system

Abstract

Provide a system. A means for collecting video data in the vicinity of a traffic light using a camera; means for performing noise reduction and resolution adjustment on the collected video data; means for analyzing the movement of vehicles and people from the preprocessed video data; A means of assessing the risk of traffic accidents based on the analysis results, and A means of notifying management and suggesting countermeasures in cases of high risk; means for storing the analysis results and risk assessment results in a database and generating reports; A system including:

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] In recent years, the frequency of traffic accidents has been increasing, with serious human and property damage caused by accidents occurring near traffic lights. Conventional traffic monitoring systems lack the ability to detect accidents in real time, which often results in delayed response after an accident occurs. Furthermore, accident prevention is difficult due to inappropriate operation of traffic lights and installation of traffic signs. Therefore, there is a need for a system that can monitor traffic accidents in real time and take appropriate measures. [Means for solving the problem]

[0005] The present invention solves this problem by providing a system that includes: a means for collecting video data near traffic lights using a camera; a means for performing noise reduction and resolution adjustment on the collected video data; a means for analyzing the movements of vehicles and people from the preprocessed video data; a means for assessing the risk of traffic accidents based on the analysis results; a means for notifying an administrator and proposing countermeasures if the risk is high; and a means for storing the analysis results and risk assessment results in a database and generating a report. The system has the functions of sending a streaming request to the camera's IP address to acquire video data in real time, performing traffic flow analysis, and detecting abnormal behavior such as red light ignoring and dangerous driving during a specific period. This enables early detection of traffic accident risks and prompt countermeasures.

[0006] A "camera" is a device for collecting video data in the vicinity of traffic lights in real time.

[0007] "Video data" refers to image information of vehicles, people, and the environment near the traffic light captured by a camera.

[0008] "Noise reduction" is a process that removes unnecessary signals and distortions from collected video data to improve the quality of the data.

[0009] "Resolution adjustment" is a process of changing the resolution in order to optimize the image quality of the video data.

[0010] "Preprocessing" refers to the initial processing of collected video data, such as noise removal and resolution adjustment.

[0011] "Vehicle and pedestrian movement analysis" is the process of identifying the movement and direction of vehicles and pedestrians from pre-processed video data.

[0012] "Traffic accident risk assessment" is the process of analyzing and evaluating the conditions and factors that make traffic accidents more likely to occur based on analyzed data.

[0013] "Notification" refers to a means such as a message or alarm to communicate the results of the risk assessment to the administrator.

[0014] "Countermeasure proposal" is the process of presenting specific countermeasure methods to the administrator based on the results of risk assessment.

[0015] A "database" is a system for electronically storing and managing information such as analysis results and risk assessment results.

[0016] "Report generation" is the process of compiling periodic analysis results and recommendations based on stored data and providing them as reports.

[0017] A "streaming request" refers to sending a request to obtain video data from a camera in real time.

[0018] "Traffic flow analysis" is the process of analyzing traffic volume and vehicle movements over a specific period of time and identifying abnormal behavior.

[0019] "Abnormal behavior" refers to dangerous driving that disregards traffic rules and behavior such as ignoring traffic lights. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention provides a system that uses a camera to collect video data around traffic lights, analyzes the data to assess the risk of traffic accidents, and proposes countermeasures under specific conditions. An embodiment of the present invention will now be described in detail.

[0042] System configuration

[0043] The system consists of the following main components:

[0044] 1. Camera

[0045] 2. Server

[0046] 3. Database

[0047] 4. Administrator terminal

[0048] System Operation

[0049] Data collection

[0050] The server collects video data in real time from cameras installed near traffic lights, which monitor traffic volume, vehicle and pedestrian movements, and transmits the video data to the server.

[0051] Data Preprocessing

[0052] The server performs noise reduction and resolution adjustment on the collected video data, improving the quality of the video data and ensuring accurate subsequent analysis.

[0053] Movement Analysis

[0054] The server analyzes the movement of vehicles and people in the pre-processed video data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel. It also analyzes the status of traffic lights (red, green, yellow).

[0055] Risk Assessment

[0056] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it compares the results with past data and identifies risk patterns at specific times and intersections. If the risk is high, the server sends a notification to the administrator.

[0057] Notification and suggested solutions

[0058] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[0059] Data Storage and Reporting

[0060] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[0061] Specific examples

[0062] Example 1: Red light detection

[0063] 1. Data collection: The server acquires video data of traffic light A from the camera.

[0064] 2. Data preprocessing: The server removes noise from the video data and adjusts the resolution.

[0065] 3. Analysis: The server detects that the vehicle ran a red light.

[0066] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations.

[0067] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the traffic light timing."

[0068] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[0069] Example 2: Risks from increased traffic

[0070] 1. Data collection: The server acquires video data from the camera at traffic light B during rush hour.

[0071] 2. Data preprocessing: The server divides the data into time periods and removes noise.

[0072] 3. Analysis: The server performs traffic flow analysis and detects increases in traffic volume.

[0073] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[0074] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs."

[0075] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[0076] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures.

[0077] The processing flow will be explained below.

[0078] Step 1: Data collection

[0079] Subject: Server

[0080] The server obtains the IP address of the camera installed at each traffic light.

[0081] The server sends a streaming request to the specified IP address.

[0082] The server receives and stores the video data sent from the camera in real time.

[0083] Step 2: Data Preprocessing

[0084] Subject: Server

[0085] The server applies a noise reduction algorithm to the received video data.

[0086] The server adjusts the resolution and frame rate of the video data.

[0087] The server segments the video data by time as needed and divides it into segments of a fixed length.

[0088] Step 3: Analyze vehicle and human movements

[0089] Subject: Server

[0090] The server detects vehicles from the video data using a pre-trained vehicle detection model.

[0091] The server tracks the movement of the detected vehicle and calculates its speed and direction of travel.

[0092] The server analyzes the traffic light status (red, green, yellow).

[0093] Step 4: Risk assessment

[0094] Subject: Server

[0095] The server saves the analysis results in a temporary data store.

[0096] The server compares historical data with real-time data to detect outliers.

[0097] The server identifies risk patterns at specific times and intersections and calculates a risk score.

[0098] Step 5: Notification and proposed action

[0099] Subject: Server

[0100] The server will send a notification email or SMS to the administrator based on the assessed risk score.

[0101] The server refers to a database of past countermeasures and automatically proposes the most appropriate countermeasure.

[0102] The server will propose specific countermeasures such as "changing traffic light timing," "adding traffic signs," and "deploying police officers."

[0103] Step 6: Data storage and reporting

[0104] Subject: Server

[0105] The server stores the analysis results and risk assessment results in a database.

[0106] The server will regularly back up your data and store it safely.

[0107] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[0108] Example 1

[0109] 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."

[0110] Traffic accidents are a serious problem worldwide, affecting many lives and assets. The risk of accidents is particularly high near intersections and traffic lights due to the high volume of traffic and complex pedestrian movements. Predicting accidents in these locations and taking appropriate countermeasures is also difficult. To solve these problems, a system that can monitor and analyze traffic conditions in real time is required.

[0111] 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.

[0112] In this invention, the server includes a means for collecting video data around traffic lights in real time using a camera, a means for performing noise reduction and resolution adjustment on the collected video data, and a means for analyzing the movements of vehicles and pedestrians from the preprocessed video data using an algorithm, which makes it possible to evaluate the risk of traffic accidents by comparing with past data and propose specific countermeasures under specific conditions.

[0113] The "camera" is a device that collects video data around traffic lights in real time.

[0114] The "server" is a central processing unit that receives the video data sent from the camera and performs various analytical processes.

[0115] "Video data" refers to continuous image data captured by a camera that shows the traffic and pedestrian conditions around a traffic light.

[0116] "Noise reduction" is a process that removes unnecessary noise from video data to improve its quality.

[0117] "Resolution adjustment" is a process of unifying the resolution (level of image detail) of video data to an appropriate level.

[0118] "Algorithm" refers to the procedures and calculation methods used to analyze vehicle and pedestrian movements from video data.

[0119] "Motion analysis" is the process of detecting the movement of vehicles and pedestrians from pre-processed video data and identifying their speed and direction of travel.

[0120] "Risk assessment" is the process of evaluating the risk of traffic accidents based on analysis results and comparing them with past data.

[0121] "Notification" is a means of communication to inform managers of the results of traffic accident risk assessments.

[0122] "Proposals for countermeasures" refer to specific measures, such as changing traffic light timing or installing additional road signs, when there is a high risk of traffic accidents.

[0123] A "database" is a data management system that safely stores analysis and risk assessment results for later reference.

[0124] A "report" is a document that summarizes the analysis results and risk assessment results that are generated periodically.

[0125] The present invention is a system that monitors traffic conditions around traffic signals in real time, assesses the risk of traffic accidents, and proposes countermeasures. The system consists of the following main components:

[0126] 1. Camera

[0127] 2. Server

[0128] 3. Database

[0129] 4. Administrator terminal

[0130] System Overview

[0131] Users install network-connected cameras at intersections and near traffic lights. The cameras capture images of traffic and pedestrians in real time and send the video data to a server. A typical example of such a camera is a commonly used network camera.

[0132] The server receives the video data sent from the camera and performs the following processes:

[0133] 1. Data preprocessing: Denoise using OpenCV library and adjust resolution with FFmpeg software.

[0134] 2. Movement analysis: Analyze the movement of vehicles and pedestrians using the YOLO (You Only Look Once) algorithm.

[0135] 3. Risk assessment: Using TENSORFLOW®, we compare data with past data to assess the risk of traffic accidents.

[0136] If the risk is high, the results of the assessment are sent to the administrator's terminal and specific countermeasures are proposed. The analysis results and risk assessment results are then stored in a database, and reports are generated periodically.

[0137] Specific examples

[0138] Data collection

[0139] The server collects real-time video data from a network camera near the traffic lights, such as an Axis Q1765-LE, and captures image frames every 30 seconds.

[0140] Data Preprocessing

[0141] The server uses the OpenCV library to remove noise from the video and uses FFmpeg to standardize the resolution to 1280x720 pixels.

[0142] Movement Analysis

[0143] The server uses the YOLO model to identify the positions of vehicles and pedestrians in each frame and calculates the change in position between each frame to calculate speed.

[0144] Risk Assessment

[0145] The server uses TensorFlow to model past data and compare it with current data to calculate a risk score.

[0146] Notification and suggested solutions

[0147] The server uses the Twilio API to send SMS and email notifications to the administrator's device. For example, if there are frequent cases of people running red lights, the server can suggest changing the timing of the traffic lights.

[0148] Data Storage and Reporting

[0149] The server stores the analysis results and risk assessment results in a MySQL® database and uses JasperReports to periodically generate reports and save them in PDF format.

[0150] Examples of prompt statements

[0151] "Please describe in detail a program that monitors traffic conditions in real time near traffic light A and evaluates the risk of traffic accidents."

[0152] The system of the present invention continuously monitors traffic conditions near traffic signals and can take appropriate countermeasures by detecting the risk of traffic accidents at an early stage, which is expected to improve traffic safety.

[0153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0154] Step 1: Data collection

[0155] The server collects video data around traffic lights from a network camera in real time. As input, it receives streaming video data from the network camera (e.g., Axis Q1765-LE). Specifically, the server sends a streaming request to the camera's IP address and stores the received video data in a temporary directory.

[0156] Input: Video data from a network camera

[0157] Output: Video data saved in temporary directory

[0158] Step 2: Data Preprocessing

[0159] The server performs noise reduction and resolution adjustment on the acquired video data. It receives the collected video data as input and uses the OpenCV library to remove noise. Then, it uses FFmpeg software to unify the resolution to 1280x720 pixels. This process ensures accurate subsequent analysis.

[0160] Input: Video data saved in the temporary directory

[0161] Output: High-quality pre-processed video data

[0162] Step 3: Analyze the movement

[0163] The server uses the preprocessed video data to analyze the movement of vehicles and pedestrians. It receives the preprocessed video data as input and uses the YOLO model to identify the positions of vehicles and pedestrians. It then calculates the change in position between frames and determines their speed and direction of travel.

[0164] Input: High-quality pre-processed video data

[0165] Output: Position, speed, and heading data of vehicles and pedestrians

[0166] Step 4: Risk assessment

[0167] The server evaluates the risk of traffic accidents based on the movement analysis results. It receives the analyzed location, speed, and direction of travel data as input, and uses TensorFlow to compare it with past data and calculate a risk score. This process evaluates the risk of traffic accidents under certain conditions.

[0168] Input: Vehicle and pedestrian position, speed, and heading data

[0169] Output: Risk score

[0170] Step 5: Notification and proposed action

[0171] Based on the results of the risk assessment, if the risk is high, the server sends a notification to the administrator's device and proposes specific countermeasures. It receives the calculated risk score as input and uses the Twilio API to notify the administrator via SMS or email. Suggested countermeasures include changing traffic light timings or installing additional road signs.

[0172] Input: Risk Score

[0173] Output: Notification to administrator and suggested action

[0174] Step 6: Data storage and reporting

[0175] The server stores the analysis and risk assessment results in a database and generates reports periodically. As input, it takes the analysis and risk assessment results and stores them in a MySQL database. It then uses JasperReports to generate monthly or weekly reports and saves them in PDF format.

[0176] Input: Analysis results and risk assessment results

[0177] Output: Data stored in database, generated reports

[0178] (Application example 1)

[0179] 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."

[0180] In modern society, as autonomous vehicles become more widespread, there is a need to detect traffic accident risks early and implement appropriate countermeasures. However, conventional systems do not accurately assess the risk of traffic accidents and often only respond after an accident has occurred. In addition, drivers cannot receive risk information in real time, which can result in delayed preventive measures. To solve these issues, a system is needed that can monitor traffic conditions with high accuracy and assess and notify risks in real time.

[0181] 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.

[0182] In this invention, the server includes means for collecting video data around traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, and means for sending a real-time notification to the driver of the autonomous vehicle based on the analysis results and proposing specific safety measures, thereby enabling the driver of the autonomous vehicle to grasp the risk of a traffic accident early and take appropriate preventive measures.

[0183] A "camera" is a photographing device for collecting video data around a traffic light.

[0184] "Noise reduction" is a process that removes unnecessary information from collected video data to improve the quality of the data.

[0185] "Resolution adjustment" is a process that optimizes the image quality and size of collected video data to enhance the details.

[0186] "Motion analysis" is a technology that recognizes and analyzes the movements of vehicles and people from pre-processed video data.

[0187] "Assessing the risk of traffic accidents" is the process of calculating the probability of an accident occurring in a specific traffic situation based on the results of motion analysis.

[0188] "Sending notifications in real time" means instantly delivering the analysis results to the driver of the autonomous vehicle.

[0189] "Proposing specific safety measures" means advising drivers on specific actions and measures to take in response to assessed risks.

[0190] A "database" is an information management system that stores analysis results and risk assessment results so that they can be referenced later.

[0191] "Report generation" is the process of organizing the analysis results and risk assessment results and outputting them in an easy-to-read format.

[0192] This invention is a system that monitors traffic conditions near traffic signals in real time, assesses the risk of traffic accidents, and notifies drivers of autonomous vehicles, enabling them to take appropriate countermeasures quickly.

[0193] System configuration

[0194] The system consists of the following main components:

[0195] 1. Camera

[0196] It is installed near traffic lights and collects video data on traffic conditions.

[0197] 2. Server

[0198] Receives video data and performs various data processing and analysis.

[0199] 3. Database

[0200] Store the analysis and risk assessment results and generate reports.

[0201] 4. Administrator terminal

[0202] A device that lets you receive real-time notifications and identify the best course of action.

[0203] How to carry out the invention

[0204] Data collection

[0205] The system's camera collects video data around traffic lights in real time and sends it to a server. The hardware used is a built-in camera in a smartphone or a dedicated surveillance camera, and the communication protocol is HTTP / HTTPS.

[0206] Data Preprocessing

[0207] The server performs noise reduction and resolution adjustment on the received video data. The software used here is the OpenCV library, which improves the video quality.

[0208] Movement Analysis

[0209] The pre-processed video data is then used to apply deep learning models (e.g., YOLO or TensorFlow) to analyze vehicle and pedestrian movements, which allows for vehicle detection, tracking, and speed calculation.

[0210] Risk Assessment

[0211] The server assesses the risk of traffic accidents based on the results of the motion analysis, using a custom algorithm that compares the results with past data patterns, and sends a real-time notification to the administrator's device if the risk is high.

[0212] Notification and suggested solutions

[0213] The server sends real-time notifications to the driver of the autonomous vehicle and suggests specific safety measures, using software such as Firebase Cloud Messaging.

[0214] Data Storage and Reporting

[0215] The analysis and risk assessment results are stored in a database and periodically generated as reports, enabling long-term data management and backup.

[0216] Specific examples

[0217] While the driver is driving in autonomous mode, the system detects vehicles running red lights and sends a notification when the light changes, encouraging safe driving. The notification sent to the driver includes specific instructions such as, "A vehicle running a red light has been detected ahead. Please reduce your speed."

[0218] Example prompts to input to the generative AI model

[0219] "Analyze video data around traffic lights to assess the risk of traffic accidents. Detect vehicles running red lights and send real-time notifications to the driver of autonomous vehicles."

[0220] The present invention provides a powerful means for drivers of autonomous vehicles to instantly grasp traffic conditions and minimize the risk of accidents.

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] The camera collects video data around the traffic light.

[0224] Input: Real-time video around the traffic light

[0225] Output: Collected video data

[0226] Specific operation: The camera continuously captures video around the traffic light and sends it to the server.

[0227] Step 2:

[0228] The server performs noise reduction and resolution adjustment on the video data.

[0229] Input: Collected video data

[0230] Output: Pre-processed video data

[0231] Specific operation: The server uses the OpenCV library to remove noise from the data and adjust the resolution to improve image quality.

[0232] Step 3:

[0233] The server analyzes the movement of vehicles and people from the pre-processed video data.

[0234] Input: Preprocessed video data

[0235] Output: Analysis results (position, movement, and speed of vehicles and people)

[0236] Specific operation: The server uses a deep learning model (YOLO or TensorFlow) to detect vehicles and people from video data, track them, and calculate their speed and direction of travel.

[0237] Step 4:

[0238] The server evaluates the risk of traffic accidents based on the analysis results.

[0239] Input: Analysis results

[0240] Output: Risk assessment (risk score, risk pattern)

[0241] What it does: The server compares historical data with real-time analytics data, calculates a risk score using custom algorithms, and identifies risk patterns.

