system

Abstract

Provide a system. [Solution] means for receiving video data acquired from a surveillance camera; means for analyzing the received video data and detecting vehicles and pedestrians; means for calculating an optimal signal change timing based on the detection result; means for transmitting the calculated signal change timing to a traffic light control device; means for controlling a signal based on the received signal change timing; 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] Current traffic signal systems operate based on fixed signal timing, and are often unable to respond appropriately to fluctuations in traffic volume. As a result, inefficient signal operation is likely to occur, such as stopping vehicles at crosswalks where no one is crossing, or turning on the green light even when there are no vehicles. Such inefficient signal operation increases congestion and carbon dioxide emissions. Therefore, we aim to alleviate congestion and reduce environmental impact by realizing appropriate signal control according to traffic volume. [Means for solving the problem]

[0005] The present invention provides a system including a means for receiving video data acquired from a surveillance camera, a means for analyzing the received video data and detecting vehicles and pedestrians, a means for calculating optimal signal change timing based on the detection results, a means for transmitting the calculated signal change timing to a traffic light control device, and a means for controlling signals based on the received signal change timing. This allows for real-time appropriate signal operation according to traffic volume and pedestrian conditions, thereby smoothing traffic flow. Furthermore, by aggregating video data from multiple surveillance cameras and comprehensively analyzing traffic volume at each intersection, overall traffic efficiency can be improved. Furthermore, by monitoring changes in traffic volume in real time and updating the signal change timing as appropriate, optimal signal control can always be maintained.

[0006] A "surveillance camera" is a device that captures images of specific locations such as roads and intersections and transmits the image data.

[0007] "Video data" refers to information recorded in digital format from video captured by a surveillance camera.

[0008] "Means for receiving" refers to a function or method for receiving specific data or information from another device or system.

[0009] "Means for analyzing and detecting" refers to the functions and methods for processing received video data by a computer, recognizing specific objects (e.g., vehicles or pedestrians), and determining their presence or absence and location.

[0010] "Means for calculating signal change timing" refers to functions and methods for calculating optimal traffic signal time allocation and change timing based on the analysis results.

[0011] A "traffic light control device" is a device for controlling the display of traffic signals, and can change signals based on external instructions.

[0012] "Transmitting means" refers to the function or method for sending specific data or information to other devices or systems.

[0013] "Means for controlling signals" refers to the functions and methods for changing the actual state of traffic signals based on the received signal change timing.

[0014] "Traffic volume" refers to the number of vehicles and pedestrians passing through a location within a specific time period.

[0015] "Real-time monitoring" means checking and analyzing current situations and data immediately without delay. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

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

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that uses surveillance cameras and generative AI to analyze traffic volume and control traffic signals at appropriate times. This system aims to smooth traffic flow, alleviate congestion, and reduce carbon dioxide emissions. A specific embodiment of this system is described below.

[0038] System configuration

[0039] The system consists of the following elements:

[0040] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[0041] Server: A device that receives video data and analyzes it using generative AI.

[0042] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0043] Explanation of program processing

[0044] Acquiring camera footage

[0045] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[0046] The terminal compresses the captured image data and sends it to the server.

[0047] Image analysis

[0048] The server receives the image data sent from the terminal.

[0049] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[0050] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0051] Determining signal timing

[0052] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range, for example, the average traffic volume for the past 10 seconds.

[0053] The server calculates the timing of the next traffic light change based on traffic volume data, for example, setting a longer green light time for directions with a higher volume of vehicles and taking into account the timing of pedestrians if they are present.

[0054] The server transmits the calculation results to the traffic light control device.

[0055] Traffic light control

[0056] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[0057] Specific examples

[0058] scenario

[0059] Three surveillance cameras are installed at an intersection, and the data from these cameras is used to control traffic lights.

[0060] Camera footage acquisition:

[0061] The terminal (surveillance camera) captures video every second and sends it to the server.

[0062] Image analysis:

[0063] The server receives the captured video data and inputs it into a generative AI model.

[0064] The AI ​​model detects five vehicles and two pedestrians.

[0065] Determining signal timing:

[0066] The server aggregates the analysis results and calculates the average traffic volume.

