sends the data to the server at a rate of 30 frames per second. The server then performs noise removal and resolution adjustment on the received image data, thereby maintaining data precision and improving the accuracy of analysis. This processing is performed using the OpenCV image processing library.

[1669] The preprocessed image data is input into a generative AI model (e.g., YOLOv5). The AI ​​model is built using the Python framework TensorFlow and analyzes traffic volume, vehicle direction, and vehicle speed from the image. Based on the results of this analysis, the server calculates the next traffic light switching timing and generates specific control instructions. These instructions include the number of seconds to keep the traffic light green for each direction.

[1670] The generated signal switching instructions are sent from the server to the traffic light control system. This communication uses the HTTP protocol, and the instructions are sent in JSON format. The traffic light control system automatically controls the traffic lights based on the instructions received from the server. Specifically, it switches the LED display of the traffic lights using GPIO pins.

[1671] The system checks whether the traffic light control was successful and sends the result back to the server. This is done again using HTTP communication, and the result is sent to the server in JSON format. This feedback allows the server to obtain new data to generate the next instruction.

[1672] Examples of specific examples and prompts

[1673] During the 8:00 a.m. rush hour, when there are many vehicles coming from the north at intersection A, the system operates as follows:

[1674] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[1675] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[1676] The user enters intersection A from the north and can pass through the intersection smoothly because the traffic light is green for a long time, which reduces congestion and shortens commuting time.

[1677] Example prompt sentence:

[1678] Image data is input into the generative AI model, which analyzes traffic volume, vehicle direction, and speed.

[1679] Based on the analysis results, the next signal switching timing is calculated and traffic light control instructions are generated.

[1680] It sends instructions to the traffic light control system to control the traffic lights.

[1681] The above is an embodiment of the invention.

[1682] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1683] Step 1:

[1684] The server receives image data in real time from high-definition cameras installed at intersections. As input, it receives image data from the cameras in JPEG or H.264 format. The output is raw image data stored in the server's memory. Specifically, the server receives data from the cameras at a rate of 30 frames per second and prepares it for the next processing step.

[1685] Step 2:

[1686] The server performs preprocessing on the received image data. The input is the raw image data received in step 1. The data is processed using the image processing library OpenCV to remove noise (Gaussian filter) and adjust the resolution. The output is clean image data after preprocessing. Specifically, the server performs the following operations:

[1687] Apply a Gaussian filter to remove noise

[1688] Resize the image resolution to 640x480

[1689] Step 3:

[1690] The server inputs the preprocessed image data into the generative AI model for analysis. The input is the clean image data preprocessed in step 2. The generative AI model (e.g., YOLOv5, TensorFlow) analyzes traffic volume, vehicle direction, and vehicle speed from the input image data. The output is analysis result data (JSON format) showing traffic conditions. Specifically, the server performs the following operations:

[1691] Initialize the generative AI model

[1692] Input image data into the model and generate analysis results

[1693] Step 4:

[1694] The server generates signal switching instructions based on the analysis results. The input is the analysis result data obtained in step 3. For data processing, the server analyzes the analysis results and calculates the next signal switching timing and the signal status for each direction. The output is specific signal switching instructions (JSON format). Specifically, the server performs the following operations:

[1695] Analyze the analysis results and understand the traffic situation

[1696] Calculates the timing of traffic lights switching for each direction and generates specific instructions

[1697] Step 5:

[1698] The server sends the generated signal change instruction to the traffic light control system. The input is the signal change instruction (JSON format) generated in step 4. The output is the acknowledgment (HTTP response) received by the traffic light control system. Specifically, the server performs the following operations:

[1699] Send a signal switching command using the HTTP POST method

[1700] Obtaining acknowledgement from the traffic light control system

[1701] Step 6:

[1702] The terminal receives a signal switching instruction sent from the server. The input is the signal switching instruction (JSON format) from the server. The output is the signal switching instruction data stored on the terminal. In concrete terms, the terminal receives the instruction from the server via HTTP communication and prepares for the next processing step.

[1703] Step 7:

[1704] The terminal controls the traffic light based on the received signal switching instruction. The input is the signal switching instruction data received in step 6. The output is the change in the LED display of the traffic light. Specifically, the terminal performs the following operations:

[1705] Controlling traffic light LEDs using GPIO pins

[1706] Turning the traffic light green in one direction and red in another

[1707] Step 8:

[1708] The device checks whether the traffic light switch was successful and feeds the result back to the server. The input is the current state of the traffic light. The output is feedback data (in JSON format) to the server. Specifically, the device performs the following operations:

[1709] Check the traffic light status

[1710] Generate feedback data and send it to the server using the HTTP POST method

[1711] Step 9:

[1712] When approaching an intersection, the user checks the traffic light information. The input is the current road condition and the traffic light status. The output is information that allows the user to pass through the intersection safely. Specifically, the user checks the traffic light status using the navigation system or visually and performs driving operations.