[0242] Step 5:

[0243] Based on the risk assessment results, the server sends notifications to the driver of the autonomous vehicle in real time and suggests specific safety measures.

[0244] Input: Risk assessment results

[0245] Output: Notifications and safety suggestions

[0246] Specific operation: The server uses Firebase Cloud Messaging to send push notifications to the driver's smartphone or in-vehicle system, suggesting specific countermeasures such as, "A vehicle running a red light has been detected. Please reduce your speed."

[0247] Step 6:

[0248] The server stores the analysis results and risk assessment results in a database and generates periodic reports.

[0249] Input: Analysis results, risk assessment results

[0250] Output: Data stored in database, generated reports

[0251] Specific operation: The server stores the analysis results and risk assessment results in an SQL database, generates monthly and weekly reports, and sends them to the administrator's terminal.

[0252] keyword

[0253] Generative AI model, prompt sentence

[0254] 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.

[0255] The present invention improves the accuracy of risk assessment by combining a system that uses a camera to collect video data around traffic lights, analyzes the risk of traffic accidents, and proposes countermeasures under specific conditions with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will be described in detail below.

[0256] System configuration

[0257] The system consists of the following main components:

[0258] 1. Camera

[0259] 2. Server

[0260] 3. Database

[0261] 4. Administrator terminal

[0262] 5. Emotion Engine

[0263] System Operation

[0264] Data collection

[0265] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[0266] Data Preprocessing

[0267] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data, improving the quality of the data and enabling more accurate subsequent analysis.

[0268] Movement and Emotion Analysis

[0269] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotional data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel, while also analyzing the user's facial expressions and voice to identify emotions such as stress and impatience.

[0270] Risk Assessment

[0271] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score by taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect outliers and identify risk patterns at specific times of day or at intersections. If the risk due to the user's emotional state is high, the server sends a notification to the administrator.

[0272] Notification and suggested solutions

[0273] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[0274] Data Storage and Reporting

[0275] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[0276] Specific examples

[0277] Example 1: Red light detection

[0278] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[0279] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[0280] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[0281] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[0282] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[0283] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[0284] Example 2: Risks from increased traffic and impatience

[0285] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[0286] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[0287] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[0288] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[0289] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[0290] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[0291] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures. In addition, by taking the user's emotional state into consideration, it is possible to provide more accurate risk assessments and countermeasures.

[0292] The processing flow will be explained below.

[0293] Step 1: Data collection

[0294] Subject: Server

[0295] The server obtains the IP addresses of the cameras and emotion engines installed at each traffic light.

[0296] The server sends a streaming request to the camera and receives video data in real time.

[0297] The server also sends a streaming request to the emotion engine and receives the user's emotion data in real time.

[0298] Step 2: Data Preprocessing

[0299] Subject: Server

[0300] The server applies a noise reduction algorithm to the received video data to improve the quality of the video.

[0301] The server adjusts the resolution and frame rate of the video data and converts it into a format suitable for analysis.

[0302] The server also performs noise removal on the received emotion data to improve the accuracy of emotional state recognition.

[0303] Step 3: Analyze vehicle and human movements

[0304] Subject: Server

[0305] The server applies machine learning models to detect vehicles and people from the pre-processed video data.

[0306] The server tracks the movement of detected vehicles and people and calculates their speed and direction of travel.

[0307] The server analyzes the traffic light status (red, green, yellow) and compares it with the movement of vehicles and people.

[0308] Step 4: Analyze the sentiment data

[0309] Subject: Server

[0310] The server analyzes the data received from the emotion engine to determine the user's emotional state.

[0311] The server classifies the user's emotional state into categories such as "impatience," "stress," and "anger" based on the user's facial expressions and voice.

[0312] The server evaluates the user's psychological state from the emotion data and analyzes its influence on traffic behavior.

[0313] Step 5: Risk assessment

[0314] Subject: Server

[0315] The server integrates the analysis results of vehicle and human movement with the analysis results of emotional data to comprehensively assess the risk of traffic accidents.

[0316] The server compares this data with past data to detect abnormal behavior and high-risk situations in real time.

[0317] The server calculates a risk score based on abnormal behavior and high-risk situations and sends the evaluation results to the administrator terminal.

[0318] Step 6: Notification and proposed action

[0319] Subject: Server

[0320] The server sends notification emails and alerts to administrators based on the assessed risk score.

[0321] The server references a past database and automatically suggests optimal countermeasures for similar risk scenarios.

[0322] The server will suggest specific countermeasures such as "changing the timing of traffic lights," "deploying police officers," and "sending warning messages to drivers."

[0323] Step 7: Data storage and reporting

[0324] Subject: Server

[0325] The server stores the analysis results and risk assessment results in a database.

[0326] The server will regularly back up data and store it safely.

[0327] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[0328] Specific examples

[0329] Example 1: Red light detection

[0330] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[0331] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[0332] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[0333] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[0334] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[0335] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[0336] Example 2: Risks from increased traffic and impatience

[0337] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[0338] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[0339] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[0340] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[0341] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[0342] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[0343] Example 2

[0344] 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."

[0345] Current traffic monitoring systems mainly assess risk based on the movements of vehicles and pedestrians, and few take into account the emotional state of drivers and pedestrians. Therefore, there is a need for more accurate traffic accident risk assessments that incorporate psychological factors of drivers and pedestrians, such as emotional stress and impatience, into the risk assessment. In addition, there is a need for systems that can quickly propose specific countermeasures, such as operating traffic lights and installing traffic signs.

[0346] 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.

[0347] In this invention, the server includes means for collecting video data near traffic lights using a camera and collecting user emotion data using an emotion engine, means for performing noise reduction and resolution adjustment on the collected video data and emotion data, and means for analyzing the movements of vehicles and people from the preprocessed video data and recognizing the user's emotional state from the emotion data. This enables traffic accident risk assessment that takes into account the psychological factors of drivers and pedestrians, and makes it possible to propose quick and specific countermeasures for high-risk situations.

[0348] A "camera" is a device for collecting video data around traffic lights.

[0349] An "emotion engine" is a software or hardware system for collecting and analyzing a user's emotional data.

[0350] "Server" refers to the computer system used to process, analyze, and store data collected from the camera and emotion engine.

[0351] "Noise removal" is a process of removing unnecessary noise from collected data to improve the quality of the data.

[0352] "Resolution adjustment" is a process of changing the resolution of data to an appropriate level.

[0353] "Analysis of vehicle and human movement" is a process of identifying and analyzing the position, movement, speed, etc. of vehicles and pedestrians from preprocessed video data.

[0354] "Recognizing the user's emotional state" is a process of determining the user's emotion (for example, stress, impatience, joy, sadness, etc.) from the emotion data.

[0355] "Assessing the risk of traffic accidents" is the process of calculating and assessing the possibility of a traffic accident occurring based on analyzed data.

[0356] A "risk score" is a numerical indicator of the risk level of a traffic accident.

[0357] "Notification" is the act of informing administrators of warnings and information based on the results of risk assessment.

[0358] "Proposing countermeasures" refers to the act of presenting specific guidelines for action and improvement measures to managers based on the results of risk assessment.

[0359] A "database" is a system for persistently storing collected and analyzed data.

[0360] "Generating a report" refers to the act of creating a document that summarizes the results of analysis and risk assessment based on the information stored in the database.

[0361] A "streaming request" is a request to obtain data in real time over a network.

[0362] "Traffic flow analysis" is the process of statistically analyzing traffic volume and vehicle movements to evaluate traffic conditions.

[0363] "Abnormal behavior" refers to behavior that is not normally expected or is dangerous (e.g., running red lights or dangerous driving).

[0364] In an embodiment of the present invention, a system is constructed using the following components: a camera, a server, a database, an administrator terminal, and an emotion engine. This section describes a system that uses these devices and software to collect, analyze, notify, and propose countermeasures for assessing the risk of traffic accidents.

[0365] System Components

[0366] 1. Camera: A high-resolution IP camera is used to collect video data around the traffic lights. For example, a general outdoor camera is used.

[0367] 2. Emotion engine: A system for collecting and analyzing emotional data, identifying emotions from the user's facial expressions, voice, etc. As a concrete example, a general emotion analysis engine is used.

[0368] 3. Server: A high-performance computer system that processes data. For example, a general-purpose server is used. The server collects, preprocesses, analyzes, assesses risk, and notifies data.

[0369] 4. Database: Stores the collected and analyzed data. For example, a typical relational database is used.

[0370] 5. Administrator terminal: A terminal that receives notifications and suggestions from the server and takes specific countermeasures. For example, a general-purpose tablet terminal or PC is used.

[0371] System Operation

[0372] Data collection

[0373] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[0374] Data Preprocessing

[0375] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data.The hardware and software used are a high-performance server and a general image processing library.

[0376] Movement and Emotion Analysis

[0377] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotion data, using common object detection technology and emotion analysis APIs.

[0378] Risk Assessment

[0379] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect abnormalities.

[0380] Notification and suggested solutions

[0381] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device, who receives a notification via the device and takes measures such as operating traffic lights or installing traffic signs.

[0382] Data Storage and Reporting

[0383] The server stores the analysis results and risk assessment results in a database. This allows the data to be backed up and stored safely. The data is periodically generated as reports and provided to relevant organizations.

[0384] Specific examples

[0385] Example 1: Red light violation detection

[0386] The server obtains video data of traffic light A and the driver's emotional data from the camera and emotion engine. It removes noise from the video data and adjusts the resolution. It also pre-processes the emotional data. The server uses object detection technology to detect when a vehicle has run a red light and confirms that the driver's emotional data indicates "impatience." It calculates a risk score based on the frequency of red light violations and the driver's emotional state, and proposes specific countermeasures to the administrator.

[0387] Example 2: Risks of increased traffic and rushing

[0388] The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B. The data is divided by time period and noise is removed. The server then performs traffic flow analysis and detects increases in traffic volume and driver emotion indicating "impatience." Based on the risk score, the server evaluates the accident risk during specific time periods and proposes specific countermeasures to the manager.

[0389] Prompt Sentence Examples

[0390] The system's program collects and analyzes video and emotion data to assess the risk of traffic accidents. Specifically, the server acquires and preprocesses data through the camera and emotion engine. It then uses object detection technology and emotion analysis APIs to analyze movements and emotions and calculate a risk score. Based on the results of the risk assessment, it sends notifications to administrators and suggests countermeasures. The analysis results are stored in a database and periodic reports are generated.

[0391] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0392] Step 1: Data collection

[0393] The server collects video data and user emotion data in real time through a camera installed near a traffic light and the emotion engine. Specifically, the server sends a streaming request to the camera's IP address and acquires video data at 30 frames per second. It also sends a similar request to the emotion engine to collect the user's facial expressions and voice data.

[0394] Input: Real-time data from camera and emotion engine

[0395] Output: Collected raw data (video data and emotion data)

[0396] Step 2: Data Preprocessing

[0397] The server performs noise reduction and resolution adjustment on the collected video and emotion data. Specifically, the server uses the OpenCV library to apply a Gaussian filter to the video data to remove noise. For emotion data, the server also cleans up the data using the emotion engine API.

[0398] Input: Raw data collected

[0399] Output: Preprocessed data (high-quality video data and clean emotion data)

[0400] Step 3: Movement and emotion analysis

[0401] The server analyzes the movement of vehicles and people in the preprocessed video data and recognizes the user's emotional state based on the emotional data. Specifically, the server uses YOLOv5 to detect vehicles and pedestrians, and a Kalman filter to track and calculate their speed. The server then uses Affectiva's API to determine the user's emotional state.

[0402] Input: Preprocessed data

[0403] Output: Analysis results (vehicle and human movement data, emotional state data)

[0404] Step 4: Risk assessment

[0405] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. The server compares past data with real-time data to detect abnormalities.

[0406] Input: Analysis results

[0407] Output: Risk assessment result (risk score)

[0408] Step 5: Notification and proposed action

[0409] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device. Specifically, if the risk score exceeds a set threshold, the server sends a push notification to the administrator's device and proposes countermeasures such as changing traffic light timing or installing traffic signs.

[0410] Input: Risk assessment results

[0411] Output: Notification and suggested action

[0412] Step 6: Data storage and reporting

[0413] The server stores the analysis and risk assessment results in a database. Specifically, the server records each data in a MySQL database. Furthermore, the server generates regular reports using the Python Pandas library and provides them to relevant organizations.

[0414] Input: Analysis results and risk assessment results

[0415] Output: Save to database and generate report

[0416] (Application example 2)

[0417] 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."

[0418] Conventional systems for assessing the risk of traffic accidents rely solely on traffic situation data, making it difficult to accurately assess risk. Furthermore, risk assessments are performed without taking into account the driver's emotional state, potentially overlooking risks caused by driver stress or impatience. This has resulted in insufficient traffic accident prevention measures, making it difficult to improve road safety.

[0419] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting video data near traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, means for assessing the risk of a traffic accident based on the analysis results, means for notifying an administrator and proposing countermeasures if the risk is high, means for saving the analysis results and risk assessment results in a database and generating a report, means for analyzing the driver's emotional state using an emotion engine and reflecting the results in a traffic accident risk assessment, and means for providing warnings and driving assistance information in real time using a smart device. This enables accurate risk assessment and prompt proposal of countermeasures that take the driver's emotional state into account.

[0420] A "camera" is an image capture device installed to collect video data near a traffic light.

[0421] The "server" is a central processing unit that processes and analyzes video data and emotion data, and performs risk assessments and proposes countermeasures.

[0422] A "database" is a data management system for storing analysis results and risk assessment results and generating reports.

[0423] The "administrator terminal" is a device equipped with a user interface that receives notifications of traffic risk assessments and proposed countermeasures, and enables the administrator to take countermeasures.

[0424] The "Emotion Engine" is an emotion recognition system that analyzes the driver's emotional state and uses it to assess the risk of traffic accidents.

[0425] "Noise removal" is a process that removes unnecessary signals and noise from collected video data and emotion data.

[0426] "Resolution adjustment" is an image processing technique for optimizing the image quality of collected video data.

[0427] "Analyzing vehicle and human movement" is the process of detecting the movement of traffic objects from pre-processed video data and calculating their tracking and speed.

[0428] "Risk assessment" is the process of quantifying and evaluating the risk of traffic accidents based on the results of analysis.

[0429] "Notification and suggestion of countermeasures" is a process of sending a warning to the administrator terminal when there is a high risk and suggesting an appropriate countermeasure.

[0430] "Smart devices" are advanced electronic devices designed to provide drivers with real-time warning and driving assistance information.

[0431] This invention is a system that uses a camera and an emotion engine to analyze the traffic conditions near traffic signals and the emotional state of the driver, and evaluate the risk of traffic accidents.The main components of this system are a camera, a server, a database, an administrator terminal, and an emotion engine.

[0432] The server receives video data from the camera device in real time, removes noise, and adjusts the resolution. It then analyzes the movement of vehicles and people from the preprocessed video data. This allows for tracking, speed calculations, and traffic conditions to be understood. The server also analyzes the driver's emotional state from their facial expressions and voice via an emotion engine, and reflects this in traffic accident risk assessments.

[0433] After the risk assessment is completed, if the risk is high, a notification is sent to the administrator's device and specific countermeasures are proposed. Based on this notification and proposal, the intersection administrator can take appropriate measures, such as adjusting traffic light timing or installing signs. The results of the countermeasures and analysis data are stored in a database and used for future improvements.

[0434] Additionally, smart devices (e.g., smart glasses) can provide drivers with real-time warnings and driving assistance information, allowing them to modify their driving behavior or relax, thereby reducing the risk of accidents.

[0435] As a specific example, if a camera detects a vehicle running a red light near a traffic light and the driver appears impatient, the server will assess the risk as high and suggest to the administrator's device that the timing of the traffic light be changed or a warning message be sent to the driver. The administrator can then take immediate action based on this. The driver will see a warning message on their smart device saying, "The light is red. Please be careful."

[0436] The specific hardware used includes a high-resolution IP camera for the camera device, a machine with high-performance computing power for the server, advanced emotion recognition software for the emotion engine, a large-capacity data management system for the database, and a computer capable of real-time display and operation for the administrator terminal.

[0437] The use of generative AI models is also recommended. For example, by entering a prompt such as "Build a system that detects traffic objects from video data and analyzes emotion data to assess high risk. Please also include a function to display appropriate relaxation and warning messages," the detailed structure and operation method of the invention can be obtained from the generative AI model.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1:

[0440] The camera collects video data around the traffic light. The camera is a high-resolution IP camera and sends a real-time streaming request to the server. The server takes the video data received from the camera as input and stores the data as video.

[0441] Step 2:

[0442] The server performs noise reduction and resolution adjustment on the collected video data. First, when the server receives the video data, it applies a noise reduction filter to clean up the data. Then it adjusts the resolution to ensure optimal quality for analysis. The output is pre-processed, high-quality video data.

[0443] Step 3:

[0444] The server analyzes the movement of vehicles and people from the pre-processed video data. The server receives the video data as input and uses object detection algorithms to detect vehicles and pedestrians. It then tracks the positions of these objects and calculates their speed and direction of travel. The server outputs the position, speed, and direction of travel data for vehicles and people.

[0445] Step 4:

[0446] The server uses an emotion engine to analyze the driver's emotional state. The server receives video captured by the camera and audio data from the microphone as input and applies an emotion recognition algorithm to extract emotional data (e.g., impatience, stress, etc.) from the driver's facial expressions and voice. The output is the driver's emotional state data.

[0447] Step 5:

[0448] The server assesses the risk of traffic accidents based on the analysis results. The server receives vehicle and pedestrian movement data, as well as the driver's emotional state data, as input and applies a risk assessment model. It compares historical data with real-time data, detects outliers, and calculates a risk score. The output is a traffic accident risk score.

[0449] Step 6:

[0450] If the risk is high, the server will notify the administrator's device and suggest countermeasures. Specifically, if the risk score is high, the server will send a warning message to the administrator's device and suggest specific countermeasures such as "changing traffic light timing" or "sending warning messages to drivers." The administrator's device will display these suggestions, allowing the administrator to take appropriate action.

[0451] Step 7:

[0452] The server stores the analysis results and risk assessment results in a database and generates reports. The server receives the risk assessment scores and analysis data as input documents and generates periodic reports, which are provided to traffic management authorities and other relevant organizations. A comprehensive analysis report is obtained as output.

[0453] Step 8:

[0454] The server provides real-time warnings and driver assistance information using smart devices. The server receives the risk assessment results as input and sends warning messages and driver assistance information to the driver's smart device, so that the driver can immediately pay attention and take appropriate driving actions. The server provides real-time warnings and assistance information to the driver as output.