[0067] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[0068] Signal Control:

[0069] The server transmits timing information to the traffic light controller.

[0070] The terminal (traffic light controller) controls the signal based on the new timing settings.

[0071] This invention can optimize traffic flow, alleviate congestion, and reduce carbon dioxide emissions.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[0075] Step 2:

[0076] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[0077] Step 3:

[0078] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[0079] Step 4:

[0080] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[0081] Step 5:

[0082] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0083] Step 6:

[0084] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[0085] Step 7:

[0086] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[0087] Step 8:

[0088] The server transmits the calculated signal change timing information to the traffic light controller using HTTP or other protocols.

[0089] Step 9:

[0090] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[0091] Step 10:

[0092] Users (traffic managers) can monitor the system's operating status and signal fluctuations, and can also manually intervene and change settings as needed.

[0093] Example 1

[0094] 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."

[0095] Conventional traffic signal control systems change signals at fixed timing, making it difficult to respond to changes in traffic volume in real time. As a result, traffic congestion in specific directions and overall traffic congestion are likely to occur, making efficient traffic management difficult. Furthermore, conventional systems do not realize adaptive signal control that reduces environmental impact and facilitates traffic flow.

[0096] 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.

[0097] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and using a generative AI model to detect vehicles and pedestrians, means for aggregating the detection results and calculating traffic volume, means for calculating optimal signal change timing based on the calculated traffic volume, means for transmitting the calculated signal change timing to a display control device, and means for controlling signals based on the received signal change timing, thereby enabling adaptive signal control in line with changes in traffic volume in real time.

[0098] A "monitoring device" is a device that monitors a specific area such as a road or intersection and periodically captures video data.

[0099] "Video data" refers to still images or video files captured by surveillance devices and used for traffic monitoring and analysis.

[0100] The "receiving means" refers to a communication interface or software function that allows the server to receive the video data transmitted from the monitoring device.

[0101] A "generative AI model" is an algorithm that uses deep learning techniques to detect and identify specific objects in image data, and is used to detect vehicles and pedestrians in traffic.

[0102] The "means for analyzing" is a software function in the server for detecting vehicles and pedestrians in the received video data using a generative AI model.

[0103] "Detection results" are the results of analysis by the generative AI model, and are information about the location and number of vehicles and pedestrians within a specific time period.

[0104] The "means for calculating traffic volume" is a software function in the server for aggregating the detection results and calculating the traffic volume (total number of vehicles and pedestrians) within a specific time range.

[0105] "Signal change timing" refers to the time at which a traffic signal changes from green to red or vice versa, and is calculated based on traffic volume data.

[0106] A "display control device" is a control unit that operates traffic lights and changes the signals at the appropriate times.

[0107] The "control means" is a function for changing the state of a signal based on the signal change timing received by the display control device from the server.

[0108] "Adaptive signal control" is a control method that dynamically adjusts the timing of signal switching according to real-time traffic conditions, and is used to optimize traffic flow.

[0109] This invention aims to improve traffic signal control by using a monitoring device and a generative AI model to analyze traffic volume in real time and realize adaptive signal control.

[0110] Overall system configuration

[0111] The system consists of the following components:

[0112] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[0113] Server: A device that receives video data and analyzes it using a generative AI model.

[0114] Display control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0115] Program processing explanation

[0116] Acquiring camera footage

[0117] The terminal (monitoring device) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[0118] Specifically, the camera uses sensors to adjust for the surrounding lighting environment and capture video, which is then saved in a format such as JPEG.

[0119] Sending image data

[0120] The terminal (monitoring device) compresses the captured image data and sends it to the server. Standard algorithms (e.g., JPEG compression) are used for compression to reduce the amount of data. The image data is then sent to the server via Wi-Fi or a wired network.

[0121] AI-based image analysis

[0122] The server receives image data sent from the device. The received data is input to a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The server feeds the image data to the input layer of the AI ​​model and obtains the detection results from the output layer.