[1713] Step 10:

[1714] The user passes through the intersection according to the optimized signal pattern. The input is the status of the traffic lights and the current road conditions. The output is the reduction of congestion and safe driving. As a specific action, the user passes through the intersection while the signal is green and can drive safely.

[1715] Step 11:

[1716] The user reaches their destination quickly as a result of smooth traffic flow and avoidance of congestion. The input is smooth traffic flow due to optimal control of traffic lights. The output is a state in which the user can reach their destination quickly and safely. In concrete terms, the user can reach their destination without stress.

[1717] (Application example 1)

[1718] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1719] In modern traffic systems, traffic signals at intersections are controlled in a fixed manner and are unable to respond to fluctuations in traffic volume, resulting in frequent traffic congestion. Furthermore, with the spread of autonomous vehicles, real-time traffic signal information is required, but current systems lack the mechanisms to accommodate this. Therefore, it is necessary to optimize traffic signal switching and provide traffic signal information to autonomous vehicles.

[1720] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1721] In this invention, the server includes means for installing high-precision cameras at intersections and monitoring traffic volume in real time, means for analyzing the acquired image data with a generative AI model and instructing optimal signal switching according to traffic conditions, means for automatically controlling signal switching at traffic lights, and means for providing real-time signal information to the navigation system of autonomous vehicles. This optimizes signal switching according to traffic volume, alleviating traffic congestion and enabling autonomous vehicles to pass through intersections efficiently.

[1722] A "high-precision camera" is a camera device that can capture the entire intersection in real time with high resolution, capturing detailed traffic conditions.

[1723] "Means for monitoring traffic volume in real time" refers to technology that uses high-precision cameras to instantly monitor current traffic volume and vehicle movements and acquire that data.

[1724] "Means of analyzing acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions" refers to a technology in which image data acquired from a camera is input into a generative AI model for analysis, and based on the results, optimal switching instructions are given to traffic lights.

[1725] "Means for automatically controlling signal switching for traffic lights" refers to technology that automatically adjusts the color and timing of traffic lights based on the analysis results of a generative AI model.

[1726] "Means for providing real-time traffic light information to the navigation system of an autonomous vehicle" refers to technology that provides real-time information such as the current status of traffic lights and the timing of the next change of traffic lights to the navigation system of an autonomous vehicle.

[1727] "Means to optimize signal control in response to time-of-day and daily fluctuations" refers to technology that takes into account daily and time-of-day fluctuations in traffic volume and performs optimal signal switching.

[1728] "Means that take into account traffic volume in each direction, vehicle direction of travel, and vehicle speed" refers to technology that analyzes in detail the traffic volume and vehicle movement from each direction at a specific intersection and controls traffic signals based on that information.

[1729] In this invention, a high-precision camera, a generative AI model, a traffic light control server, and a navigation system for autonomous vehicles are combined to realize a traffic light control system that utilizes real-time monitoring of traffic volume and a generative AI model. Specific embodiments of the system are described below from the perspectives of the server, terminal, and user.

[1730] Server Roles and Operations

[1731] The server is the core of the system, analyzing traffic conditions and generating traffic light control instructions.

[1732] 1. Receiving image data

[1733] The server receives real-time image data from high-precision cameras installed at intersections, which constantly capture the entire intersection and send the data to the server.

[1734] 2. Image data preprocessing

[1735] The server performs preprocessing on the received image data, such as noise removal and resolution adjustment, to maintain data accuracy and improve the accuracy of analysis.

[1736] 3. Analysis using generative AI models

[1737] The pre-processed image data is fed into a generative AI model, which analyzes traffic volume, vehicle direction, vehicle speed, etc. to provide a detailed assessment of the traffic situation at the intersection.

[1738] 4. Creating signal switching instructions

[1739] Based on the analysis results, the server calculates the timing of the next traffic light switch and generates specific instructions such as which direction the traffic light should be green for and for how long.

[1740] 5. Sending instructions to traffic lights

[1741] The server sends the created signal switching instructions to the traffic light control server, which gives specific control instructions to the traffic lights.

[1742] 6. Providing information to autonomous vehicles

[1743] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the timing of the next traffic light change and the current traffic light status.