[0455] 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.

[0456] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0457] 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.

[0458] [Second embodiment]

[0459] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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."

[0471] The present invention provides a system that uses a camera to collect video data around traffic lights, analyzes the data to assess the risk of traffic accidents, and proposes countermeasures under specific conditions. An embodiment of the present invention will now be described in detail.

[0472] System configuration

[0473] The system consists of the following main components:

[0474] 1. Camera

[0475] 2. Server

[0476] 3. Database

[0477] 4. Administrator terminal

[0478] System Operation

[0479] Data collection

[0480] The server collects video data in real time from cameras installed near traffic lights, which monitor traffic volume, vehicle and pedestrian movements, and transmits the video data to the server.

[0481] Data Preprocessing

[0482] The server performs noise reduction and resolution adjustment on the collected video data, improving the quality of the video data and ensuring accurate subsequent analysis.

[0483] Movement Analysis

[0484] The server analyzes the movement of vehicles and people in the pre-processed video data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel. It also analyzes the status of traffic lights (red, green, yellow).

[0485] Risk Assessment

[0486] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it compares the results with past data and identifies risk patterns at specific times and intersections. If the risk is high, the server sends a notification to the administrator.

[0487] Notification and suggested solutions

[0488] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[0489] Data Storage and Reporting

[0490] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[0491] Specific examples

[0492] Example 1: Red light detection

[0493] 1. Data collection: The server acquires video data of traffic light A from the camera.

[0494] 2. Data preprocessing: The server removes noise from the video data and adjusts the resolution.

[0495] 3. Analysis: The server detects that the vehicle ran a red light.

[0496] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations.

[0497] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the traffic light timing."

[0498] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[0499] Example 2: Risks from increased traffic

[0500] 1. Data collection: The server acquires video data from the camera at traffic light B during rush hour.

[0501] 2. Data preprocessing: The server divides the data into time periods and removes noise.

[0502] 3. Analysis: The server performs traffic flow analysis and detects increases in traffic volume.

[0503] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[0504] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs."

[0505] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[0506] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures.

[0507] The processing flow will be explained below.

[0508] Step 1: Data collection

[0509] Subject: Server

[0510] The server obtains the IP address of the camera installed at each traffic light.

[0511] The server sends a streaming request to the specified IP address.

[0512] The server receives and stores the video data sent from the camera in real time.

[0513] Step 2: Data Preprocessing

[0514] Subject: Server

[0515] The server applies a noise reduction algorithm to the received video data.

[0516] The server adjusts the resolution and frame rate of the video data.

[0517] The server segments the video data by time as needed and divides it into segments of a fixed length.

[0518] Step 3: Analyze vehicle and human movements

[0519] Subject: Server

[0520] The server detects vehicles from the video data using a pre-trained vehicle detection model.

[0521] The server tracks the movement of the detected vehicle and calculates its speed and direction of travel.

[0522] The server analyzes the traffic light status (red, green, yellow).

[0523] Step 4: Risk assessment

[0524] Subject: Server

[0525] The server saves the analysis results in a temporary data store.

[0526] The server compares historical data with real-time data to detect outliers.

[0527] The server identifies risk patterns at specific times and intersections and calculates a risk score.

[0528] Step 5: Notification and proposed action

[0529] Subject: Server

[0530] The server will send a notification email or SMS to the administrator based on the assessed risk score.

[0531] The server refers to a database of past countermeasures and automatically proposes the most appropriate countermeasure.

[0532] The server will propose specific countermeasures such as "changing traffic light timing," "adding traffic signs," and "deploying police officers."

[0533] Step 6: Data storage and reporting

[0534] Subject: Server

[0535] The server stores the analysis results and risk assessment results in a database.

[0536] The server will regularly back up your data and store it safely.

[0537] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[0538] Example 1

[0539] 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."

[0540] Traffic accidents are a serious problem worldwide, affecting many lives and assets. The risk of accidents is particularly high near intersections and traffic lights due to the high volume of traffic and complex pedestrian movements. Predicting accidents in these locations and taking appropriate countermeasures is also difficult. To solve these problems, a system that can monitor and analyze traffic conditions in real time is required.

[0541] 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.

[0542] In this invention, the server includes a means for collecting video data around traffic lights in real time using a camera, a means for performing noise reduction and resolution adjustment on the collected video data, and a means for analyzing the movements of vehicles and pedestrians from the preprocessed video data using an algorithm, which makes it possible to evaluate the risk of traffic accidents by comparing with past data and propose specific countermeasures under specific conditions.

[0543] The "camera" is a device that collects video data around traffic lights in real time.

[0544] The "server" is a central processing unit that receives the video data sent from the camera and performs various analytical processes.

[0545] "Video data" refers to continuous image data captured by a camera that shows the traffic and pedestrian conditions around a traffic light.

[0546] "Noise reduction" is a process that removes unnecessary noise from video data to improve its quality.

[0547] "Resolution adjustment" is a process of unifying the resolution (level of image detail) of video data to an appropriate level.

[0548] "Algorithm" refers to the procedures and calculation methods used to analyze vehicle and pedestrian movements from video data.

[0549] "Motion analysis" is the process of detecting the movement of vehicles and pedestrians from pre-processed video data and identifying their speed and direction of travel.

[0550] "Risk assessment" is the process of evaluating the risk of traffic accidents based on analysis results and comparing them with past data.

[0551] "Notification" is a means of communication to inform managers of the results of traffic accident risk assessments.

[0552] "Proposals for countermeasures" refer to specific measures, such as changing traffic light timing or installing additional road signs, when there is a high risk of traffic accidents.

[0553] A "database" is a data management system that safely stores analysis and risk assessment results for later reference.

[0554] A "report" is a document that summarizes the analysis results and risk assessment results that are generated periodically.

[0555] The present invention is a system that monitors traffic conditions around traffic signals in real time, assesses the risk of traffic accidents, and proposes countermeasures. The system consists of the following main components:

[0556] 1. Camera

[0557] 2. Server

[0558] 3. Database

[0559] 4. Administrator terminal

[0560] System Overview

[0561] Users install network-connected cameras at intersections and near traffic lights. The cameras capture images of traffic and pedestrians in real time and send the video data to a server. A typical example of such a camera is a commonly used network camera.

[0562] The server receives the video data sent from the camera and performs the following processes:

[0563] 1. Data preprocessing: Denoise using OpenCV library and adjust resolution with FFmpeg software.

[0564] 2. Movement analysis: Analyze the movement of vehicles and pedestrians using the YOLO (You Only Look Once) algorithm.

[0565] 3. Risk assessment: Using TensorFlow, we compare the data with past data to assess the risk of traffic accidents.

[0566] If the risk is high, the results of the assessment are sent to the administrator's terminal and specific countermeasures are proposed. The analysis results and risk assessment results are then stored in a database, and reports are generated periodically.

[0567] Specific examples

[0568] Data collection

[0569] The server collects real-time video data from a network camera near the traffic lights, such as an Axis Q1765-LE, and captures image frames every 30 seconds.

[0570] Data Preprocessing

[0571] The server uses the OpenCV library to remove noise from the video and uses FFmpeg to standardize the resolution to 1280x720 pixels.

[0572] Movement Analysis

[0573] The server uses the YOLO model to identify the positions of vehicles and pedestrians in each frame and calculates the change in position between each frame to calculate speed.

[0574] Risk Assessment

[0575] The server uses TensorFlow to model past data and compare it with current data to calculate a risk score.

[0576] Notification and suggested solutions

[0577] The server uses the Twilio API to send SMS and email notifications to the administrator's device. For example, if there are frequent cases of people running red lights, the server can suggest changing the timing of the traffic lights.

[0578] Data Storage and Reporting

[0579] The server stores the analysis and risk assessment results in a MySQL database and uses JasperReports to periodically generate reports and save them in PDF format.

[0580] Examples of prompt statements

[0581] "Please describe in detail a program that monitors traffic conditions in real time near traffic light A and evaluates the risk of traffic accidents."

[0582] The system of the present invention continuously monitors traffic conditions near traffic signals and can take appropriate countermeasures by detecting the risk of traffic accidents at an early stage, which is expected to improve traffic safety.

[0583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0584] Step 1: Data collection

[0585] The server collects video data around traffic lights from a network camera in real time. As input, it receives streaming video data from the network camera (e.g., Axis Q1765-LE). Specifically, the server sends a streaming request to the camera's IP address and stores the received video data in a temporary directory.

[0586] Input: Video data from a network camera

[0587] Output: Video data saved in temporary directory

[0588] Step 2: Data Preprocessing

[0589] The server performs noise reduction and resolution adjustment on the acquired video data. It receives the collected video data as input and uses the OpenCV library to remove noise. Then, it uses FFmpeg software to unify the resolution to 1280x720 pixels. This process ensures accurate subsequent analysis.

[0590] Input: Video data saved in the temporary directory

[0591] Output: High-quality pre-processed video data

[0592] Step 3: Analyze the movement

[0593] The server uses the preprocessed video data to analyze the movement of vehicles and pedestrians. It receives the preprocessed video data as input and uses the YOLO model to identify the positions of vehicles and pedestrians. It then calculates the change in position between frames and determines their speed and direction of travel.

[0594] Input: High-quality pre-processed video data

[0595] Output: Position, speed, and heading data of vehicles and pedestrians

[0596] Step 4: Risk assessment

[0597] The server evaluates the risk of traffic accidents based on the movement analysis results. It receives the analyzed location, speed, and direction of travel data as input, and uses TensorFlow to compare it with past data and calculate a risk score. This process evaluates the risk of traffic accidents under certain conditions.

[0598] Input: Vehicle and pedestrian position, speed, and heading data

[0599] Output: Risk score

[0600] Step 5: Notification and proposed action

[0601] Based on the results of the risk assessment, if the risk is high, the server sends a notification to the administrator's device and proposes specific countermeasures. It receives the calculated risk score as input and uses the Twilio API to notify the administrator via SMS or email. Suggested countermeasures include changing traffic light timings or installing additional road signs.

[0602] Input: Risk Score

[0603] Output: Notification to administrator and suggested action

[0604] Step 6: Data storage and reporting

[0605] The server stores the analysis and risk assessment results in a database and generates reports periodically. As input, it takes the analysis and risk assessment results and stores them in a MySQL database. It then uses JasperReports to generate monthly or weekly reports and saves them in PDF format.

[0606] Input: Analysis results and risk assessment results

[0607] Output: Data stored in database, generated reports

[0608] (Application example 1)

[0609] 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."

[0610] In modern society, as autonomous vehicles become more widespread, there is a need to detect traffic accident risks early and implement appropriate countermeasures. However, conventional systems do not accurately assess the risk of traffic accidents and often only respond after an accident has occurred. In addition, drivers cannot receive risk information in real time, which can result in delayed preventive measures. To solve these issues, a system is needed that can monitor traffic conditions with high accuracy and assess and notify risks in real time.

[0611] 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.

[0612] In this invention, the server includes means for collecting video data around traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, and means for sending a real-time notification to the driver of the autonomous vehicle based on the analysis results and proposing specific safety measures, thereby enabling the driver of the autonomous vehicle to grasp the risk of a traffic accident early and take appropriate preventive measures.

[0613] A "camera" is a photographing device for collecting video data around a traffic light.

[0614] "Noise reduction" is a process that removes unnecessary information from collected video data to improve the quality of the data.

[0615] "Resolution adjustment" is a process that optimizes the image quality and size of collected video data to enhance the details.

[0616] "Motion analysis" is a technology that recognizes and analyzes the movements of vehicles and people from pre-processed video data.

[0617] "Assessing the risk of traffic accidents" is the process of calculating the probability of an accident occurring in a specific traffic situation based on the results of motion analysis.

[0618] "Sending notifications in real time" means instantly delivering the analysis results to the driver of the autonomous vehicle.

[0619] "Proposing specific safety measures" means advising drivers on specific actions and measures to take in response to assessed risks.

[0620] A "database" is an information management system that stores analysis results and risk assessment results so that they can be referenced later.

[0621] "Report generation" is the process of organizing the analysis results and risk assessment results and outputting them in an easy-to-read format.

[0622] This invention is a system that monitors traffic conditions near traffic signals in real time, assesses the risk of traffic accidents, and notifies drivers of autonomous vehicles, enabling them to take appropriate countermeasures quickly.

[0623] System configuration

[0624] The system consists of the following main components:

[0625] 1. Camera

[0626] It is installed near traffic lights and collects video data on traffic conditions.

[0627] 2. Server

[0628] Receives video data and performs various data processing and analysis.

[0629] 3. Database

[0630] Store the analysis and risk assessment results and generate reports.

[0631] 4. Administrator terminal

[0632] A device that lets you receive real-time notifications and identify the best course of action.

[0633] How to carry out the invention

[0634] Data collection

[0635] The system's camera collects video data around traffic lights in real time and sends it to a server. The hardware used is a built-in camera in a smartphone or a dedicated surveillance camera, and the communication protocol is HTTP / HTTPS.

[0636] Data Preprocessing

[0637] The server performs noise reduction and resolution adjustment on the received video data. The software used here is the OpenCV library, which improves the video quality.

[0638] Movement Analysis

[0639] The pre-processed video data is then used to apply deep learning models (e.g., YOLO or TensorFlow) to analyze vehicle and pedestrian movements, which allows for vehicle detection, tracking, and speed calculation.

[0640] Risk Assessment

[0641] The server assesses the risk of traffic accidents based on the results of the motion analysis, using a custom algorithm that compares the results with past data patterns, and sends a real-time notification to the administrator's device if the risk is high.

[0642] Notification and suggested solutions

[0643] The server sends real-time notifications to the driver of the autonomous vehicle and suggests specific safety measures, using software such as Firebase Cloud Messaging.

[0644] Data Storage and Reporting

[0645] The analysis and risk assessment results are stored in a database and periodically generated as reports, enabling long-term data management and backup.

[0646] Specific examples

[0647] While the driver is driving in autonomous mode, the system detects vehicles running red lights and sends a notification when the light changes, encouraging safe driving. The notification sent to the driver includes specific instructions such as, "A vehicle running a red light has been detected ahead. Please reduce your speed."

[0648] Example prompts to input to the generative AI model

[0649] "Analyze video data around traffic lights to assess the risk of traffic accidents. Detect vehicles running red lights and send real-time notifications to the driver of autonomous vehicles."

[0650] The present invention provides a powerful means for drivers of autonomous vehicles to instantly grasp traffic conditions and minimize the risk of accidents.

[0651] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0652] Step 1:

[0653] The camera collects video data around the traffic light.

[0654] Input: Real-time video around the traffic light

[0655] Output: Collected video data

[0656] Specific operation: The camera continuously captures video around the traffic light and sends it to the server.

[0657] Step 2:

[0658] The server performs noise reduction and resolution adjustment on the video data.

[0659] Input: Collected video data

[0660] Output: Pre-processed video data

[0661] Specific operation: The server uses the OpenCV library to remove noise from the data and adjust the resolution to improve image quality.

[0662] Step 3:

[0663] The server analyzes the movement of vehicles and people from the pre-processed video data.

[0664] Input: Preprocessed video data

[0665] Output: Analysis results (position, movement, and speed of vehicles and people)

[0666] Specific operation: The server uses a deep learning model (YOLO or TensorFlow) to detect vehicles and people from video data, track them, and calculate their speed and direction of travel.

[0667] Step 4:

[0668] The server evaluates the risk of traffic accidents based on the analysis results.

[0669] Input: Analysis results

[0670] Output: Risk assessment (risk score, risk pattern)

[0671] What it does: The server compares historical data with real-time analytics data, calculates a risk score using custom algorithms, and identifies risk patterns.

[0672] Step 5:

[0673] Based on the risk assessment results, the server sends notifications to the driver of the autonomous vehicle in real time and suggests specific safety measures.

[0674] Input: Risk assessment results

[0675] Output: Notifications and safety suggestions

[0676] Specific operation: The server uses Firebase Cloud Messaging to send push notifications to the driver's smartphone or in-vehicle system, suggesting specific countermeasures such as, "A vehicle running a red light has been detected. Please reduce your speed."

[0677] Step 6:

[0678] The server stores the analysis results and risk assessment results in a database and generates periodic reports.

[0679] Input: Analysis results, risk assessment results

[0680] Output: Data stored in database, generated reports

[0681] Specific operation: The server stores the analysis results and risk assessment results in an SQL database, generates monthly and weekly reports, and sends them to the administrator's terminal.

[0682] keyword

[0683] Generative AI model, prompt sentence

[0684] 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.

[0685] The present invention improves the accuracy of risk assessment by combining a system that uses a camera to collect video data around traffic lights, analyzes the risk of traffic accidents, and proposes countermeasures under specific conditions with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will be described in detail below.

[0686] System configuration

[0687] The system consists of the following main components:

[0688] 1. Camera

[0689] 2. Server

[0690] 3. Database

[0691] 4. Administrator terminal

[0692] 5. Emotion Engine

[0693] System Operation

[0694] Data collection

[0695] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[0696] Data Preprocessing

[0697] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data, improving the quality of the data and enabling more accurate subsequent analysis.

[0698] Movement and Emotion Analysis

[0699] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotional data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel, while also analyzing the user's facial expressions and voice to identify emotions such as stress and impatience.

[0700] Risk Assessment

[0701] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score by taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect outliers and identify risk patterns at specific times of day or at intersections. If the risk due to the user's emotional state is high, the server sends a notification to the administrator.

[0702] Notification and suggested solutions

[0703] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[0704] Data Storage and Reporting

[0705] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[0706] Specific examples

[0707] Example 1: Red light detection

[0708] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[0709] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[0710] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[0711] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[0712] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[0713] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[0714] Example 2: Risks from increased traffic and impatience

[0715] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[0716] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[0717] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[0718] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[0719] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[0720] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[0721] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures. In addition, by taking the user's emotional state into consideration, it is possible to provide more accurate risk assessments and countermeasures.

[0722] The processing flow will be explained below.

[0723] Step 1: Data collection

[0724] Subject: Server

[0725] The server obtains the IP addresses of the cameras and emotion engines installed at each traffic light.

[0726] The server sends a streaming request to the camera and receives video data in real time.

[0727] The server also sends a streaming request to the emotion engine and receives the user's emotion data in real time.

[0728] Step 2: Data Preprocessing

[0729] Subject: Server

[0730] The server applies a noise reduction algorithm to the received video data to improve the quality of the video.

[0731] The server adjusts the resolution and frame rate of the video data and converts it into a format suitable for analysis.