[0123] Traffic volume data aggregation

[0124] The server aggregates the detected vehicle and pedestrian data. For example, it calculates traffic volume by averaging the number of vehicles and pedestrians in each image for the past 10 seconds. The server stores the detection results in a buffer every hour and periodically aggregates the data in the buffer.

[0125] Determining signal timing

[0126] The server calculates the next signal change timing based on aggregated traffic volume data, extending the green light time for directions with high vehicle traffic and taking into account pedestrian traffic. The server runs traffic engineering algorithms to determine the optimal signal timing.

[0127] Signal timing transmission

[0128] The server sends the calculation results to the display control device. The communication uses a secure protocol (e.g., TLS) to ensure data integrity and safety. The server also sends timing information to the control device via TCP / IP communication.

[0129] Traffic light control

[0130] The display control device controls the traffic signal based on the new signal change timing received from the server. The traffic light control device sets a timer and changes the signal to green, yellow, or red at the determined timing. The control device operates a relay-type switch and controls the power supply to the traffic signal.

[0131] Specific examples

[0132] A specific example using this system is given below.

[0133] scenario

[0134] Three monitoring devices are installed at an intersection, and the data from these devices is used to control traffic lights.

[0135] Camera footage acquisition:

[0136] The terminal (monitoring device) captures images every second at Ryuo intersection and saves them as JPEG files.

[0137] Sending image data:

[0138] The terminal (monitoring device) sends the compressed image data to the server via Wi-Fi.

[0139] AI-powered image analysis:

[0140] The server inputs the received image data into the YOLO model and detects five vehicles and two pedestrians.

[0141] Traffic data aggregation:

[0142] The server aggregates data from the past 10 seconds and calculates the average traffic volume.

[0143] Determining signal timing:

[0144] The server sets the green light to 30 seconds for directions with a large number of vehicles and 15 seconds for directions with a small number of vehicles.

[0145] Transmitting signal timing:

[0146] The server transmits the calculation results to the display control device using a secure protocol.

[0147] Signal Control:

[0148] The display controller controls the traffic signals in real time based on the new signal timing settings.

[0149] Prompt Sentence Examples

[0150] "The number of vehicles and pedestrians is detected from the video data of the monitoring device installed at this intersection, and the timing of the traffic lights is optimized based on the results."

[0151] This system will optimize traffic flow, alleviate congestion, and reduce the burden on the environment.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1: Acquire camera footage

[0154] The terminal (monitoring device) captures video of the road or intersection where it is installed every second. The input is light data from the terminal's camera sensor, and the output is still image data in JPEG format.

[0155] Specifically, the device's camera automatically adjusts exposure and white balance to capture video with optimal brightness and contrast, and the captured image is saved to internal memory.

[0156] Step 2: Compress and transmit image data

[0157] The terminal (monitoring device) compresses the captured image data and sends it to the server. The input is still image data in JPEG format, and the output is compressed image data.

[0158] Specifically, the device applies a standard compression algorithm (e.g., JPEG compression) to reduce the data volume, and then transmits the data to a server via Wi-Fi or a wired network.

[0159] Step 3: Receiving image data

[0160] The server receives image data sent from the terminal. The input is compressed image data, and the output is image data stored in an internal buffer.

[0161] Specifically, the server receives data packets using the TCP / IP protocol and stores them in its internal memory.

[0162] Step 4: Analyzing the image data

[0163] The server inputs the received image data into the generative AI model to detect vehicles and pedestrians. The input is the received image data, and the output is the location information (bounding box coordinates and class) of the detected vehicles and pedestrians.

[0164] Specifically, the server feeds image data to the input layer of an AI model (e.g., YOLO, Faster R-CNN). The AI ​​model performs image analysis through a neural network and obtains detection results from the output layer. The results are stored in the server's memory in list format.

[0165] Step 5: Aggregating traffic data

[0166] The server aggregates multiple analysis results and calculates traffic volume within a specific time range (e.g., the past 10 seconds). The input is a list of analysis results, and the output is traffic volume data (e.g., the number of vehicles and pedestrians at a certain point in time).

[0167] Specifically, the server repeatedly processes the analysis results stored in the buffer, sums up the number of vehicles and pedestrians for each result, and then calculates the average traffic volume over a certain period of time.