[1744] Terminal roles and processing

[1745] The terminal is responsible for directly controlling the traffic lights.

[1746] 1. Receiving Instructions

[1747] The terminal receives a signal switching instruction sent from the server, and the received data includes the specific timing and direction of signal switching.

[1748] 2. Traffic light control

[1749] Based on the received instructions, the terminal controls the traffic lights, for example, turning the northbound traffic light green and the eastbound traffic light red.

[1750] 3. Feedback of results

[1751] It checks whether the signal switch was successful and feeds the result back to the server, so that the server has new data to generate the next instruction.

[1752] User roles and processes (for road users)

[1753] Users benefit from a real-time optimized signaling system.

[1754] 1. Check traffic light information

[1755] As users approach an intersection, they can check traffic light information, which is updated in real time, visually or through their navigation system.

[1756] 2. Passing through an intersection

[1757] Users can navigate through intersections smoothly by following optimized traffic light patterns. For example, if the northbound traffic light is set to stay green longer, vehicles coming from the north can proceed more smoothly.

[1758] 3. Avoiding traffic jams

[1759] Traffic flows more smoothly and congestion is reduced, allowing users to reach their destinations more quickly. Traffic signals are optimally controlled, allowing for stress-free driving.

[1760] Specific examples

[1761] Take the example of 8:00 AM rush hour. At intersection A, there are many vehicles coming from the north.

[1762] Server Processing

[1763] The server analyzes the camera images and determines that there is a sudden increase in the number of vehicles traveling north. Based on the analysis results, it generates an instruction to turn the northbound traffic light green for 60 seconds and the east-westbound traffic light red for 30 seconds, and sends this instruction to the traffic light control server.

[1764] Terminal handling

[1765] The device receives instructions from the server, switches the north traffic light to green for 60 seconds, and switches the east-west traffic light to red for 30 seconds, and provides feedback to the server that the switch was successfully completed.

[1766] User Action

[1767] Users approaching intersection A from the north can pass through the intersection smoothly because the traffic light is green for a long time, reducing congestion and shortening commute times.

[1768] Prompt Sentence Examples

[1769] "A high-precision camera system that uses generative AI models to analyze intersection traffic volume in real time and optimize traffic light switching. We want to create an application that provides real-time traffic light switching information to autonomous vehicles and navigation systems."

[1770] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1771] Step 1:

[1772] Receiving image data

[1773] The server receives image data in real time from a high-definition camera. The camera constantly captures the entire intersection and sends the data to the server via the Internet. The input is image data from the high-definition camera, and the output is image data stored on the server.

[1774] Step 2:

[1775] Image data preprocessing

[1776] The server performs noise reduction and resolution adjustment on the received image data. For this, it uses an image processing library (e.g., OpenCV). Preprocessing removes unnecessary noise in the image and optimizes the resolution for analysis. The input is image data from a high-precision camera, and the output is preprocessed image data.

[1777] Step 3:

[1778] Analysis using generative AI models

[1779] The server inputs the preprocessed image data into a generative AI model (e.g., TensorFlow or PyTorch) to analyze traffic conditions such as traffic volume, vehicle direction, and vehicle speed. The generative AI model analyzes the acquired data and quantifies and evaluates the traffic conditions. The input is the preprocessed image data, and the output is the analysis results of the traffic conditions.

[1780] Step 4:

[1781] Creating signal switching instructions

[1782] The server calculates the next signal switching timing based on the analysis results. Specifically, it generates instructions such as which direction the signal should be green for and for how long. The signal switching timing is determined based on the evaluation results of the generative AI model. The input is the analysis result of the traffic situation, and the output is the signal switching instruction.

[1783] Step 5:

[1784] Sending instructions to traffic lights

[1785] The server sends the created signal switching instruction to the traffic light control server. This gives specific control instructions to the traffic lights. The input is the signal switching instruction, and the output is the control instruction sent to the traffic light control server.

[1786] Step 6:

[1787] Providing information to autonomous vehicles

[1788] The server transmits real-time traffic light information to the autonomous vehicle's navigation system, including the next traffic light switch timing and the current traffic light status. The input is a traffic light switch instruction, and the output is real-time traffic light information provided to the autonomous vehicle's navigation system.

[1789] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1790] This invention optimizes traffic signal control at intersections and smooths traffic flow through a system that combines a high-precision camera, a generative AI model, and an emotion engine that recognizes user emotions. Below, we will explain each process in detail from the perspectives of the server, terminal, and user.