[0732] The server also performs noise removal on the received emotion data to improve the accuracy of emotional state recognition.

[0733] Step 3: Analyze vehicle and human movements

[0734] Subject: Server

[0735] The server applies machine learning models to detect vehicles and people from the pre-processed video data.

[0736] The server tracks the movement of detected vehicles and people and calculates their speed and direction of travel.

[0737] The server analyzes the traffic light status (red, green, yellow) and compares it with the movement of vehicles and people.

[0738] Step 4: Analyze the sentiment data

[0739] Subject: Server

[0740] The server analyzes the data received from the emotion engine to determine the user's emotional state.

[0741] The server classifies the user's emotional state into categories such as "impatience," "stress," and "anger" based on the user's facial expressions and voice.

[0742] The server evaluates the user's psychological state from the emotion data and analyzes its influence on traffic behavior.

[0743] Step 5: Risk assessment

[0744] Subject: Server

[0745] The server integrates the analysis results of vehicle and human movement with the analysis results of emotional data to comprehensively assess the risk of traffic accidents.

[0746] The server compares this data with past data to detect abnormal behavior and high-risk situations in real time.

[0747] The server calculates a risk score based on abnormal behavior and high-risk situations and sends the evaluation results to the administrator terminal.

[0748] Step 6: Notification and proposed action

[0749] Subject: Server

[0750] The server sends notification emails and alerts to administrators based on the assessed risk score.

[0751] The server references a past database and automatically suggests optimal countermeasures for similar risk scenarios.

[0752] The server will suggest specific countermeasures such as "changing the timing of traffic lights," "deploying police officers," and "sending warning messages to drivers."

[0753] Step 7: Data storage and reporting

[0754] Subject: Server

[0755] The server stores the analysis results and risk assessment results in a database.

[0756] The server will regularly back up data and store it safely.

[0757] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[0758] Specific examples

[0759] Example 1: Red light detection

[0760] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[0761] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[0762] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[0763] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[0764] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[0765] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[0766] Example 2: Risks from increased traffic and impatience

[0767] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[0768] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[0769] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[0770] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[0771] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[0772] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[0773] Example 2

[0774] 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."

[0775] Current traffic monitoring systems mainly assess risk based on the movements of vehicles and pedestrians, and few take into account the emotional state of drivers and pedestrians. Therefore, there is a need for more accurate traffic accident risk assessments that incorporate psychological factors of drivers and pedestrians, such as emotional stress and impatience, into the risk assessment. In addition, there is a need for systems that can quickly propose specific countermeasures, such as operating traffic lights and installing traffic signs.

[0776] 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.

[0777] In this invention, the server includes means for collecting video data near traffic lights using a camera and collecting user emotion data using an emotion engine, means for performing noise reduction and resolution adjustment on the collected video data and emotion data, and means for analyzing the movements of vehicles and people from the preprocessed video data and recognizing the user's emotional state from the emotion data. This enables traffic accident risk assessment that takes into account the psychological factors of drivers and pedestrians, and makes it possible to propose quick and specific countermeasures for high-risk situations.

[0778] A "camera" is a device for collecting video data around traffic lights.

[0779] An "emotion engine" is a software or hardware system for collecting and analyzing a user's emotional data.

[0780] "Server" refers to the computer system used to process, analyze, and store data collected from the camera and emotion engine.

[0781] "Noise removal" is a process of removing unnecessary noise from collected data to improve the quality of the data.

[0782] "Resolution adjustment" is a process of changing the resolution of data to an appropriate level.

[0783] "Analysis of vehicle and human movement" is a process of identifying and analyzing the position, movement, speed, etc. of vehicles and pedestrians from preprocessed video data.

[0784] "Recognizing the user's emotional state" is a process of determining the user's emotion (for example, stress, impatience, joy, sadness, etc.) from the emotion data.

[0785] "Assessing the risk of traffic accidents" is the process of calculating and assessing the possibility of a traffic accident occurring based on analyzed data.

[0786] A "risk score" is a numerical indicator of the risk level of a traffic accident.

[0787] "Notification" is the act of informing administrators of warnings and information based on the results of risk assessment.

[0788] "Proposing countermeasures" refers to the act of presenting specific guidelines for action and improvement measures to managers based on the results of risk assessment.

[0789] A "database" is a system for persistently storing collected and analyzed data.

[0790] "Generating a report" refers to the act of creating a document that summarizes the results of analysis and risk assessment based on the information stored in the database.

[0791] A "streaming request" is a request to obtain data in real time over a network.

[0792] "Traffic flow analysis" is the process of statistically analyzing traffic volume and vehicle movements to evaluate traffic conditions.

[0793] "Abnormal behavior" refers to behavior that is not normally expected or is dangerous (e.g., running red lights or dangerous driving).

[0794] In an embodiment of the present invention, a system is constructed using the following components: a camera, a server, a database, an administrator terminal, and an emotion engine. This section describes a system that uses these devices and software to collect, analyze, notify, and propose countermeasures for assessing the risk of traffic accidents.

[0795] System Components

[0796] 1. Camera: A high-resolution IP camera is used to collect video data around the traffic lights. For example, a general outdoor camera is used.

[0797] 2. Emotion engine: A system for collecting and analyzing emotional data, identifying emotions from the user's facial expressions, voice, etc. As a concrete example, a general emotion analysis engine is used.

[0798] 3. Server: A high-performance computer system that processes data. For example, a general-purpose server is used. The server collects, preprocesses, analyzes, assesses risk, and notifies data.

[0799] 4. Database: Stores the collected and analyzed data. For example, a typical relational database is used.

[0800] 5. Administrator terminal: A terminal that receives notifications and suggestions from the server and takes specific countermeasures. For example, a general-purpose tablet terminal or PC is used.

[0801] System Operation

[0802] Data collection

[0803] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[0804] Data Preprocessing

[0805] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data.The hardware and software used are a high-performance server and a general image processing library.

[0806] Movement and Emotion Analysis

[0807] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotion data, using common object detection technology and emotion analysis APIs.

[0808] Risk Assessment

[0809] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect abnormalities.

[0810] Notification and suggested solutions

[0811] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device, who receives a notification via the device and takes measures such as operating traffic lights or installing traffic signs.

[0812] Data Storage and Reporting

[0813] The server stores the analysis results and risk assessment results in a database. This allows the data to be backed up and stored safely. The data is periodically generated as reports and provided to relevant organizations.

[0814] Specific examples

[0815] Example 1: Red light violation detection

[0816] The server obtains video data of traffic light A and the driver's emotional data from the camera and emotion engine. It removes noise from the video data and adjusts the resolution. It also pre-processes the emotional data. The server uses object detection technology to detect when a vehicle has run a red light and confirms that the driver's emotional data indicates "impatience." It calculates a risk score based on the frequency of red light violations and the driver's emotional state, and proposes specific countermeasures to the administrator.

[0817] Example 2: Risks of increased traffic and rushing

[0818] The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B. The data is divided by time period and noise is removed. The server then performs traffic flow analysis and detects increases in traffic volume and driver emotion indicating "impatience." Based on the risk score, the server evaluates the accident risk during specific time periods and proposes specific countermeasures to the manager.

[0819] Prompt Sentence Examples

[0820] The system's program collects and analyzes video and emotion data to assess the risk of traffic accidents. Specifically, the server acquires and preprocesses data through the camera and emotion engine. It then uses object detection technology and emotion analysis APIs to analyze movements and emotions and calculate a risk score. Based on the results of the risk assessment, it sends notifications to administrators and suggests countermeasures. The analysis results are stored in a database and periodic reports are generated.

[0821] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0822] Step 1: Data collection

[0823] The server collects video data and user emotion data in real time through a camera installed near a traffic light and the emotion engine. Specifically, the server sends a streaming request to the camera's IP address and acquires video data at 30 frames per second. It also sends a similar request to the emotion engine to collect the user's facial expressions and voice data.

[0824] Input: Real-time data from camera and emotion engine

[0825] Output: Collected raw data (video data and emotion data)

[0826] Step 2: Data Preprocessing

[0827] The server performs noise reduction and resolution adjustment on the collected video and emotion data. Specifically, the server uses the OpenCV library to apply a Gaussian filter to the video data to remove noise. For emotion data, the server also cleans up the data using the emotion engine API.

[0828] Input: Raw data collected

[0829] Output: Preprocessed data (high-quality video data and clean emotion data)

[0830] Step 3: Movement and emotion analysis

[0831] The server analyzes the movement of vehicles and people in the preprocessed video data and recognizes the user's emotional state based on the emotional data. Specifically, the server uses YOLOv5 to detect vehicles and pedestrians, and a Kalman filter to track and calculate their speed. The server then uses Affectiva's API to determine the user's emotional state.

[0832] Input: Preprocessed data

[0833] Output: Analysis results (vehicle and human movement data, emotional state data)

[0834] Step 4: Risk assessment

[0835] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. The server compares past data with real-time data to detect abnormalities.

[0836] Input: Analysis results

[0837] Output: Risk assessment result (risk score)

[0838] Step 5: Notification and proposed action

[0839] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device. Specifically, if the risk score exceeds a set threshold, the server sends a push notification to the administrator's device and proposes countermeasures such as changing traffic light timing or installing traffic signs.

[0840] Input: Risk assessment results

[0841] Output: Notification and suggested action

[0842] Step 6: Data storage and reporting

[0843] The server stores the analysis and risk assessment results in a database. Specifically, the server records each data in a MySQL database. Furthermore, the server generates regular reports using the Python Pandas library and provides them to relevant organizations.

[0844] Input: Analysis results and risk assessment results

[0845] Output: Save to database and generate report

[0846] (Application example 2)

[0847] 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."

[0848] Conventional systems for assessing the risk of traffic accidents rely solely on traffic situation data, making it difficult to accurately assess risk. Furthermore, risk assessments are performed without taking into account the driver's emotional state, potentially overlooking risks caused by driver stress or impatience. This has resulted in insufficient traffic accident prevention measures, making it difficult to improve road safety.

[0849] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting video data near traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, means for assessing the risk of a traffic accident based on the analysis results, means for notifying an administrator and proposing countermeasures if the risk is high, means for saving the analysis results and risk assessment results in a database and generating a report, means for analyzing the driver's emotional state using an emotion engine and reflecting the results in a traffic accident risk assessment, and means for providing warnings and driving assistance information in real time using a smart device. This enables accurate risk assessment and prompt proposal of countermeasures that take the driver's emotional state into account.

[0850] A "camera" is an image capture device installed to collect video data near a traffic light.

[0851] The "server" is a central processing unit that processes and analyzes video data and emotion data, and performs risk assessments and proposes countermeasures.

[0852] A "database" is a data management system for storing analysis results and risk assessment results and generating reports.

[0853] The "administrator terminal" is a device equipped with a user interface that receives notifications of traffic risk assessments and proposed countermeasures, and enables the administrator to take countermeasures.

[0854] The "Emotion Engine" is an emotion recognition system that analyzes the driver's emotional state and uses it to assess the risk of traffic accidents.

[0855] "Noise removal" is a process that removes unnecessary signals and noise from collected video data and emotion data.

[0856] "Resolution adjustment" is an image processing technique for optimizing the image quality of collected video data.

[0857] "Analyzing vehicle and human movement" is the process of detecting the movement of traffic objects from pre-processed video data and calculating their tracking and speed.

[0858] "Risk assessment" is the process of quantifying and evaluating the risk of traffic accidents based on the results of analysis.

[0859] "Notification and suggestion of countermeasures" is a process of sending a warning to the administrator terminal when there is a high risk and suggesting an appropriate countermeasure.

[0860] "Smart devices" are advanced electronic devices designed to provide drivers with real-time warning and driving assistance information.

[0861] This invention is a system that uses a camera and an emotion engine to analyze the traffic conditions near traffic signals and the emotional state of the driver, and evaluate the risk of traffic accidents.The main components of this system are a camera, a server, a database, an administrator terminal, and an emotion engine.

[0862] The server receives video data from the camera device in real time, removes noise, and adjusts the resolution. It then analyzes the movement of vehicles and people from the preprocessed video data. This allows for tracking, speed calculations, and traffic conditions to be understood. The server also analyzes the driver's emotional state from their facial expressions and voice via an emotion engine, and reflects this in traffic accident risk assessments.

[0863] After the risk assessment is completed, if the risk is high, a notification is sent to the administrator's device and specific countermeasures are proposed. Based on this notification and proposal, the intersection administrator can take appropriate measures, such as adjusting traffic light timing or installing signs. The results of the countermeasures and analysis data are stored in a database and used for future improvements.

[0864] Additionally, smart devices (e.g., smart glasses) can provide drivers with real-time warnings and driving assistance information, allowing them to modify their driving behavior or relax, thereby reducing the risk of accidents.

[0865] As a specific example, if a camera detects a vehicle running a red light near a traffic light and the driver appears impatient, the server will assess the risk as high and suggest to the administrator's device that the timing of the traffic light be changed or a warning message be sent to the driver. The administrator can then take immediate action based on this. The driver will see a warning message on their smart device saying, "The light is red. Please be careful."

[0866] The specific hardware used includes a high-resolution IP camera for the camera device, a machine with high-performance computing power for the server, advanced emotion recognition software for the emotion engine, a large-capacity data management system for the database, and a computer capable of real-time display and operation for the administrator terminal.

[0867] The use of generative AI models is also recommended. For example, by entering a prompt such as "Build a system that detects traffic objects from video data and analyzes emotion data to assess high risk. Please also include a function to display appropriate relaxation and warning messages," the detailed structure and operation method of the invention can be obtained from the generative AI model.

[0868] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0869] Step 1:

[0870] The camera collects video data around the traffic light. The camera is a high-resolution IP camera and sends a real-time streaming request to the server. The server takes the video data received from the camera as input and stores the data as video.

[0871] Step 2:

[0872] The server performs noise reduction and resolution adjustment on the collected video data. First, when the server receives the video data, it applies a noise reduction filter to clean up the data. Then it adjusts the resolution to ensure optimal quality for analysis. The output is pre-processed, high-quality video data.

[0873] Step 3:

[0874] The server analyzes the movement of vehicles and people from the pre-processed video data. The server receives the video data as input and uses object detection algorithms to detect vehicles and pedestrians. It then tracks the positions of these objects and calculates their speed and direction of travel. The server outputs the position, speed, and direction of travel data for vehicles and people.

[0875] Step 4:

[0876] The server uses an emotion engine to analyze the driver's emotional state. The server receives video captured by the camera and audio data from the microphone as input and applies an emotion recognition algorithm to extract emotional data (e.g., impatience, stress, etc.) from the driver's facial expressions and voice. The output is the driver's emotional state data.

[0877] Step 5:

[0878] The server assesses the risk of traffic accidents based on the analysis results. The server receives vehicle and pedestrian movement data, as well as the driver's emotional state data, as input and applies a risk assessment model. It compares historical data with real-time data, detects outliers, and calculates a risk score. The output is a traffic accident risk score.

[0879] Step 6:

[0880] If the risk is high, the server will notify the administrator's device and suggest countermeasures. Specifically, if the risk score is high, the server will send a warning message to the administrator's device and suggest specific countermeasures such as "changing traffic light timing" or "sending warning messages to drivers." The administrator's device will display these suggestions, allowing the administrator to take appropriate action.

[0881] Step 7:

[0882] The server stores the analysis results and risk assessment results in a database and generates reports. The server receives the risk assessment scores and analysis data as input documents and generates periodic reports, which are provided to traffic management authorities and other relevant organizations. A comprehensive analysis report is obtained as output.

[0883] Step 8:

[0884] The server provides real-time warnings and driver assistance information using smart devices. The server receives the risk assessment results as input and sends warning messages and driver assistance information to the driver's smart device, so that the driver can immediately pay attention and take appropriate driving actions. The server provides real-time warnings and assistance information to the driver as output.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] [Third embodiment]

[0889] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0890] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0891] 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).

[0892] 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.

[0893] 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.

[0894] 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).

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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."

[0901] The present invention provides a system that uses a camera to collect video data around traffic lights, analyzes the data to assess the risk of traffic accidents, and proposes countermeasures under specific conditions. An embodiment of the present invention will now be described in detail.

[0902] System configuration

[0903] The system consists of the following main components:

[0904] 1. Camera

[0905] 2. Server

[0906] 3. Database

[0907] 4. Administrator terminal

[0908] System Operation

[0909] Data collection

[0910] The server collects video data in real time from cameras installed near traffic lights, which monitor traffic volume, vehicle and pedestrian movements, and transmits the video data to the server.

[0911] Data Preprocessing

[0912] The server performs noise reduction and resolution adjustment on the collected video data, improving the quality of the video data and ensuring accurate subsequent analysis.

[0913] Movement Analysis

[0914] The server analyzes the movement of vehicles and people in the pre-processed video data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel. It also analyzes the status of traffic lights (red, green, yellow).

[0915] Risk Assessment

[0916] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it compares the results with past data and identifies risk patterns at specific times and intersections. If the risk is high, the server sends a notification to the administrator.

[0917] Notification and suggested solutions

[0918] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[0919] Data Storage and Reporting

[0920] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[0921] Specific examples

[0922] Example 1: Red light detection

[0923] 1. Data collection: The server acquires video data of traffic light A from the camera.

[0924] 2. Data preprocessing: The server removes noise from the video data and adjusts the resolution.

[0925] 3. Analysis: The server detects that the vehicle ran a red light.

[0926] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations.

[0927] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the traffic light timing."

[0928] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[0929] Example 2: Risks from increased traffic

[0930] 1. Data collection: The server acquires video data from the camera at traffic light B during rush hour.

[0931] 2. Data preprocessing: The server divides the data into time periods and removes noise.

[0932] 3. Analysis: The server performs traffic flow analysis and detects increases in traffic volume.

[0933] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[0934] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs."

[0935] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[0936] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures.

[0937] The processing flow will be explained below.

[0938] Step 1: Data collection

[0939] Subject: Server

[0940] The server obtains the IP address of the camera installed at each traffic light.

[0941] The server sends a streaming request to the specified IP address.

[0942] The server receives and stores the video data sent from the camera in real time.

[0943] Step 2: Data Preprocessing

[0944] Subject: Server

[0945] The server applies a noise reduction algorithm to the received video data.

[0946] The server adjusts the resolution and frame rate of the video data.

[0947] The server segments the video data by time as needed and divides it into segments of a fixed length.

[0948] Step 3: Analyze vehicle and human movements

[0949] Subject: Server

[0950] The server detects vehicles from the video data using a pre-trained vehicle detection model.

[0951] The server tracks the movement of the detected vehicle and calculates its speed and direction of travel.

[0952] The server analyzes the traffic light status (red, green, yellow).

[0953] Step 4: Risk assessment

[0954] Subject: Server

[0955] The server saves the analysis results in a temporary data store.

[0956] The server compares historical data with real-time data to detect outliers.

[0957] The server identifies risk patterns at specific times and intersections and calculates a risk score.

[0958] Step 5: Notification and proposed action

[0959] Subject: Server

[0960] The server will send a notification email or SMS to the administrator based on the assessed risk score.

[0961] The server refers to a database of past countermeasures and automatically proposes the most appropriate countermeasure.

[0962] The server will propose specific countermeasures such as "changing traffic light timing," "adding traffic signs," and "deploying police officers."

[0963] Step 6: Data storage and reporting

[0964] Subject: Server

[0965] The server stores the analysis results and risk assessment results in a database.

[0966] The server will regularly back up your data and store it safely.

[0967] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[0968] Example 1

[0969] 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."

[0970] Traffic accidents are a serious problem worldwide, affecting many lives and assets. The risk of accidents is particularly high near intersections and traffic lights due to the high volume of traffic and complex pedestrian movements. Predicting accidents in these locations and taking appropriate countermeasures is also difficult. To solve these problems, a system that can monitor and analyze traffic conditions in real time is required.

[0971] 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.

[0972] In this invention, the server includes a means for collecting video data around traffic lights in real time using a camera, a means for performing noise reduction and resolution adjustment on the collected video data, and a means for analyzing the movements of vehicles and pedestrians from the preprocessed video data using an algorithm, which makes it possible to evaluate the risk of traffic accidents by comparing with past data and propose specific countermeasures under specific conditions.

[0973] The "camera" is a device that collects video data around traffic lights in real time.

[0974] The "server" is a central processing unit that receives the video data sent from the camera and performs various analytical processes.

[0975] "Video data" refers to continuous image data captured by a camera that shows the traffic and pedestrian conditions around a traffic light.

[0976] "Noise reduction" is a process that removes unnecessary noise from video data to improve its quality.

[0977] "Resolution adjustment" is a process of unifying the resolution (level of image detail) of video data to an appropriate level.

[0978] "Algorithm" refers to the procedures and calculation methods used to analyze vehicle and pedestrian movements from video data.

[0979] "Motion analysis" is the process of detecting the movement of vehicles and pedestrians from pre-processed video data and identifying their speed and direction of travel.

[0980] "Risk assessment" is the process of evaluating the risk of traffic accidents based on analysis results and comparing them with past data.

[0981] "Notification" is a means of communication to inform managers of the results of traffic accident risk assessments.

[0982] "Proposals for countermeasures" refer to specific measures, such as changing traffic light timing or installing additional road signs, when there is a high risk of traffic accidents.

[0983] A "database" is a data management system that safely stores analysis and risk assessment results for later reference.

[0984] A "report" is a document that summarizes the analysis results and risk assessment results that are generated periodically.

[0985] The present invention is a system that monitors traffic conditions around traffic signals in real time, assesses the risk of traffic accidents, and proposes countermeasures. The system consists of the following main components:

[0986] 1. Camera

[0987] 2. Server

[0988] 3. Database

[0989] 4. Administrator terminal

[0990] System Overview

[0991] Users install network-connected cameras at intersections and near traffic lights. The cameras capture images of traffic and pedestrians in real time and send the video data to a server. A typical example of such a camera is a commonly used network camera.

[0992] The server receives the video data sent from the camera and performs the following processes:

[0993] 1. Data preprocessing: Denoise using OpenCV library and adjust resolution with FFmpeg software.

[0994] 2. Movement analysis: Analyze the movement of vehicles and pedestrians using the YOLO (You Only Look Once) algorithm.

[0995] 3. Risk assessment: Using TensorFlow, we compare the data with past data to assess the risk of traffic accidents.

[0996] If the risk is high, the results of the assessment are sent to the administrator's terminal and specific countermeasures are proposed. The analysis results and risk assessment results are then stored in a database, and reports are generated periodically.

[0997] Specific examples

[0998] Data collection

[0999] The server collects real-time video data from a network camera near the traffic lights, such as an Axis Q1765-LE, and captures image frames every 30 seconds.

[1000] Data Preprocessing

[1001] The server uses the OpenCV library to remove noise from the video and uses FFmpeg to standardize the resolution to 1280x720 pixels.

[1002] Movement Analysis

[1003] The server uses the YOLO model to identify the positions of vehicles and pedestrians in each frame and calculates the change in position between each frame to calculate speed.

[1004] Risk Assessment

[1005] The server uses TensorFlow to model past data and compare it with current data to calculate a risk score.

[1006] Notification and suggested solutions

[1007] The server uses the Twilio API to send SMS and email notifications to the administrator's device. For example, if there are frequent cases of people running red lights, the server can suggest changing the timing of the traffic lights.

[1008] Data Storage and Reporting

[1009] The server stores the analysis and risk assessment results in a MySQL database and uses JasperReports to periodically generate reports and save them in PDF format.

[1010] Examples of prompt statements

[1011] "Please describe in detail a program that monitors traffic conditions in real time near traffic light A and evaluates the risk of traffic accidents."

[1012] The system of the present invention continuously monitors traffic conditions near traffic signals and can take appropriate countermeasures by detecting the risk of traffic accidents at an early stage, which is expected to improve traffic safety.

[1013] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1014] Step 1: Data collection

[1015] The server collects video data around traffic lights from a network camera in real time. As input, it receives streaming video data from the network camera (e.g., Axis Q1765-LE). Specifically, the server sends a streaming request to the camera's IP address and stores the received video data in a temporary directory.

[1016] Input: Video data from a network camera

[1017] Output: Video data saved in temporary directory

[1018] Step 2: Data Preprocessing

[1019] The server performs noise reduction and resolution adjustment on the acquired video data. It receives the collected video data as input and uses the OpenCV library to remove noise. Then, it uses FFmpeg software to unify the resolution to 1280x720 pixels. This process ensures accurate subsequent analysis.

[1020] Input: Video data saved in the temporary directory

[1021] Output: High-quality pre-processed video data

[1022] Step 3: Analyze the movement

[1023] The server uses the preprocessed video data to analyze the movement of vehicles and pedestrians. It receives the preprocessed video data as input and uses the YOLO model to identify the positions of vehicles and pedestrians. It then calculates the change in position between frames and determines their speed and direction of travel.

[1024] Input: High-quality pre-processed video data

[1025] Output: Position, speed, and heading data of vehicles and pedestrians

[1026] Step 4: Risk assessment

[1027] The server evaluates the risk of traffic accidents based on the movement analysis results. It receives the analyzed location, speed, and direction of travel data as input, and uses TensorFlow to compare it with past data and calculate a risk score. This process evaluates the risk of traffic accidents under certain conditions.

[1028] Input: Vehicle and pedestrian position, speed, and heading data

[1029] Output: Risk score

[1030] Step 5: Notification and proposed action

[1031] Based on the results of the risk assessment, if the risk is high, the server sends a notification to the administrator's device and proposes specific countermeasures. It receives the calculated risk score as input and uses the Twilio API to notify the administrator via SMS or email. Suggested countermeasures include changing traffic light timings or installing additional road signs.

[1032] Input: Risk Score

[1033] Output: Notification to administrator and suggested action

[1034] Step 6: Data storage and reporting

[1035] The server stores the analysis and risk assessment results in a database and generates reports periodically. As input, it takes the analysis and risk assessment results and stores them in a MySQL database. It then uses JasperReports to generate monthly or weekly reports and saves them in PDF format.

[1036] Input: Analysis results and risk assessment results

[1037] Output: Data stored in database, generated reports

[1038] (Application example 1)

[1039] 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."

[1040] In modern society, as autonomous vehicles become more widespread, there is a need to detect traffic accident risks early and implement appropriate countermeasures. However, conventional systems do not accurately assess the risk of traffic accidents and often only respond after an accident has occurred. In addition, drivers cannot receive risk information in real time, which can result in delayed preventive measures. To solve these issues, a system is needed that can monitor traffic conditions with high accuracy and assess and notify risks in real time.

[1041] 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.

[1042] In this invention, the server includes means for collecting video data around traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, and means for sending a real-time notification to the driver of the autonomous vehicle based on the analysis results and proposing specific safety measures, thereby enabling the driver of the autonomous vehicle to grasp the risk of a traffic accident early and take appropriate preventive measures.

[1043] A "camera" is a photographing device for collecting video data around a traffic light.

[1044] "Noise reduction" is a process that removes unnecessary information from collected video data to improve the quality of the data.

[1045] "Resolution adjustment" is a process that optimizes the image quality and size of collected video data to enhance the details.

[1046] "Motion analysis" is a technology that recognizes and analyzes the movements of vehicles and people from pre-processed video data.

[1047] "Assessing the risk of traffic accidents" is the process of calculating the probability of an accident occurring in a specific traffic situation based on the results of motion analysis.

[1048] "Sending notifications in real time" means instantly delivering the analysis results to the driver of the autonomous vehicle.

[1049] "Proposing specific safety measures" means advising drivers on specific actions and measures to take in response to assessed risks.

[1050] A "database" is an information management system that stores analysis results and risk assessment results so that they can be referenced later.

[1051] "Report generation" is the process of organizing the analysis results and risk assessment results and outputting them in an easy-to-read format.

[1052] This invention is a system that monitors traffic conditions near traffic signals in real time, assesses the risk of traffic accidents, and notifies drivers of autonomous vehicles, enabling them to take appropriate countermeasures quickly.

[1053] System configuration

[1054] The system consists of the following main components:

[1055] 1. Camera

[1056] It is installed near traffic lights and collects video data on traffic conditions.

[1057] 2. Server

[1058] Receives video data and performs various data processing and analysis.

[1059] 3. Database

[1060] Store the analysis and risk assessment results and generate reports.

[1061] 4. Administrator terminal

[1062] A device that lets you receive real-time notifications and identify the best course of action.

[1063] How to carry out the invention

[1064] Data collection

[1065] The system's camera collects video data around traffic lights in real time and sends it to a server. The hardware used is a built-in camera in a smartphone or a dedicated surveillance camera, and the communication protocol is HTTP / HTTPS.

[1066] Data Preprocessing

[1067] The server performs noise reduction and resolution adjustment on the received video data. The software used here is the OpenCV library, which improves the video quality.

[1068] Movement Analysis

[1069] The pre-processed video data is then used to apply deep learning models (e.g., YOLO or TensorFlow) to analyze vehicle and pedestrian movements, which allows for vehicle detection, tracking, and speed calculation.

[1070] Risk Assessment

[1071] The server assesses the risk of traffic accidents based on the results of the motion analysis, using a custom algorithm that compares the results with past data patterns, and sends a real-time notification to the administrator's device if the risk is high.

[1072] Notification and suggested solutions

[1073] The server sends real-time notifications to the driver of the autonomous vehicle and suggests specific safety measures, using software such as Firebase Cloud Messaging.

[1074] Data Storage and Reporting

[1075] The analysis and risk assessment results are stored in a database and periodically generated as reports, enabling long-term data management and backup.

[1076] Specific examples

[1077] While the driver is driving in autonomous mode, the system detects vehicles running red lights and sends a notification when the light changes, encouraging safe driving. The notification sent to the driver includes specific instructions such as, "A vehicle running a red light has been detected ahead. Please reduce your speed."

[1078] Example prompts to input to the generative AI model

[1079] "Analyze video data around traffic lights to assess the risk of traffic accidents. Detect vehicles running red lights and send real-time notifications to the driver of autonomous vehicles."

[1080] The present invention provides a powerful means for drivers of autonomous vehicles to instantly grasp traffic conditions and minimize the risk of accidents.

[1081] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1082] Step 1:

[1083] The camera collects video data around the traffic light.

[1084] Input: Real-time video around the traffic light

[1085] Output: Collected video data

[1086] Specific operation: The camera continuously captures video around the traffic light and sends it to the server.

[1087] Step 2:

[1088] The server performs noise reduction and resolution adjustment on the video data.

[1089] Input: Collected video data

[1090] Output: Pre-processed video data

[1091] Specific operation: The server uses the OpenCV library to remove noise from the data and adjust the resolution to improve image quality.

[1092] Step 3:

[1093] The server analyzes the movement of vehicles and people from the pre-processed video data.

[1094] Input: Preprocessed video data

[1095] Output: Analysis results (position, movement, and speed of vehicles and people)

[1096] Specific operation: The server uses a deep learning model (YOLO or TensorFlow) to detect vehicles and people from video data, track them, and calculate their speed and direction of travel.

[1097] Step 4:

[1098] The server evaluates the risk of traffic accidents based on the analysis results.

[1099] Input: Analysis results

[1100] Output: Risk assessment (risk score, risk pattern)

[1101] What it does: The server compares historical data with real-time analytics data, calculates a risk score using custom algorithms, and identifies risk patterns.

[1102] Step 5:

[1103] Based on the risk assessment results, the server sends notifications to the driver of the autonomous vehicle in real time and suggests specific safety measures.

[1104] Input: Risk assessment results

[1105] Output: Notifications and safety suggestions

[1106] Specific operation: The server uses Firebase Cloud Messaging to send push notifications to the driver's smartphone or in-vehicle system, suggesting specific countermeasures such as, "A vehicle running a red light has been detected. Please reduce your speed."

[1107] Step 6:

[1108] The server stores the analysis results and risk assessment results in a database and generates periodic reports.

[1109] Input: Analysis results, risk assessment results

[1110] Output: Data stored in database, generated reports

[1111] Specific operation: The server stores the analysis results and risk assessment results in an SQL database, generates monthly and weekly reports, and sends them to the administrator's terminal.

[1112] keyword

[1113] Generative AI model, prompt sentence

[1114] 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.

[1115] The present invention improves the accuracy of risk assessment by combining a system that uses a camera to collect video data around traffic lights, analyzes the risk of traffic accidents, and proposes countermeasures under specific conditions with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will be described in detail below.

[1116] System configuration

[1117] The system consists of the following main components:

[1118] 1. Camera

[1119] 2. Server

[1120] 3. Database

[1121] 4. Administrator terminal

[1122] 5. Emotion Engine

[1123] System Operation

[1124] Data collection

[1125] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[1126] Data Preprocessing

[1127] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data, improving the quality of the data and enabling more accurate subsequent analysis.

[1128] Movement and Emotion Analysis

[1129] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotional data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel, while also analyzing the user's facial expressions and voice to identify emotions such as stress and impatience.

[1130] Risk Assessment

[1131] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score by taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect outliers and identify risk patterns at specific times of day or at intersections. If the risk due to the user's emotional state is high, the server sends a notification to the administrator.

[1132] Notification and suggested solutions

[1133] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[1134] Data Storage and Reporting

[1135] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[1136] Specific examples

[1137] Example 1: Red light detection

[1138] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[1139] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[1140] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[1141] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[1142] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[1143] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[1144] Example 2: Risks from increased traffic and impatience

[1145] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[1146] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[1147] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[1148] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[1149] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[1150] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[1151] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures. In addition, by taking the user's emotional state into consideration, it is possible to provide more accurate risk assessments and countermeasures.

[1152] The processing flow will be explained below.

[1153] Step 1: Data collection

[1154] Subject: Server

[1155] The server obtains the IP addresses of the cameras and emotion engines installed at each traffic light.

[1156] The server sends a streaming request to the camera and receives video data in real time.

[1157] The server also sends a streaming request to the emotion engine and receives the user's emotion data in real time.

[1158] Step 2: Data Preprocessing

[1159] Subject: Server

[1160] The server applies a noise reduction algorithm to the received video data to improve the quality of the video.

[1161] The server adjusts the resolution and frame rate of the video data and converts it into a format suitable for analysis.

[1162] The server also performs noise removal on the received emotion data to improve the accuracy of emotional state recognition.

[1163] Step 3: Analyze vehicle and human movements

[1164] Subject: Server

[1165] The server applies machine learning models to detect vehicles and people from the pre-processed video data.

[1166] The server tracks the movement of detected vehicles and people and calculates their speed and direction of travel.

[1167] The server analyzes the traffic light status (red, green, yellow) and compares it with the movement of vehicles and people.

[1168] Step 4: Analyze the sentiment data

[1169] Subject: Server

[1170] The server analyzes the data received from the emotion engine to determine the user's emotional state.

[1171] The server classifies the user's emotional state into categories such as "impatience," "stress," and "anger" based on the user's facial expressions and voice.

[1172] The server evaluates the user's psychological state from the emotion data and analyzes its influence on traffic behavior.

[1173] Step 5: Risk assessment

[1174] Subject: Server

[1175] The server integrates the analysis results of vehicle and human movement with the analysis results of emotional data to comprehensively assess the risk of traffic accidents.

[1176] The server compares this data with past data to detect abnormal behavior and high-risk situations in real time.

[1177] The server calculates a risk score based on abnormal behavior and high-risk situations and sends the evaluation results to the administrator terminal.

[1178] Step 6: Notification and proposed action

[1179] Subject: Server

[1180] The server sends notification emails and alerts to administrators based on the assessed risk score.

[1181] The server references a past database and automatically suggests optimal countermeasures for similar risk scenarios.

[1182] The server will suggest specific countermeasures such as "changing the timing of traffic lights," "deploying police officers," and "sending warning messages to drivers."

[1183] Step 7: Data storage and reporting

[1184] Subject: Server

[1185] The server stores the analysis results and risk assessment results in a database.

[1186] The server will regularly back up data and store it safely.

[1187] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[1188] Specific examples

[1189] Example 1: Red light detection

[1190] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[1191] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[1192] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[1193] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[1194] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[1195] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[1196] Example 2: Risks from increased traffic and impatience

[1197] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[1198] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[1199] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[1200] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[1201] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[1202] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[1203] Example 2

[1204] 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."

[1205] Current traffic monitoring systems mainly assess risk based on the movements of vehicles and pedestrians, and few take into account the emotional state of drivers and pedestrians. Therefore, there is a need for more accurate traffic accident risk assessments that incorporate psychological factors of drivers and pedestrians, such as emotional stress and impatience, into the risk assessment. In addition, there is a need for systems that can quickly propose specific countermeasures, such as operating traffic lights and installing traffic signs.

[1206] 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.

[1207] In this invention, the server includes means for collecting video data near traffic lights using a camera and collecting user emotion data using an emotion engine, means for performing noise reduction and resolution adjustment on the collected video data and emotion data, and means for analyzing the movements of vehicles and people from the preprocessed video data and recognizing the user's emotional state from the emotion data. This enables traffic accident risk assessment that takes into account the psychological factors of drivers and pedestrians, and makes it possible to propose quick and specific countermeasures for high-risk situations.