[1791] Server Roles and Operations

[1792] The server is the center of the system, responsible for analyzing traffic conditions, generating signal control instructions, and processing user emotion data.

[1793] 1. Receiving image data

[1794] The server receives real-time image data from high-precision cameras installed at intersections, which monitor the entire intersection and continuously transmit video data to the server.

[1795] 2. Image data preprocessing

[1796] The server removes noise from the received image data, adjusts the resolution, and also crops the target area to maintain data accuracy.

[1797] 3. Analysis of Traffic Conditions Using Generative AI Models

[1798] The pre-processed image data is input into a generative AI model to analyze traffic volume, vehicle direction, vehicle speed, etc. This allows for a detailed assessment of the current state of the intersection.

[1799] 4. Analysis of user emotion data using emotion engine

[1800] The server collects emotional data from the user's voice and facial expressions through an emotion engine, and detects stress levels in particular. For example, it analyzes the driver's facial expressions and the voices inside the car to determine the current emotional state.

[1801] 5. Signal switching instruction generation

[1802] Based on traffic conditions and user emotion data, the server calculates the next traffic light change timing. For example, if the user's stress level is high, the server selects a setting that switches the traffic light more smoothly.

[1803] 6. Sending instructions to traffic lights

[1804] The created signal switching instruction is sent to the traffic light control server. The instruction contains specific information such as which direction the signal should be green for and for how long.

[1805] Terminal roles and processing

[1806] The terminal is responsible for directly controlling the traffic lights at the intersection.

[1807] 1. Receiving Instructions

[1808] The terminal receives traffic light switching instructions from the server, which include the specific timing and direction of the traffic light switching.

[1809] 2. Traffic light control

[1810] Based on the received instructions, the device controls the traffic lights, for example, setting the northbound traffic light to green and the eastbound traffic light to red.

[1811] 3. Feedback of results

[1812] It checks whether the signal switching was successful and reports the result to the server. The feedback information is used to instruct the next signal switching.

[1813] User roles and processes (for road users)

[1814] Users benefit from real-time optimized signal control.

[1815] 1. Check traffic light information

[1816] As a user approaches an intersection, they check the traffic light indications visually or through their in-car navigation system.

[1817] 2. Passing through an intersection

[1818] Users can smoothly navigate through intersections by following optimized traffic light patterns. For example, the northbound traffic light will stay green longer, allowing vehicles coming from the north to proceed smoothly.

[1819] 3. Reflecting emotions

[1820] Traffic light control that reflects the user's emotions reduces stress and provides a comfortable driving environment. For example, if the emotion engine detects high stress levels in the user, it will quickly switch traffic lights to alleviate traffic congestion, which causes stress.

[1821] Specific examples

[1822] Let's take the 5:00 PM rush hour as an example. At intersection B, there is a significant increase in vehicles coming from the east.

[1823] Server Processing

[1824] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[1825] Terminal handling

[1826] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[1827] User Action

[1828] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[1829] The above is a specific embodiment of the present invention and the flow of the entire system.

[1830] The processing flow will be explained below.

[1831] Server Processing

[1832] Step 1:

[1833] The server receives image data in real time from high-precision cameras installed at intersections.

[1834] The server connects to the camera's data stream and continuously captures the video data.

[1835] Step 2:

[1836] The server preprocesses the received image data.

[1837] Remove noise, adjust resolution, and crop specific areas of intersections to improve data accuracy.

[1838] Step 3:

[1839] The server inputs the preprocessed image data into the generative AI model.

[1840] The generative AI model analyzes data such as traffic volume, vehicle direction, and vehicle speed.

[1841] Step 4:

[1842] The server uses an emotion engine to collect the user's voice and facial expression data and analyze the user's emotions.

[1843] In particular, it analyzes the user's facial expressions and the voices inside the car to detect stress levels.

[1844] Step 5:

[1845] The server generates optimal signal switching instructions based on traffic conditions and emotion data.

[1846] For example, if the user's stress level is high, the signal may be set to switch quickly.

[1847] Step 6:

[1848] The server transmits the generated signal switching instruction to the signal control server.

[1849] Send instructions that include the specific timing and direction of switching signals.

[1850] Terminal handling

[1851] Step 1:

[1852] The terminal receives a signal switching instruction from the server.

[1853] The received information includes the specific timing and direction of traffic light changes.

[1854] Step 2:

[1855] The terminal controls the traffic lights based on the instructions received.

[1856] For example, the northbound traffic light will turn green and the eastbound traffic light will turn red.

[1857] Step 3:

[1858] The terminal checks the execution status of the signal switching and sends feedback to the server.