[1208] A "camera" is a device for collecting video data around traffic lights.

[1209] An "emotion engine" is a software or hardware system for collecting and analyzing a user's emotional data.

[1210] "Server" refers to the computer system used to process, analyze, and store data collected from the camera and emotion engine.

[1211] "Noise removal" is a process of removing unnecessary noise from collected data to improve the quality of the data.

[1212] "Resolution adjustment" is a process of changing the resolution of data to an appropriate level.

[1213] "Analysis of vehicle and human movement" is a process of identifying and analyzing the position, movement, speed, etc. of vehicles and pedestrians from preprocessed video data.

[1214] "Recognizing the user's emotional state" is a process of determining the user's emotion (for example, stress, impatience, joy, sadness, etc.) from the emotion data.

[1215] "Assessing the risk of traffic accidents" is the process of calculating and assessing the possibility of a traffic accident occurring based on analyzed data.

[1216] A "risk score" is a numerical indicator of the risk level of a traffic accident.

[1217] "Notification" is the act of informing administrators of warnings and information based on the results of risk assessment.

[1218] "Proposing countermeasures" refers to the act of presenting specific guidelines for action and improvement measures to managers based on the results of risk assessment.

[1219] A "database" is a system for persistently storing collected and analyzed data.

[1220] "Generating a report" refers to the act of creating a document that summarizes the results of analysis and risk assessment based on the information stored in the database.

[1221] A "streaming request" is a request to obtain data in real time over a network.

[1222] "Traffic flow analysis" is the process of statistically analyzing traffic volume and vehicle movements to evaluate traffic conditions.

[1223] "Abnormal behavior" refers to behavior that is not normally expected or is dangerous (e.g., running red lights or dangerous driving).

[1224] In an embodiment of the present invention, a system is constructed using the following components: a camera, a server, a database, an administrator terminal, and an emotion engine. This section describes a system that uses these devices and software to collect, analyze, notify, and propose countermeasures for assessing the risk of traffic accidents.

[1225] System Components

[1226] 1. Camera: A high-resolution IP camera is used to collect video data around the traffic lights. For example, a general outdoor camera is used.

[1227] 2. Emotion engine: A system for collecting and analyzing emotional data, identifying emotions from the user's facial expressions, voice, etc. As a concrete example, a general emotion analysis engine is used.

[1228] 3. Server: A high-performance computer system that processes data. For example, a general-purpose server is used. The server collects, preprocesses, analyzes, assesses risk, and notifies data.

[1229] 4. Database: Stores the collected and analyzed data. For example, a typical relational database is used.

[1230] 5. Administrator terminal: A terminal that receives notifications and suggestions from the server and takes specific countermeasures. For example, a general-purpose tablet terminal or PC is used.

[1231] System Operation

[1232] Data collection

[1233] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[1234] Data Preprocessing

[1235] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data.The hardware and software used are a high-performance server and a general image processing library.

[1236] Movement and Emotion Analysis

[1237] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotion data, using common object detection technology and emotion analysis APIs.

[1238] Risk Assessment

[1239] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect abnormalities.

[1240] Notification and suggested solutions

[1241] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device, who receives a notification via the device and takes measures such as operating traffic lights or installing traffic signs.

[1242] Data Storage and Reporting

[1243] The server stores the analysis results and risk assessment results in a database. This allows the data to be backed up and stored safely. The data is periodically generated as reports and provided to relevant organizations.

[1244] Specific examples

[1245] Example 1: Red light violation detection

[1246] The server obtains video data of traffic light A and the driver's emotional data from the camera and emotion engine. It removes noise from the video data and adjusts the resolution. It also pre-processes the emotional data. The server uses object detection technology to detect when a vehicle has run a red light and confirms that the driver's emotional data indicates "impatience." It calculates a risk score based on the frequency of red light violations and the driver's emotional state, and proposes specific countermeasures to the administrator.

[1247] Example 2: Risks of increased traffic and rushing

[1248] The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B. The data is divided by time period and noise is removed. The server then performs traffic flow analysis and detects increases in traffic volume and driver emotion indicating "impatience." Based on the risk score, the server evaluates the accident risk during specific time periods and proposes specific countermeasures to the manager.

[1249] Prompt Sentence Examples

[1250] The system's program collects and analyzes video and emotion data to assess the risk of traffic accidents. Specifically, the server acquires and preprocesses data through the camera and emotion engine. It then uses object detection technology and emotion analysis APIs to analyze movements and emotions and calculate a risk score. Based on the results of the risk assessment, it sends notifications to administrators and suggests countermeasures. The analysis results are stored in a database and periodic reports are generated.

[1251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1252] Step 1: Data collection

[1253] The server collects video data and user emotion data in real time through a camera installed near a traffic light and the emotion engine. Specifically, the server sends a streaming request to the camera's IP address and acquires video data at 30 frames per second. It also sends a similar request to the emotion engine to collect the user's facial expressions and voice data.

[1254] Input: Real-time data from camera and emotion engine

[1255] Output: Collected raw data (video data and emotion data)

[1256] Step 2: Data Preprocessing

[1257] The server performs noise reduction and resolution adjustment on the collected video and emotion data. Specifically, the server uses the OpenCV library to apply a Gaussian filter to the video data to remove noise. For emotion data, the server also cleans up the data using the emotion engine API.

[1258] Input: Raw data collected

[1259] Output: Preprocessed data (high-quality video data and clean emotion data)

[1260] Step 3: Movement and emotion analysis

[1261] The server analyzes the movement of vehicles and people in the preprocessed video data and recognizes the user's emotional state based on the emotional data. Specifically, the server uses YOLOv5 to detect vehicles and pedestrians, and a Kalman filter to track and calculate their speed. The server then uses Affectiva's API to determine the user's emotional state.

[1262] Input: Preprocessed data

[1263] Output: Analysis results (vehicle and human movement data, emotional state data)

[1264] Step 4: Risk assessment

[1265] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. The server compares past data with real-time data to detect abnormalities.

[1266] Input: Analysis results

[1267] Output: Risk assessment result (risk score)

[1268] Step 5: Notification and proposed action

[1269] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device. Specifically, if the risk score exceeds a set threshold, the server sends a push notification to the administrator's device and proposes countermeasures such as changing traffic light timing or installing traffic signs.

[1270] Input: Risk assessment results

[1271] Output: Notification and suggested action

[1272] Step 6: Data storage and reporting

[1273] The server stores the analysis and risk assessment results in a database. Specifically, the server records each data in a MySQL database. Furthermore, the server generates regular reports using the Python Pandas library and provides them to relevant organizations.

[1274] Input: Analysis results and risk assessment results

[1275] Output: Save to database and generate report

[1276] (Application example 2)

[1277] 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."

[1278] Conventional systems for assessing the risk of traffic accidents rely solely on traffic situation data, making it difficult to accurately assess risk. Furthermore, risk assessments are performed without taking into account the driver's emotional state, potentially overlooking risks caused by driver stress or impatience. This has resulted in insufficient traffic accident prevention measures, making it difficult to improve road safety.

[1279] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting video data near traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, means for assessing the risk of a traffic accident based on the analysis results, means for notifying an administrator and proposing countermeasures if the risk is high, means for saving the analysis results and risk assessment results in a database and generating a report, means for analyzing the driver's emotional state using an emotion engine and reflecting the results in a traffic accident risk assessment, and means for providing warnings and driving assistance information in real time using a smart device. This enables accurate risk assessment and prompt proposal of countermeasures that take the driver's emotional state into account.

[1280] A "camera" is an image capture device installed to collect video data near a traffic light.

[1281] The "server" is a central processing unit that processes and analyzes video data and emotion data, and performs risk assessments and proposes countermeasures.

[1282] A "database" is a data management system for storing analysis results and risk assessment results and generating reports.

[1283] The "administrator terminal" is a device equipped with a user interface that receives notifications of traffic risk assessments and proposed countermeasures, and enables the administrator to take countermeasures.

[1284] The "Emotion Engine" is an emotion recognition system that analyzes the driver's emotional state and uses it to assess the risk of traffic accidents.

[1285] "Noise removal" is a process that removes unnecessary signals and noise from collected video data and emotion data.

[1286] "Resolution adjustment" is an image processing technique for optimizing the image quality of collected video data.

[1287] "Analyzing vehicle and human movement" is the process of detecting the movement of traffic objects from pre-processed video data and calculating their tracking and speed.

[1288] "Risk assessment" is the process of quantifying and evaluating the risk of traffic accidents based on the results of analysis.

[1289] "Notification and suggestion of countermeasures" is a process of sending a warning to the administrator terminal when there is a high risk and suggesting an appropriate countermeasure.

[1290] "Smart devices" are advanced electronic devices designed to provide drivers with real-time warning and driving assistance information.

[1291] This invention is a system that uses a camera and an emotion engine to analyze the traffic conditions near traffic signals and the emotional state of the driver, and evaluate the risk of traffic accidents.The main components of this system are a camera, a server, a database, an administrator terminal, and an emotion engine.

[1292] The server receives video data from the camera device in real time, removes noise, and adjusts the resolution. It then analyzes the movement of vehicles and people from the preprocessed video data. This allows for tracking, speed calculations, and traffic conditions to be understood. The server also analyzes the driver's emotional state from their facial expressions and voice via an emotion engine, and reflects this in traffic accident risk assessments.

[1293] After the risk assessment is completed, if the risk is high, a notification is sent to the administrator's device and specific countermeasures are proposed. Based on this notification and proposal, the intersection administrator can take appropriate measures, such as adjusting traffic light timing or installing signs. The results of the countermeasures and analysis data are stored in a database and used for future improvements.

[1294] Additionally, smart devices (e.g., smart glasses) can provide drivers with real-time warnings and driving assistance information, allowing them to modify their driving behavior or relax, thereby reducing the risk of accidents.

[1295] As a specific example, if a camera detects a vehicle running a red light near a traffic light and the driver appears impatient, the server will assess the risk as high and suggest to the administrator's device that the timing of the traffic light be changed or a warning message be sent to the driver. The administrator can then take immediate action based on this. The driver will see a warning message on their smart device saying, "The light is red. Please be careful."

[1296] The specific hardware used includes a high-resolution IP camera for the camera device, a machine with high-performance computing power for the server, advanced emotion recognition software for the emotion engine, a large-capacity data management system for the database, and a computer capable of real-time display and operation for the administrator terminal.

[1297] The use of generative AI models is also recommended. For example, by entering a prompt such as "Build a system that detects traffic objects from video data and analyzes emotion data to assess high risk. Please also include a function to display appropriate relaxation and warning messages," the detailed structure and operation method of the invention can be obtained from the generative AI model.

[1298] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1299] Step 1:

[1300] The camera collects video data around the traffic light. The camera is a high-resolution IP camera and sends a real-time streaming request to the server. The server takes the video data received from the camera as input and stores the data as video.

[1301] Step 2:

[1302] The server performs noise reduction and resolution adjustment on the collected video data. First, when the server receives the video data, it applies a noise reduction filter to clean up the data. Then it adjusts the resolution to ensure optimal quality for analysis. The output is pre-processed, high-quality video data.

[1303] Step 3:

[1304] The server analyzes the movement of vehicles and people from the pre-processed video data. The server receives the video data as input and uses object detection algorithms to detect vehicles and pedestrians. It then tracks the positions of these objects and calculates their speed and direction of travel. The server outputs the position, speed, and direction of travel data for vehicles and people.

[1305] Step 4:

[1306] The server uses an emotion engine to analyze the driver's emotional state. The server receives video captured by the camera and audio data from the microphone as input and applies an emotion recognition algorithm to extract emotional data (e.g., impatience, stress, etc.) from the driver's facial expressions and voice. The output is the driver's emotional state data.

[1307] Step 5:

[1308] The server assesses the risk of traffic accidents based on the analysis results. The server receives vehicle and pedestrian movement data, as well as the driver's emotional state data, as input and applies a risk assessment model. It compares historical data with real-time data, detects outliers, and calculates a risk score. The output is a traffic accident risk score.

[1309] Step 6:

[1310] If the risk is high, the server will notify the administrator's device and suggest countermeasures. Specifically, if the risk score is high, the server will send a warning message to the administrator's device and suggest specific countermeasures such as "changing traffic light timing" or "sending warning messages to drivers." The administrator's device will display these suggestions, allowing the administrator to take appropriate action.

[1311] Step 7:

[1312] The server stores the analysis results and risk assessment results in a database and generates reports. The server receives the risk assessment scores and analysis data as input documents and generates periodic reports, which are provided to traffic management authorities and other relevant organizations. A comprehensive analysis report is obtained as output.

[1313] Step 8:

[1314] The server provides real-time warnings and driver assistance information using smart devices. The server receives the risk assessment results as input and sends warning messages and driver assistance information to the driver's smart device, so that the driver can immediately pay attention and take appropriate driving actions. The server provides real-time warnings and assistance information to the driver as output.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] [Fourth embodiment]

[1319] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1320] 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.

[1321] 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).

[1322] 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.

[1323] 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.

[1324] 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).

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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."

[1332] The present invention provides a system that uses a camera to collect video data around traffic lights, analyzes the data to assess the risk of traffic accidents, and proposes countermeasures under specific conditions. An embodiment of the present invention will now be described in detail.

[1333] System configuration

[1334] The system consists of the following main components:

[1335] 1. Camera

[1336] 2. Server

[1337] 3. Database

[1338] 4. Administrator terminal

[1339] System Operation

[1340] Data collection

[1341] The server collects video data in real time from cameras installed near traffic lights, which monitor traffic volume, vehicle and pedestrian movements, and transmits the video data to the server.

[1342] Data Preprocessing

[1343] The server performs noise reduction and resolution adjustment on the collected video data, improving the quality of the video data and ensuring accurate subsequent analysis.

[1344] Movement Analysis

[1345] The server analyzes the movement of vehicles and people in the pre-processed video data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel. It also analyzes the status of traffic lights (red, green, yellow).

[1346] Risk Assessment

[1347] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it compares the results with past data and identifies risk patterns at specific times and intersections. If the risk is high, the server sends a notification to the administrator.

[1348] Notification and suggested solutions

[1349] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[1350] Data Storage and Reporting

[1351] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[1352] Specific examples

[1353] Example 1: Red light detection

[1354] 1. Data collection: The server acquires video data of traffic light A from the camera.

[1355] 2. Data preprocessing: The server removes noise from the video data and adjusts the resolution.

[1356] 3. Analysis: The server detects that the vehicle ran a red light.

[1357] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations.

[1358] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the traffic light timing."

[1359] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[1360] Example 2: Risks from increased traffic

[1361] 1. Data collection: The server acquires video data from the camera at traffic light B during rush hour.

[1362] 2. Data preprocessing: The server divides the data into time periods and removes noise.

[1363] 3. Analysis: The server performs traffic flow analysis and detects increases in traffic volume.

[1364] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[1365] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs."

[1366] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[1367] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures.

[1368] The processing flow will be explained below.

[1369] Step 1: Data collection

[1370] Subject: Server

[1371] The server obtains the IP address of the camera installed at each traffic light.

[1372] The server sends a streaming request to the specified IP address.

[1373] The server receives and stores the video data sent from the camera in real time.

[1374] Step 2: Data Preprocessing

[1375] Subject: Server

[1376] The server applies a noise reduction algorithm to the received video data.

[1377] The server adjusts the resolution and frame rate of the video data.

[1378] The server segments the video data by time as needed and divides it into segments of a fixed length.

[1379] Step 3: Analyze vehicle and human movements

[1380] Subject: Server

[1381] The server detects vehicles from the video data using a pre-trained vehicle detection model.

[1382] The server tracks the movement of the detected vehicle and calculates its speed and direction of travel.

[1383] The server analyzes the traffic light status (red, green, yellow).

[1384] Step 4: Risk assessment

[1385] Subject: Server

[1386] The server saves the analysis results in a temporary data store.

[1387] The server compares historical data with real-time data to detect outliers.

[1388] The server identifies risk patterns at specific times and intersections and calculates a risk score.

[1389] Step 5: Notification and proposed action

[1390] Subject: Server

[1391] The server will send a notification email or SMS to the administrator based on the assessed risk score.

[1392] The server refers to a database of past countermeasures and automatically proposes the most appropriate countermeasure.

[1393] The server will propose specific countermeasures such as "changing traffic light timing," "adding traffic signs," and "deploying police officers."

[1394] Step 6: Data storage and reporting

[1395] Subject: Server

[1396] The server stores the analysis results and risk assessment results in a database.

[1397] The server will regularly back up your data and store it safely.

[1398] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[1399] Example 1

[1400] 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."

[1401] Traffic accidents are a serious problem worldwide, affecting many lives and assets. The risk of accidents is particularly high near intersections and traffic lights due to the high volume of traffic and complex pedestrian movements. Predicting accidents in these locations and taking appropriate countermeasures is also difficult. To solve these problems, a system that can monitor and analyze traffic conditions in real time is required.

[1402] 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.

[1403] In this invention, the server includes a means for collecting video data around traffic lights in real time using a camera, a means for performing noise reduction and resolution adjustment on the collected video data, and a means for analyzing the movements of vehicles and pedestrians from the preprocessed video data using an algorithm, which makes it possible to evaluate the risk of traffic accidents by comparing with past data and propose specific countermeasures under specific conditions.

[1404] The "camera" is a device that collects video data around traffic lights in real time.

[1405] The "server" is a central processing unit that receives the video data sent from the camera and performs various analytical processes.

[1406] "Video data" refers to continuous image data captured by a camera that shows the traffic and pedestrian conditions around a traffic light.

[1407] "Noise reduction" is a process that removes unnecessary noise from video data to improve its quality.

[1408] "Resolution adjustment" is a process of unifying the resolution (level of image detail) of video data to an appropriate level.

[1409] "Algorithm" refers to the procedures and calculation methods used to analyze vehicle and pedestrian movements from video data.

[1410] "Motion analysis" is the process of detecting the movement of vehicles and pedestrians from pre-processed video data and identifying their speed and direction of travel.

[1411] "Risk assessment" is the process of evaluating the risk of traffic accidents based on analysis results and comparing them with past data.

[1412] "Notification" is a means of communication to inform managers of the results of traffic accident risk assessments.

[1413] "Proposals for countermeasures" refer to specific measures, such as changing traffic light timing or installing additional road signs, when there is a high risk of traffic accidents.