[1859] The feedback includes successful completion of the signal switch.

[1860] User processing (for road users)

[1861] Step 1:

[1862] When a user approaches an intersection, the user checks the traffic light display visually or through the in-car navigation system.

[1863] Check the traffic light status, which is updated in real time, and prepare to pass through the intersection.

[1864] Step 2:

[1865] The user follows the traffic lights and passes through the intersection.

[1866] For example, if the northbound traffic light is set to stay green for a longer period of time, vehicles coming from the north can proceed smoothly.

[1867] Step 3:

[1868] Traffic light control that reflects the user's emotions reduces stress.

[1869] If the emotion engine detects high stress in the user, the traffic lights will switch quickly to ease traffic congestion, thereby reducing the user's stress.

[1870] Example 2

[1871] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1872] Conventional traffic signal control systems are often limited to monitoring traffic volume and controlling signal switching, and are unable to consider real-time changes in traffic conditions or the emotional state of users. This has resulted in problems such as congestion and a lack of reduction in user stress. The present invention aims to solve these problems and optimize traffic flow while also reducing user stress.

[1873] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1874] In this invention, the server includes a means for installing high-precision camera devices at road intersections and monitoring traffic volume in real time, a means for analyzing acquired video data using a generative AI model and optimizing traffic light switching based on traffic conditions and vehicle speed and direction, a means for adjusting traffic light switching based on an emotion analysis engine for grasping the emotional state of users, and a means for automatically controlling traffic lights to switch signals, thereby enabling real-time response to changes in traffic conditions and reducing user stress.

[1875] A "high-precision imaging device" is a device that captures high-resolution images of specific areas, such as intersections, in real time.

[1876] "Real-time" means that data is collected and processed in accordance with the current moment.

[1877] "Traffic volume" refers to the number of vehicles passing through a particular road or intersection.

[1878] A "generative AI model" refers to a model that uses machine learning algorithms to analyze data and make predictions.

[1879] "Traffic conditions" refers to the state of traffic flow and congestion at the current time.

[1880] "Vehicle speed" is a measurement of how fast a particular vehicle is traveling.

[1881] "Heading" refers to the direction in which a vehicle is moving.

[1882] "Switching lights" means that the color of a traffic light is changed.

[1883] An "emotion analysis engine" is a system that analyzes and evaluates a user's emotional state from data such as audio and video.

[1884] "Automatically" means that the system completes the action by itself without human intervention.

[1885] A "traffic light" is a device installed on a road to direct traffic.

[1886] "Users" refers to drivers and pedestrians who use the system.

[1887] "Stress" refers to a state of psychological and physiological tension caused by external stimuli or stress.

[1888] The present invention is a traffic light control system that uses a high-precision imaging device, a generative AI model, and an emotion analysis engine. Specific embodiments will be described below from the perspectives of the server, terminal, and user.

[1889] Server Roles and Operations

[1890] The server plays a central role in the system and performs the following processes:

[1891] 1. Receiving image data

[1892] The server receives real-time video data from high-definition cameras installed at intersections, which transmit the video at 1080p resolution at 30 frames per second via RTSP (Real-Time Streaming Protocol).

[1893] 2. Image data preprocessing

[1894] The server uses image processing libraries such as OpenCV to remove noise, adjust resolution, and crop the target area from the received video data, maintaining data accuracy.

[1895] 3. Analysis of Traffic Conditions Using Generative AI Models

[1896] The server inputs the preprocessed video data into a generative AI model (such as YOLO) to analyze traffic volume, vehicle direction, and vehicle speed, thereby obtaining a detailed understanding of the current situation at the intersection.

[1897] 4. Analysis of user emotion data using emotion engine

[1898] The server analyzes voice and facial expression data acquired from the in-car microphone and dashboard camera to assess the user's emotional state, particularly their stress level.

[1899] 5. Signal switching instruction generation

[1900] The server calculates the timing of the next traffic light switch based on traffic conditions and user emotion data, generates specific instructions such as which direction the signal should be green for and for how long, and sends these to the traffic light control server.

[1901] Terminal roles and processing

[1902] The terminal (traffic light control device) performs the following processing.

[1903] 1. Receiving Instructions

[1904] The terminal receives signal switching instructions from the server via the REST API.

[1905] 2. Traffic light control

[1906] The device controls the traffic lights based on the received instructions, for example, setting the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[1907] 3. Feedback of results

[1908] The device checks whether the signal switching was performed correctly using its built-in sensors and camera, and reports the results to the server.