[1414] A "database" is a data management system that safely stores analysis and risk assessment results for later reference.

[1415] A "report" is a document that summarizes the analysis results and risk assessment results that are generated periodically.

[1416] The present invention is a system that monitors traffic conditions around traffic signals in real time, assesses the risk of traffic accidents, and proposes countermeasures. The system consists of the following main components:

[1417] 1. Camera

[1418] 2. Server

[1419] 3. Database

[1420] 4. Administrator terminal

[1421] System Overview

[1422] Users install network-connected cameras at intersections and near traffic lights. The cameras capture images of traffic and pedestrians in real time and send the video data to a server. A typical example of such a camera is a commonly used network camera.

[1423] The server receives the video data sent from the camera and performs the following processes:

[1424] 1. Data preprocessing: Denoise using OpenCV library and adjust resolution with FFmpeg software.

[1425] 2. Movement analysis: Analyze the movement of vehicles and pedestrians using the YOLO (You Only Look Once) algorithm.

[1426] 3. Risk assessment: Using TensorFlow, we compare the data with past data to assess the risk of traffic accidents.

[1427] If the risk is high, the results of the assessment are sent to the administrator's terminal and specific countermeasures are proposed. The analysis results and risk assessment results are then stored in a database, and reports are generated periodically.

[1428] Specific examples

[1429] Data collection

[1430] The server collects real-time video data from a network camera near the traffic lights, such as an Axis Q1765-LE, and captures image frames every 30 seconds.

[1431] Data Preprocessing

[1432] The server uses the OpenCV library to remove noise from the video and uses FFmpeg to standardize the resolution to 1280x720 pixels.

[1433] Movement Analysis

[1434] The server uses the YOLO model to identify the positions of vehicles and pedestrians in each frame and calculates the change in position between each frame to calculate speed.

[1435] Risk Assessment

[1436] The server uses TensorFlow to model past data and compare it with current data to calculate a risk score.

[1437] Notification and suggested solutions

[1438] The server uses the Twilio API to send SMS and email notifications to the administrator's device. For example, if there are frequent cases of people running red lights, the server can suggest changing the timing of the traffic lights.

[1439] Data Storage and Reporting

[1440] The server stores the analysis and risk assessment results in a MySQL database and uses JasperReports to periodically generate reports and save them in PDF format.

[1441] Examples of prompt statements

[1442] "Please describe in detail a program that monitors traffic conditions in real time near traffic light A and evaluates the risk of traffic accidents."

[1443] The system of the present invention continuously monitors traffic conditions near traffic signals and can take appropriate countermeasures by detecting the risk of traffic accidents at an early stage, which is expected to improve traffic safety.

[1444] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1445] Step 1: Data collection

[1446] The server collects video data around traffic lights from a network camera in real time. As input, it receives streaming video data from the network camera (e.g., Axis Q1765-LE). Specifically, the server sends a streaming request to the camera's IP address and stores the received video data in a temporary directory.

[1447] Input: Video data from a network camera

[1448] Output: Video data saved in temporary directory

[1449] Step 2: Data Preprocessing

[1450] The server performs noise reduction and resolution adjustment on the acquired video data. It receives the collected video data as input and uses the OpenCV library to remove noise. Then, it uses FFmpeg software to unify the resolution to 1280x720 pixels. This process ensures accurate subsequent analysis.

[1451] Input: Video data saved in the temporary directory

[1452] Output: High-quality pre-processed video data

[1453] Step 3: Analyze the movement

[1454] The server uses the preprocessed video data to analyze the movement of vehicles and pedestrians. It receives the preprocessed video data as input and uses the YOLO model to identify the positions of vehicles and pedestrians. It then calculates the change in position between frames and determines their speed and direction of travel.

[1455] Input: High-quality pre-processed video data

[1456] Output: Position, speed, and heading data of vehicles and pedestrians

[1457] Step 4: Risk assessment

[1458] The server evaluates the risk of traffic accidents based on the movement analysis results. It receives the analyzed location, speed, and direction of travel data as input, and uses TensorFlow to compare it with past data and calculate a risk score. This process evaluates the risk of traffic accidents under certain conditions.

[1459] Input: Vehicle and pedestrian position, speed, and heading data

[1460] Output: Risk score

[1461] Step 5: Notification and proposed action

[1462] Based on the results of the risk assessment, if the risk is high, the server sends a notification to the administrator's device and proposes specific countermeasures. It receives the calculated risk score as input and uses the Twilio API to notify the administrator via SMS or email. Suggested countermeasures include changing traffic light timings or installing additional road signs.

[1463] Input: Risk Score

[1464] Output: Notification to administrator and suggested action

[1465] Step 6: Data storage and reporting

[1466] The server stores the analysis and risk assessment results in a database and generates reports periodically. As input, it takes the analysis and risk assessment results and stores them in a MySQL database. It then uses JasperReports to generate monthly or weekly reports and saves them in PDF format.

[1467] Input: Analysis results and risk assessment results

[1468] Output: Data stored in database, generated reports

[1469] (Application example 1)

[1470] 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."

[1471] In modern society, as autonomous vehicles become more widespread, there is a need to detect traffic accident risks early and implement appropriate countermeasures. However, conventional systems do not accurately assess the risk of traffic accidents and often only respond after an accident has occurred. In addition, drivers cannot receive risk information in real time, which can result in delayed preventive measures. To solve these issues, a system is needed that can monitor traffic conditions with high accuracy and assess and notify risks in real time.

[1472] 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.

[1473] In this invention, the server includes means for collecting video data around traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, and means for sending a real-time notification to the driver of the autonomous vehicle based on the analysis results and proposing specific safety measures, thereby enabling the driver of the autonomous vehicle to grasp the risk of a traffic accident early and take appropriate preventive measures.

[1474] A "camera" is a photographing device for collecting video data around a traffic light.

[1475] "Noise reduction" is a process that removes unnecessary information from collected video data to improve the quality of the data.

[1476] "Resolution adjustment" is a process that optimizes the image quality and size of collected video data to enhance the details.

[1477] "Motion analysis" is a technology that recognizes and analyzes the movements of vehicles and people from pre-processed video data.

[1478] "Assessing the risk of traffic accidents" is the process of calculating the probability of an accident occurring in a specific traffic situation based on the results of motion analysis.

[1479] "Sending notifications in real time" means instantly delivering the analysis results to the driver of the autonomous vehicle.

[1480] "Proposing specific safety measures" means advising drivers on specific actions and measures to take in response to assessed risks.

[1481] A "database" is an information management system that stores analysis results and risk assessment results so that they can be referenced later.

[1482] "Report generation" is the process of organizing the analysis results and risk assessment results and outputting them in an easy-to-read format.

[1483] This invention is a system that monitors traffic conditions near traffic signals in real time, assesses the risk of traffic accidents, and notifies drivers of autonomous vehicles, enabling them to take appropriate countermeasures quickly.

[1484] System configuration

[1485] The system consists of the following main components:

[1486] 1. Camera

[1487] It is installed near traffic lights and collects video data on traffic conditions.

[1488] 2. Server

[1489] Receives video data and performs various data processing and analysis.

[1490] 3. Database

[1491] Store the analysis and risk assessment results and generate reports.

[1492] 4. Administrator terminal

[1493] A device that lets you receive real-time notifications and identify the best course of action.

[1494] How to carry out the invention

[1495] Data collection

[1496] The system's camera collects video data around traffic lights in real time and sends it to a server. The hardware used is a built-in camera in a smartphone or a dedicated surveillance camera, and the communication protocol is HTTP / HTTPS.

[1497] Data Preprocessing

[1498] The server performs noise reduction and resolution adjustment on the received video data. The software used here is the OpenCV library, which improves the video quality.

[1499] Movement Analysis

[1500] The pre-processed video data is then used to apply deep learning models (e.g., YOLO or TensorFlow) to analyze vehicle and pedestrian movements, which allows for vehicle detection, tracking, and speed calculation.

[1501] Risk Assessment

[1502] The server assesses the risk of traffic accidents based on the results of the motion analysis, using a custom algorithm that compares the results with past data patterns, and sends a real-time notification to the administrator's device if the risk is high.

[1503] Notification and suggested solutions

[1504] The server sends real-time notifications to the driver of the autonomous vehicle and suggests specific safety measures, using software such as Firebase Cloud Messaging.

[1505] Data Storage and Reporting

[1506] The analysis and risk assessment results are stored in a database and periodically generated as reports, enabling long-term data management and backup.

[1507] Specific examples

[1508] While the driver is driving in autonomous mode, the system detects vehicles running red lights and sends a notification when the light changes, encouraging safe driving. The notification sent to the driver includes specific instructions such as, "A vehicle running a red light has been detected ahead. Please reduce your speed."

[1509] Example prompts to input to the generative AI model

[1510] "Analyze video data around traffic lights to assess the risk of traffic accidents. Detect vehicles running red lights and send real-time notifications to the driver of autonomous vehicles."

[1511] The present invention provides a powerful means for drivers of autonomous vehicles to instantly grasp traffic conditions and minimize the risk of accidents.

[1512] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1513] Step 1:

[1514] The camera collects video data around the traffic light.

[1515] Input: Real-time video around the traffic light

[1516] Output: Collected video data

[1517] Specific operation: The camera continuously captures video around the traffic light and sends it to the server.

[1518] Step 2:

[1519] The server performs noise reduction and resolution adjustment on the video data.

[1520] Input: Collected video data

[1521] Output: Pre-processed video data

[1522] Specific operation: The server uses the OpenCV library to remove noise from the data and adjust the resolution to improve image quality.

[1523] Step 3:

[1524] The server analyzes the movement of vehicles and people from the pre-processed video data.

[1525] Input: Preprocessed video data

[1526] Output: Analysis results (position, movement, and speed of vehicles and people)

[1527] Specific operation: The server uses a deep learning model (YOLO or TensorFlow) to detect vehicles and people from video data, track them, and calculate their speed and direction of travel.

[1528] Step 4:

[1529] The server evaluates the risk of traffic accidents based on the analysis results.

[1530] Input: Analysis results

[1531] Output: Risk assessment (risk score, risk pattern)

[1532] What it does: The server compares historical data with real-time analytics data, calculates a risk score using custom algorithms, and identifies risk patterns.

[1533] Step 5:

[1534] Based on the risk assessment results, the server sends notifications to the driver of the autonomous vehicle in real time and suggests specific safety measures.

[1535] Input: Risk assessment results

[1536] Output: Notifications and safety suggestions

[1537] Specific operation: The server uses Firebase Cloud Messaging to send push notifications to the driver's smartphone or in-vehicle system, suggesting specific countermeasures such as, "A vehicle running a red light has been detected. Please reduce your speed."

[1538] Step 6:

[1539] The server stores the analysis results and risk assessment results in a database and generates periodic reports.

[1540] Input: Analysis results, risk assessment results

[1541] Output: Data stored in database, generated reports

[1542] Specific operation: The server stores the analysis results and risk assessment results in an SQL database, generates monthly and weekly reports, and sends them to the administrator's terminal.

[1543] keyword

[1544] Generative AI model, prompt sentence

[1545] 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.

[1546] The present invention improves the accuracy of risk assessment by combining a system that uses a camera to collect video data around traffic lights, analyzes the risk of traffic accidents, and proposes countermeasures under specific conditions with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will be described in detail below.

[1547] System configuration

[1548] The system consists of the following main components:

[1549] 1. Camera

[1550] 2. Server

[1551] 3. Database

[1552] 4. Administrator terminal

[1553] 5. Emotion Engine

[1554] System Operation

[1555] Data collection

[1556] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[1557] Data Preprocessing

[1558] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data, improving the quality of the data and enabling more accurate subsequent analysis.

[1559] Movement and Emotion Analysis

[1560] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotional data. Specifically, it detects and tracks vehicles, calculates their speed, and identifies their direction of travel, while also analyzing the user's facial expressions and voice to identify emotions such as stress and impatience.

[1561] Risk Assessment

[1562] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score by taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect outliers and identify risk patterns at specific times of day or at intersections. If the risk due to the user's emotional state is high, the server sends a notification to the administrator.

[1563] Notification and suggested solutions

[1564] The server then proposes specific countermeasures based on the results of the risk assessment. Administrators receive notifications via their devices and can take measures such as adjusting traffic lights or installing traffic signs based on the server's suggestions.

[1565] Data Storage and Reporting

[1566] The server stores the analysis results and risk assessment results in a database, which ensures that the data is backed up and stored safely. The server periodically generates reports and provides them to relevant organizations.

[1567] Specific examples

[1568] Example 1: Red light detection

[1569] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[1570] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[1571] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[1572] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[1573] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[1574] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[1575] Example 2: Risks from increased traffic and impatience

[1576] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[1577] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[1578] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[1579] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[1580] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[1581] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[1582] This system can improve road safety by detecting traffic accident risks early and proposing prompt and appropriate countermeasures. In addition, by taking the user's emotional state into consideration, it is possible to provide more accurate risk assessments and countermeasures.

[1583] The processing flow will be explained below.

[1584] Step 1: Data collection

[1585] Subject: Server

[1586] The server obtains the IP addresses of the cameras and emotion engines installed at each traffic light.

[1587] The server sends a streaming request to the camera and receives video data in real time.

[1588] The server also sends a streaming request to the emotion engine and receives the user's emotion data in real time.

[1589] Step 2: Data Preprocessing

[1590] Subject: Server

[1591] The server applies a noise reduction algorithm to the received video data to improve the quality of the video.

[1592] The server adjusts the resolution and frame rate of the video data and converts it into a format suitable for analysis.

[1593] The server also performs noise removal on the received emotion data to improve the accuracy of emotional state recognition.

[1594] Step 3: Analyze vehicle and human movements

[1595] Subject: Server

[1596] The server applies machine learning models to detect vehicles and people from the pre-processed video data.

[1597] The server tracks the movement of detected vehicles and people and calculates their speed and direction of travel.

[1598] The server analyzes the traffic light status (red, green, yellow) and compares it with the movement of vehicles and people.

[1599] Step 4: Analyze the sentiment data

[1600] Subject: Server

[1601] The server analyzes the data received from the emotion engine to determine the user's emotional state.

[1602] The server classifies the user's emotional state into categories such as "impatience," "stress," and "anger" based on the user's facial expressions and voice.

[1603] The server evaluates the user's psychological state from the emotion data and analyzes its influence on traffic behavior.

[1604] Step 5: Risk assessment

[1605] Subject: Server

[1606] The server integrates the analysis results of vehicle and human movement with the analysis results of emotional data to comprehensively assess the risk of traffic accidents.

[1607] The server compares this data with past data to detect abnormal behavior and high-risk situations in real time.

[1608] The server calculates a risk score based on abnormal behavior and high-risk situations and sends the evaluation results to the administrator terminal.

[1609] Step 6: Notification and proposed action

[1610] Subject: Server

[1611] The server sends notification emails and alerts to administrators based on the assessed risk score.

[1612] The server references a past database and automatically suggests optimal countermeasures for similar risk scenarios.

[1613] The server will suggest specific countermeasures such as "changing the timing of traffic lights," "deploying police officers," and "sending warning messages to drivers."

[1614] Step 7: Data storage and reporting

[1615] Subject: Server

[1616] The server stores the analysis results and risk assessment results in a database.

[1617] The server will regularly back up data and store it safely.

[1618] The server automatically generates weekly or monthly reports and provides them to relevant agencies.

[1619] Specific examples

[1620] Example 1: Red light detection

[1621] 1. Data collection: The server acquires the video data of traffic light A and the driver's emotion data from the camera and emotion engine.

[1622] 2. Data preprocessing: The server denoises the video data and adjusts the resolution. It also preprocesses the emotion data.

[1623] 3. Analysis: The server detects that the vehicle ran a red light and confirms that the driver's emotional data indicates "impatience."

[1624] 4. Risk assessment: The server calculates a risk score based on the frequency of red light violations and the driver's emotional state.

[1625] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "changing the timing of traffic lights" and "sending a warning message to the driver."

[1626] 6. Data storage and reporting: The server stores the data in a database and reflects it in monthly reports.

[1627] Example 2: Risks from increased traffic and impatience

[1628] 1. Data collection: The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B.

[1629] 2. Data preprocessing: The server divides the data into time periods and removes noise. It also preprocesses the emotion data in the same way.

[1630] 3. Analysis: The server performs traffic flow analysis to detect an increase in traffic volume and the driver's emotional state indicating "impatience."

[1631] 4. Risk assessment: The server assesses the risk of an accident at a specific time based on the risk score.

[1632] 5. Notification and suggestion of countermeasures: The server sends a notification to the administrator terminal and suggests "adding road signs" and "suggesting relaxation measures for the driver."

[1633] 6. Data storage and reporting: The server stores the analysis results in a database and compiles them into a weekly report.

[1634] Example 2

[1635] 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."

[1636] Current traffic monitoring systems mainly assess risk based on the movements of vehicles and pedestrians, and few take into account the emotional state of drivers and pedestrians. Therefore, there is a need for more accurate traffic accident risk assessments that incorporate psychological factors of drivers and pedestrians, such as emotional stress and impatience, into the risk assessment. In addition, there is a need for systems that can quickly propose specific countermeasures, such as operating traffic lights and installing traffic signs.

[1637] 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.

[1638] In this invention, the server includes means for collecting video data near traffic lights using a camera and collecting user emotion data using an emotion engine, means for performing noise reduction and resolution adjustment on the collected video data and emotion data, and means for analyzing the movements of vehicles and people from the preprocessed video data and recognizing the user's emotional state from the emotion data. This enables traffic accident risk assessment that takes into account the psychological factors of drivers and pedestrians, and makes it possible to propose quick and specific countermeasures for high-risk situations.

[1639] A "camera" is a device for collecting video data around traffic lights.

[1640] An "emotion engine" is a software or hardware system for collecting and analyzing a user's emotional data.

[1641] "Server" refers to the computer system used to process, analyze, and store data collected from the camera and emotion engine.

[1642] "Noise removal" is a process of removing unnecessary noise from collected data to improve the quality of the data.

[1643] "Resolution adjustment" is a process of changing the resolution of data to an appropriate level.

[1644] "Analysis of vehicle and human movement" is a process of identifying and analyzing the position, movement, speed, etc. of vehicles and pedestrians from preprocessed video data.

[1645] "Recognizing the user's emotional state" is a process of determining the user's emotion (for example, stress, impatience, joy, sadness, etc.) from the emotion data.

[1646] "Assessing the risk of traffic accidents" is the process of calculating and assessing the possibility of a traffic accident occurring based on analyzed data.