[1909] User roles and processes (for road users)

[1910] Users benefit from the system in the following ways:

[1911] 1. Check traffic light information

[1912] When a user approaches an intersection, they check the traffic light indications visually or through the in-car navigation system.

[1913] 2. Passing through an intersection

[1914] The user follows the optimized signal pattern and passes through the intersection smoothly.

[1915] 3. Reflecting emotions

[1916] By reflecting the user's emotions in the system, stress is reduced and a comfortable driving environment is provided.

[1917] Specific examples

[1918] Let's take the 5 PM rush hour as an example. If there is a significant increase in vehicles coming from the east at intersection B, the following process will be performed.

[1919] Server Processing

[1920] The server analyzes the camera images and determines that there are more vehicles traveling eastbound. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to keep the eastbound traffic light green for longer and the other traffic lights green for shorter periods, and sends these instructions to the traffic light control server.

[1921] Terminal handling

[1922] The device receives the instruction from the server, sets the eastbound traffic light to green for 90 seconds, and the north-south traffic light to red for 30 seconds, and sends feedback to the server that the switch was successfully completed.

[1923] User Action

[1924] Users heading towards intersection B from the east will be able to pass through the intersection smoothly and without stress because the traffic light will be green for a long time. This will ease congestion and improve users' stress levels.

[1925] Prompt Sentence Examples

[1926] "Analyze traffic flow at intersection B during the 5 PM rush hour, and generate signal switching instructions to accommodate the increase in vehicles coming from the east. Also, include measures to be taken when users' stress levels are high."

[1927] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1928] Step 1:

[1929] The server receives video data in real time from high-precision cameras installed at intersections.

[1930] How it works: The high-definition camera captures video at 1080p resolution at 30 frames per second and sends the data to a server using RTSP (Real-Time Streaming Protocol).

[1931] Input: Video data from an intersection.

[1932] Output: Real-time video data stored on the server.

[1933] Step 2:

[1934] The server performs pre-processing on the received video data.

[1935] Specific operations: Use image processing libraries such as OpenCV to remove noise (e.g., apply a Gaussian filter), adjust resolution (e.g., convert from Full HD to HD), and crop the target area.

[1936] Input: Real-time video data.

[1937] Output: Preprocessed video data.

[1938] Step 3:

[1939] The server inputs the preprocessed video data into a generative AI model to analyze traffic conditions.

[1940] How it works: It uses object detection models such as YOLO to analyze traffic volume, vehicle direction, and vehicle speed. For example, the model recognizes eight vehicles in an image and calculates their direction and speed.

[1941] Input: Preprocessed video data.

[1942] Output: Analysis results: traffic volume, vehicle direction, and vehicle speed.

[1943] Step 4:

[1944] The server analyzes the user's emotion data using an emotion engine.

[1945] Specific operation: Analyzes voice data collected from an in-car microphone and facial expression data acquired from a dashboard camera to assess the user's stress level. For example, stress is determined based on voice tone analysis and changes in facial expressions.

[1946] Input: speech and facial expression data.

[1947] Output: User's emotional assessment results (especially stress level).

[1948] Step 5:

[1949] The server generates a signal switching instruction based on the analysis result.

[1950] Specific operation: The system calculates the next traffic light switching timing by combining traffic conditions and user emotion data. For example, if traffic volume is heavy and the user's stress level is high, it generates a setting that shortens the waiting time at the traffic light.

[1951] Input: Traffic situation analysis results and user sentiment evaluation results.

[1952] Output: Signal switching instructions (e.g., set eastbound signal green for 90 seconds, other directions red for 30 seconds).

[1953] Step 6:

[1954] The server transmits the generated signal switching instruction to the signal control server.

[1955] Specific operation: Sends signal switching instructions securely and reliably using communication protocols such as REST API.

[1956] Input: Signal switching instruction.

[1957] Output: Instruction sent to traffic light control server completed.

[1958] Step 7:

[1959] The terminal receives signal switching instructions from the server and controls the traffic lights.

[1960] Specific behavior: For example, set the eastbound traffic light to green for 90 seconds and the north-south traffic light to red for 30 seconds.

[1961] Input: Signal switching instruction from the server.

[1962] Output: The set traffic light state.

[1963] Step 8:

[1964] The terminal checks whether the signal switching was performed correctly and feeds the result back to the server.

[1965] What it does: It uses built-in sensors and cameras to monitor traffic light status and ensures that the switch is operating correctly.

[1966] Input: Traffic light status data.

[1967] Output: Signal switching feedback information.

[1968] (Application example 2)

[1969] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1970] Conventional traffic light control systems only considered traffic volume, vehicle direction, and speed when switching signals, which did not adequately reduce the stress of drivers and passengers. Furthermore, because signal control depended solely on traffic flow conditions, it was difficult to quickly alleviate traffic congestion, especially during rush hour or specific time periods. With the widespread adoption of autonomous vehicles, there is a demand for more precise signal control while also improving the comfort of passengers inside the vehicle.

[1971] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1972] In this invention, the server includes a means for installing high-precision cameras at intersections and monitoring traffic volume in real time, a means for analyzing the acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions, a means for collecting user emotion data using an emotion engine and reflecting it in signal control, a means for automatically controlling signal switching at traffic lights, and a means for detecting stress levels using an emotion engine installed in the vehicle and reflecting it in signal switching. This enables highly accurate analysis of traffic conditions at intersections and signal control that takes the user's emotional state into consideration. As a result, stress caused by waiting at traffic lights can be reduced and traffic flow can be maintained smoothly.

[1973] A "high-precision camera" is a camera that can capture traffic conditions in real time with high resolution and accuracy.

[1974] A "generative AI model" is an artificial intelligence model that analyzes acquired image data, extracts information such as traffic volume, vehicle direction and speed, and performs optimal signal control according to the system.

[1975] The "emotion engine" is an analysis engine that collects emotional data from the user's voice and facial expressions, and in particular detects stress levels.

[1976] A "traffic signal control server" is a server that generates instructions to control traffic lights installed at intersections and automatically switches between traffic lights.

[1977] The "in-vehicle emotion engine" is a system that is installed inside an autonomous vehicle to collect and analyze emotional data from passengers in real time.

[1978] "Signal switch instructions" are instructions that specify the timing and direction of traffic light switch based on data analyzed by the generative AI model and emotion engine.

[1979] "Traffic conditions" refers to detailed information such as traffic flow at intersections, vehicle direction, speed, and congestion status.

[1980] "User emotional data" is data relating to a user's emotional state, particularly stress level, that is collected using the emotion engine.

[1981] This invention is a system that analyzes traffic conditions and the emotional state of the user in real time to achieve optimal signal control so that autonomous vehicles can pass through intersections smoothly. Below, we will explain in detail the processing, hardware, and software from the perspectives of the server, terminal, and user.

[1982] Server Roles and Operations

[1983] The server is the center of the system and is responsible for analyzing traffic conditions, generating signal control instructions, processing user emotion data, etc. The server uses the following hardware and software:

[1984] High-precision cameras: Capture high-precision images of traffic conditions in real time.

[1985] Generative AI model: Analyzes acquired image data and generates detailed traffic data for signal control.

[1986] Emotion engine: Collects emotional data from the user's voice and facial expressions, particularly to detect stress levels.

[1987] Server system: Receives data, analyzes it, generates instructions, and sends them.

[1988] Specifically, the server first receives image data in real time from high-precision cameras installed at intersections. The image data is then analyzed using a generative AI model to extract information such as traffic volume, vehicle direction, and vehicle speed. Furthermore, the emotion engine receives user emotion data from an emotion engine installed inside the vehicle, identifying stress levels in particular. Based on this data, optimal signal switching instructions are generated and sent to the traffic light control server.

[1989] Terminal roles and processing

[1990] The terminal is responsible for directly controlling the traffic lights at the intersection. The terminal uses the following hardware and software:

[1991] Traffic light control system: Controls traffic lights based on instructions from the server.

[1992] Communication module: Receives signal switching instructions from the server and transmits them to the traffic light control system.

[1993] Specifically, the device receives traffic light switching instructions from the server in real time and controls the traffic lights based on those instructions. For example, it may receive an instruction such as "set the northbound traffic light to green for 90 seconds and the eastbound traffic light to red for 30 seconds." It then sends feedback to the server that the traffic light switching has been successfully completed.

[1994] User Roles and Actions

[1995] The user is responsible for operating the autonomous vehicle and generating emotion data. The following hardware and software are installed in the user's vehicle:

[1996] In-car camera and microphone: Devices for collecting the user's facial expressions and voice.

[1997] In-car emotion engine: Analyzes collected data and identifies the user's emotional state.

[1998] Specifically, the user drives the vehicle in a relaxed state. The in-vehicle camera and microphone collect the user's facial expressions and voice in real time, and the emotion engine analyzes the user's stress level. The analyzed data is sent to a server and used to generate traffic light control instructions.