[1647] A "risk score" is a numerical indicator of the risk level of a traffic accident.

[1648] "Notification" is the act of informing administrators of warnings and information based on the results of risk assessment.

[1649] "Proposing countermeasures" refers to the act of presenting specific guidelines for action and improvement measures to managers based on the results of risk assessment.

[1650] A "database" is a system for persistently storing collected and analyzed data.

[1651] "Generating a report" refers to the act of creating a document that summarizes the results of analysis and risk assessment based on the information stored in the database.

[1652] A "streaming request" is a request to obtain data in real time over a network.

[1653] "Traffic flow analysis" is the process of statistically analyzing traffic volume and vehicle movements to evaluate traffic conditions.

[1654] "Abnormal behavior" refers to behavior that is not normally expected or is dangerous (e.g., running red lights or dangerous driving).

[1655] In an embodiment of the present invention, a system is constructed using the following components: a camera, a server, a database, an administrator terminal, and an emotion engine. This section describes a system that uses these devices and software to collect, analyze, notify, and propose countermeasures for assessing the risk of traffic accidents.

[1656] System Components

[1657] 1. Camera: A high-resolution IP camera is used to collect video data around the traffic lights. For example, a general outdoor camera is used.

[1658] 2. Emotion engine: A system for collecting and analyzing emotional data, identifying emotions from the user's facial expressions, voice, etc. As a concrete example, a general emotion analysis engine is used.

[1659] 3. Server: A high-performance computer system that processes data. For example, a general-purpose server is used. The server collects, preprocesses, analyzes, assesses risk, and notifies data.

[1660] 4. Database: Stores the collected and analyzed data. For example, a typical relational database is used.

[1661] 5. Administrator terminal: A terminal that receives notifications and suggestions from the server and takes specific countermeasures. For example, a general-purpose tablet terminal or PC is used.

[1662] System Operation

[1663] Data collection

[1664] The server collects video data and user emotion data in real time through cameras installed near traffic lights and an emotion engine. The cameras monitor traffic volume, vehicle and human movements, and the emotion engine obtains emotion data from the user's facial expressions and voice.

[1665] Data Preprocessing

[1666] The server performs noise reduction and resolution adjustment on the collected video data, and also performs noise reduction on the emotion data.The hardware and software used are a high-performance server and a general image processing library.

[1667] Movement and Emotion Analysis

[1668] The server analyzes the movements of vehicles and people in the pre-processed video data and recognizes the user's emotional state based on the emotion data, using common object detection technology and emotion analysis APIs.

[1669] Risk Assessment

[1670] The server evaluates the risk of traffic accidents based on the analysis results. It calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. It compares past data with real-time data to detect abnormalities.

[1671] Notification and suggested solutions

[1672] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device, who receives a notification via the device and takes measures such as operating traffic lights or installing traffic signs.

[1673] Data Storage and Reporting

[1674] The server stores the analysis results and risk assessment results in a database. This allows the data to be backed up and stored safely. The data is periodically generated as reports and provided to relevant organizations.

[1675] Specific examples

[1676] Example 1: Red light violation detection

[1677] The server obtains video data of traffic light A and the driver's emotional data from the camera and emotion engine. It removes noise from the video data and adjusts the resolution. It also pre-processes the emotional data. The server uses object detection technology to detect when a vehicle has run a red light and confirms that the driver's emotional data indicates "impatience." It calculates a risk score based on the frequency of red light violations and the driver's emotional state, and proposes specific countermeasures to the administrator.

[1678] Example 2: Risks of increased traffic and rushing

[1679] The server acquires rush hour video data and driver emotion data from the camera and emotion engine at traffic light B. The data is divided by time period and noise is removed. The server then performs traffic flow analysis and detects increases in traffic volume and driver emotion indicating "impatience." Based on the risk score, the server evaluates the accident risk during specific time periods and proposes specific countermeasures to the manager.

[1680] Prompt Sentence Examples

[1681] The system's program collects and analyzes video and emotion data to assess the risk of traffic accidents. Specifically, the server acquires and preprocesses data through the camera and emotion engine. It then uses object detection technology and emotion analysis APIs to analyze movements and emotions and calculate a risk score. Based on the results of the risk assessment, it sends notifications to administrators and suggests countermeasures. The analysis results are stored in a database and periodic reports are generated.

[1682] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1683] Step 1: Data collection

[1684] The server collects video data and user emotion data in real time through a camera installed near a traffic light and the emotion engine. Specifically, the server sends a streaming request to the camera's IP address and acquires video data at 30 frames per second. It also sends a similar request to the emotion engine to collect the user's facial expressions and voice data.

[1685] Input: Real-time data from camera and emotion engine

[1686] Output: Collected raw data (video data and emotion data)

[1687] Step 2: Data Preprocessing

[1688] The server performs noise reduction and resolution adjustment on the collected video and emotion data. Specifically, the server uses the OpenCV library to apply a Gaussian filter to the video data to remove noise. For emotion data, the server also cleans up the data using the emotion engine API.

[1689] Input: Raw data collected

[1690] Output: Preprocessed data (high-quality video data and clean emotion data)

[1691] Step 3: Movement and emotion analysis

[1692] The server analyzes the movement of vehicles and people in the preprocessed video data and recognizes the user's emotional state based on the emotional data. Specifically, the server uses YOLOv5 to detect vehicles and pedestrians, and a Kalman filter to track and calculate their speed. The server then uses Affectiva's API to determine the user's emotional state.

[1693] Input: Preprocessed data

[1694] Output: Analysis results (vehicle and human movement data, emotional state data)

[1695] Step 4: Risk assessment

[1696] The server evaluates the risk of traffic accidents based on the analysis results. Specifically, it calculates a risk score taking into account vehicle movement, traffic light status, and the user's emotional state. The server compares past data with real-time data to detect abnormalities.

[1697] Input: Analysis results

[1698] Output: Risk assessment result (risk score)

[1699] Step 5: Notification and proposed action

[1700] Based on the results of the risk assessment, the server proposes specific countermeasures to the administrator's device. Specifically, if the risk score exceeds a set threshold, the server sends a push notification to the administrator's device and proposes countermeasures such as changing traffic light timing or installing traffic signs.

[1701] Input: Risk assessment results

[1702] Output: Notification and suggested action

[1703] Step 6: Data storage and reporting

[1704] The server stores the analysis and risk assessment results in a database. Specifically, the server records each data in a MySQL database. Furthermore, the server generates regular reports using the Python Pandas library and provides them to relevant organizations.

[1705] Input: Analysis results and risk assessment results

[1706] Output: Save to database and generate report

[1707] (Application example 2)

[1708] 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."

[1709] Conventional systems for assessing the risk of traffic accidents rely solely on traffic situation data, making it difficult to accurately assess risk. Furthermore, risk assessments are performed without taking into account the driver's emotional state, potentially overlooking risks caused by driver stress or impatience. This has resulted in insufficient traffic accident prevention measures, making it difficult to improve road safety.

[1710] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting video data near traffic lights using a camera, means for performing noise reduction and resolution adjustment on the collected video data, means for analyzing the movements of vehicles and people from the preprocessed video data, means for assessing the risk of a traffic accident based on the analysis results, means for notifying an administrator and proposing countermeasures if the risk is high, means for saving the analysis results and risk assessment results in a database and generating a report, means for analyzing the driver's emotional state using an emotion engine and reflecting the results in a traffic accident risk assessment, and means for providing warnings and driving assistance information in real time using a smart device. This enables accurate risk assessment and prompt proposal of countermeasures that take the driver's emotional state into account.

[1711] A "camera" is an image capture device installed to collect video data near a traffic light.

[1712] The "server" is a central processing unit that processes and analyzes video data and emotion data, and performs risk assessments and proposes countermeasures.

[1713] A "database" is a data management system for storing analysis results and risk assessment results and generating reports.

[1714] The "administrator terminal" is a device equipped with a user interface that receives notifications of traffic risk assessments and proposed countermeasures, and enables the administrator to take countermeasures.

[1715] The "Emotion Engine" is an emotion recognition system that analyzes the driver's emotional state and uses it to assess the risk of traffic accidents.

[1716] "Noise removal" is a process that removes unnecessary signals and noise from collected video data and emotion data.

[1717] "Resolution adjustment" is an image processing technique for optimizing the image quality of collected video data.

[1718] "Analyzing vehicle and human movement" is the process of detecting the movement of traffic objects from pre-processed video data and calculating their tracking and speed.

[1719] "Risk assessment" is the process of quantifying and evaluating the risk of traffic accidents based on the results of analysis.

[1720] "Notification and suggestion of countermeasures" is a process of sending a warning to the administrator terminal when there is a high risk and suggesting an appropriate countermeasure.

[1721] "Smart devices" are advanced electronic devices designed to provide drivers with real-time warning and driving assistance information.

[1722] This invention is a system that uses a camera and an emotion engine to analyze the traffic conditions near traffic signals and the emotional state of the driver, and evaluate the risk of traffic accidents.The main components of this system are a camera, a server, a database, an administrator terminal, and an emotion engine.

[1723] The server receives video data from the camera device in real time, removes noise, and adjusts the resolution. It then analyzes the movement of vehicles and people from the preprocessed video data. This allows for tracking, speed calculations, and traffic conditions to be understood. The server also analyzes the driver's emotional state from their facial expressions and voice via an emotion engine, and reflects this in traffic accident risk assessments.

[1724] After the risk assessment is completed, if the risk is high, a notification is sent to the administrator's device and specific countermeasures are proposed. Based on this notification and proposal, the intersection administrator can take appropriate measures, such as adjusting traffic light timing or installing signs. The results of the countermeasures and analysis data are stored in a database and used for future improvements.

[1725] Additionally, smart devices (e.g., smart glasses) can provide drivers with real-time warnings and driving assistance information, allowing them to modify their driving behavior or relax, thereby reducing the risk of accidents.

[1726] As a specific example, if a camera detects a vehicle running a red light near a traffic light and the driver appears impatient, the server will assess the risk as high and suggest to the administrator's device that the timing of the traffic light be changed or a warning message be sent to the driver. The administrator can then take immediate action based on this. The driver will see a warning message on their smart device saying, "The light is red. Please be careful."

[1727] The specific hardware used includes a high-resolution IP camera for the camera device, a machine with high-performance computing power for the server, advanced emotion recognition software for the emotion engine, a large-capacity data management system for the database, and a computer capable of real-time display and operation for the administrator terminal.

[1728] The use of generative AI models is also recommended. For example, by entering a prompt such as "Build a system that detects traffic objects from video data and analyzes emotion data to assess high risk. Please also include a function to display appropriate relaxation and warning messages," the detailed structure and operation method of the invention can be obtained from the generative AI model.

[1729] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1730] Step 1:

[1731] The camera collects video data around the traffic light. The camera is a high-resolution IP camera and sends a real-time streaming request to the server. The server takes the video data received from the camera as input and stores the data as video.

[1732] Step 2:

[1733] The server performs noise reduction and resolution adjustment on the collected video data. First, when the server receives the video data, it applies a noise reduction filter to clean up the data. Then it adjusts the resolution to ensure optimal quality for analysis. The output is pre-processed, high-quality video data.

[1734] Step 3:

[1735] The server analyzes the movement of vehicles and people from the pre-processed video data. The server receives the video data as input and uses object detection algorithms to detect vehicles and pedestrians. It then tracks the positions of these objects and calculates their speed and direction of travel. The server outputs the position, speed, and direction of travel data for vehicles and people.

[1736] Step 4:

[1737] The server uses an emotion engine to analyze the driver's emotional state. The server receives video captured by the camera and audio data from the microphone as input and applies an emotion recognition algorithm to extract emotional data (e.g., impatience, stress, etc.) from the driver's facial expressions and voice. The output is the driver's emotional state data.

[1738] Step 5:

[1739] The server assesses the risk of traffic accidents based on the analysis results. The server receives vehicle and pedestrian movement data, as well as the driver's emotional state data, as input and applies a risk assessment model. It compares historical data with real-time data, detects outliers, and calculates a risk score. The output is a traffic accident risk score.

[1740] Step 6:

[1741] If the risk is high, the server will notify the administrator's device and suggest countermeasures. Specifically, if the risk score is high, the server will send a warning message to the administrator's device and suggest specific countermeasures such as "changing traffic light timing" or "sending warning messages to drivers." The administrator's device will display these suggestions, allowing the administrator to take appropriate action.

[1742] Step 7:

[1743] The server stores the analysis results and risk assessment results in a database and generates reports. The server receives the risk assessment scores and analysis data as input documents and generates periodic reports, which are provided to traffic management authorities and other relevant organizations. A comprehensive analysis report is obtained as output.

[1744] Step 8:

[1745] The server provides real-time warnings and driver assistance information using smart devices. The server receives the risk assessment results as input and sends warning messages and driver assistance information to the driver's smart device, so that the driver can immediately pay attention and take appropriate driving actions. The server provides real-time warnings and assistance information to the driver as output.

[1746] 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.

[1747] 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.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] 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).

[1753] 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.

[1754] 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."

[1755] 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.

[1756] 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).

[1757] 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.

[1758] 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.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1765] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1766] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1767] The following is further disclosed regarding the above embodiment.

[1768] (Claim 1)

[1769] A means for collecting video data in the vicinity of a traffic light using a camera;

[1770] means for performing noise reduction and resolution adjustment on the collected video data;

[1771] means for analyzing the movement of vehicles and people from the preprocessed video data;

[1772] A means of assessing the risk of traffic accidents based on the analysis results, and

[1773] A means of notifying management and suggesting countermeasures in cases of high risk;

[1774] means for storing the analysis results and risk assessment results in a database and generating reports;

[1775] A system including:

[1776] (Claim 2)

[1777] 10. The system of claim 1, wherein a streaming request is sent to an IP address of the camera to obtain video data in real time.

[1778] (Claim 3)

[1779] The system according to claim 1, which performs traffic flow analysis and detects abnormal behavior such as ignoring traffic signals or dangerous driving during a specific period of time.

[1780] "Example 1"

[1781] (Claim 1)

[1782] A means for collecting video data around a traffic light in real time using a camera;

[1783] means for performing noise reduction and resolution adjustment on the collected video data;

[1784] means for analyzing vehicle and pedestrian movements from the pre-processed video data using an algorithm;

[1785] A method for evaluating the risk of traffic accidents based on the analysis results and comparing them with past data.

[1786] A means to notify administrators when risks are high and propose specific countermeasures;

[1787] means for storing the analysis results and risk assessment results in a database and generating reports;

[1788] A system including:

[1789] (Claim 2)

[1790] 2. The system according to claim 1, wherein a streaming request is sent to an address of a network camera to obtain video data in real time.

[1791] (Claim 3)

[1792] The system according to claim 1, which performs traffic flow analysis and detects abnormal behavior such as ignoring traffic signals or dangerous driving during a specific period of time.

[1793] "Application Example 1"

[1794] (Claim 1)

[1795] A means for collecting video data in the vicinity of a traffic light using a camera;

[1796] means for performing noise reduction and resolution adjustment on the collected video data;

[1797] means for analyzing the movement of vehicles and people from the preprocessed video data;

[1798] A means of assessing the risk of traffic accidents based on the analysis results, and

[1799] A means of notifying management and suggesting countermeasures in cases of high risk;

[1800] means for storing the analysis results and risk assessment results in a database and generating reports;

[1801] A means to send real-time notifications to drivers of autonomous vehicles based on the analysis results and suggest specific safety measures;

[1802] A system including:

[1803] (Claim 2)

[1804] 10. The system of claim 1, wherein a streaming request is sent to an IP address of the camera to obtain video data in real time.

[1805] (Claim 3)

[1806] The system according to claim 1, which performs traffic flow analysis and detects abnormal behavior such as ignoring traffic signals or dangerous driving during a specific period of time.

[1807] "Example 2: Combining Emotion Engines"

[1808] (Claim 1)

[1809] A means for collecting video data around a traffic light using a camera and collecting user emotion data using an emotion engine;

[1810] means for performing noise removal and resolution adjustment on the collected video data and emotion data;

[1811] means for analyzing the movements of vehicles and people from the preprocessed video data and recognizing the emotional state of a user from the emotional data;

[1812] A means for evaluating the risk of a traffic accident based on the analysis results and calculating a risk score taking into account vehicle movement, traffic light status, and the user's emotional state;

[1813] A means of notifying administrators and proposing specific countermeasures when risks are high;

[1814] means for storing the analysis results and risk assessment results in a database and generating reports;

[1815] A system including:

[1816] (Claim 2)

[1817] 10. The system of claim 1, wherein the system sends streaming requests to IP addresses of the camera and the emotion engine to obtain video data and emotion data in real time.

[1818] (Claim 3)

[1819] The system according to claim 1, which performs traffic flow analysis and emotion analysis to detect abnormal behavior such as ignoring traffic signals, dangerous driving, and changes in the user's emotions during a specific period of time.

[1820] "Application example 2 when combining emotion engines"

[1821] (Claim 1)

[1822] A means for collecting video data in the vicinity of a traffic light using a camera;

[1823] means for performing noise reduction and resolution adjustment on the collected video data;

[1824] means for analyzing the movement of vehicles and people from the preprocessed video data;

[1825] A means of assessing the risk of traffic accidents based on the analysis results, and

[1826] A means of notifying management and suggesting countermeasures in cases of high risk;

[1827] means for storing the analysis results and risk assessment results in a database and generating reports;

[1828] A means for analyzing the driver's emotional state using an emotion engine and reflecting the result in a traffic accident risk assessment;

[1829] a means for providing real-time warning and driver assistance information using a smart device;

[1830] A system including:

[1831] (Claim 2)

[1832] 10. The system of claim 1, wherein a streaming request is sent to an IP address of the camera to obtain video data in real time.

[1833] (Claim 3)

[1834] The system according to claim 1, which performs traffic flow analysis and detects abnormal behavior such as ignoring traffic signals or dangerous driving during a specific period of time. [Explanation of symbols]

[1835] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting video data in the vicinity of a traffic light using a camera; means for performing noise reduction and resolution adjustment on the collected video data; means for analyzing the movement of vehicles and people from the preprocessed video data; A means of assessing the risk of traffic accidents based on the analysis results, and A means of notifying management and suggesting countermeasures in cases of high risk; means for storing the analysis results and risk assessment results in a database and generating reports; A system including:

2. The system of claim 1, wherein a streaming request is sent to an IP address of a camera to obtain video data in real time.

3. The system according to claim 1, wherein the system performs traffic flow analysis and detects abnormal behavior such as ignoring traffic signals or dangerous driving during a specific period of time.

Images