[1999] Specific examples

[2000] For example, during the 5:00 PM rush hour, there is a significant increase in vehicles traveling east at Intersection B. The server analyzes camera images and confirms that there is an increase in vehicles traveling east. Meanwhile, the emotion engine detects that the user's stress level is rising. Based on this data, it generates instructions to set the eastbound traffic light to green for 90 seconds and the north-southbound traffic light to red for 30 seconds, and sends these instructions to the traffic light control server. As a result, users traveling east toward Intersection B can pass through the intersection smoothly and without stress.

[2001] Prompt Sentence Examples

[2002] As an example of a specific prompt sentence for a generative AI model, enter the following:

[2003] "Provide an image of the intersection and analyze traffic volume, vehicle direction, and speed. Return the following data:

[2004] Total number of vehicles

[2005] Number of vehicles in each direction (north, south, east, west)

[2006] Average vehicle speed

[2007] Direction of traffic congestion (presence or absence)

[2008] In this way, traffic conditions at intersections can be analyzed with high accuracy and in real time, enabling optimal signal control that reflects the user's emotional state.

[2009] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2010] Step 1:

[2011] The server receives image data in real time from high-precision cameras installed at intersections.

[2012] Input: Live video from high-definition cameras at the intersection

[2013] Output: Real-time image data

[2014] The server uses this image data to prepare for the next step.

[2015] Step 2:

[2016] The server performs preprocessing on the received image data, specifically noise removal and resolution adjustment.

[2017] Input: Real-time image data

[2018] Output: Preprocessed image data

[2019] The server uses the OpenCV library to perform Gaussian blurring to remove noise and adjust the resolution of the data.

[2020] Step 3:

[2021] The server inputs the preprocessed image data into a generative AI model to analyze traffic conditions.

[2022] Input: Preprocessed image data

[2023] Output: Analysis data such as traffic volume, vehicle direction, and vehicle speed

[2024] The server uses a generative AI model to extract from the image data the total number of vehicles, the number of vehicles in each direction, the average vehicle speed, and the direction of traffic congestion.

[2025] Step 4:

[2026] The server collects the user's emotional data from an emotion engine installed in the vehicle, and detects the user's stress level in particular.

[2027] Input: Audio and image data from the in-car camera and microphone

[2028] Output: User's emotional data (e.g., stress level)

[2029] The emotion engine analyzes the user's voice and facial expressions, and in particular quantifies their stress level and sends it to the server.

[2030] Step 5:

[2031] The server generates optimal signal switching instructions based on traffic data and emotion data.

[2032] Input: Traffic data, emotion data

[2033] Output: Signal switching instruction

[2034] The server generates specific instructions, including the timing and direction of traffic light changes, based on data obtained from the generative AI model and emotion engine.

[2035] Step 6:

[2036] The server transmits the generated signal switching instruction to the signal control server.

[2037] Input: Signal switching instruction

[2038] Output: Send instructions to the signal control server

[2039] The instructions include specifics such as "set the northbound traffic light green for 90 seconds and the eastbound traffic light red for 30 seconds."

[2040] Step 7:

[2041] The terminal receives signal switching instructions from the server and controls the traffic lights based on the instructions.

[2042] Input: Signal switching instruction

[2043] Output: Traffic light operation (switching between green and red lights)

[2044] The device follows the instructions to change the status of the traffic lights and control traffic within the intersection.

[2045] Step 8:

[2046] The terminal will then provide feedback to the server that the signal switch has been successfully completed.

[2047] Input: Traffic light status data

[2048] Output: Signal switching completion confirmation data

[2049] The terminal checks the result of the signal switching and sends it as feedback to the server.

[2050] Step 9:

[2051] The user follows the optimized signal pattern and passes through the intersection smoothly.

[2052] Input: Traffic light display status

[2053] Output: Smooth passage through intersections

[2054] Users can check the status of traffic lights and pass through intersections with less stress.

[2055] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2056] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2057] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2058] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2059] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2060] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2061] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2062] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2063] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2064] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2065] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2066] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2067] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2068] 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.

[2069] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2070] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2071] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2072] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2073] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may b...

Claims

1. High-precision cameras will be installed at intersections to monitor traffic volume in real time, A means of analyzing the acquired image data using a generative AI model and instructing optimal signal switching according to traffic conditions, a means for automatically controlling signal switching for a traffic light; A system including:

2. 10. The system of claim 1, wherein the generative AI model further comprises means for optimizing signal control in response to time of day and daily variations.

3. 2. The system of claim 1, further comprising means for taking into account the volume of traffic in each direction, the direction of travel of the vehicles, and the speed of the vehicles in the process of generating the signal change instructions.

Images