[0168] Step 6: Determine signal timing

[0169] The server calculates the next signal change timing based on the collected traffic volume data. The input is traffic volume data, and the output is the optimized signal change timing.

[0170] Specifically, the server runs traffic engineering algorithms, such as extending the green light time in directions with high vehicle traffic volume and taking into account pedestrian traffic timing. The results are stored in internal memory.

[0171] Step 7: Sending signal timing

[0172] The server sends the calculated signal change timing to the display control device, where the input is the optimized signal change timing and the output is the control command sent to the control device.

[0173] Specifically, the server transmits the signal timing information to the display controller using a secure communication protocol (eg, TLS).

[0174] Step 8: Controlling the Signal

[0175] The display control device controls traffic signals based on the signal change timing received from the server. The input is the signal change timing information, and the output is the actual traffic signal display status (switching between green, yellow, and red).

[0176] Specifically, the control device sets a signal timer and changes the signal appropriately at the determined timing. The control device also operates a relay-type switch to control the power supply to the signal light.

[0177] (Application example 1)

[0178] 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."

[0179] Current traffic signal control systems have difficulty detecting vehicles and pedestrians in real time and responding immediately to changes in traffic volume. Furthermore, when autonomous vehicles approach an intersection, they need to instantly obtain signal timing information and make appropriate speed adjustments and route selections. However, a system with such capabilities has not yet been realized. This limits the operational efficiency and traffic safety of autonomous vehicles.

[0180] 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.

[0181] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for transmitting the signal change timing to an onboard computer of an autonomous vehicle to adjust the vehicle's speed and select a route, and means for controlling the traffic lights based on the received signal change timing. This enables an autonomous vehicle to obtain signal timing information in real time as it approaches an intersection and to adjust its speed and select a route appropriately.

[0182] A "monitoring device" is a device that is installed on roads and intersections and periodically captures video data.

[0183] The "receiving means" is a function or device that receives video data transmitted from a monitoring device.

[0184] The "analyzing means" is a function or device for detecting vehicles and pedestrians based on the received video data.

[0185] An "on-board computer" is a computer system installed in an autonomous vehicle that controls the vehicle and performs communication.

[0186] "Signal change timing" is information that indicates the lighting time of a traffic signal and the timing of the change.

[0187] The "calculating means" is a function or device that calculates the optimal signal change timing based on the detection results.

[0188] A "traffic light control device" is a device that controls the lighting state of a traffic signal based on the calculated signal change timing.

[0189] "Speed ​​adjustment" refers to an operation or process for appropriately changing the speed of an autonomous vehicle.

[0190] "Route selection" is the process of determining the optimal route to reach a destination.

[0191] MODE FOR CARRYING OUT THE INVENTION

[0192] System configuration

[0193] The present invention is a system comprising a monitoring device, a server, an on-board computer of an autonomous driving vehicle, and a traffic light control device.

[0194] Hardware configuration

[0195] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[0196] Server: A device that receives video data, analyzes it, and calculates and transmits the signal change timing.

[0197] On-board computer: A computer system installed in an autonomous vehicle that receives signal change timing and adjusts the vehicle's speed and route selection.

[0198] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0199] Software configuration

[0200] Data reception software: Software that runs on the server to receive video data from the surveillance device.

[0201] Generative AI model: An AI model that analyzes image data and detects vehicles and pedestrians. Specific examples include YOLO and Faster R-CNN.

[0202] Signal change timing calculation software: Software that calculates the optimal signal change timing based on analysis results.

[0203] Communication software: Software for data communication between the server, traffic light control device, and on-board computer.

[0204] Data processing and calculation

[0205] The monitoring device periodically captures video data, compresses it, and sends it to a server. The server inputs the received video data into a generative AI model to detect vehicles and pedestrians. The detection results provide each object's location information (bounding box coordinates) and class type (vehicle or pedestrian). The server aggregates multiple analysis results and calculates traffic volume within a specific time range. Based on this, it calculates the optimal signal change timing and sends it to the traffic light control device. At the same time, this signal change timing is also sent to the autonomous vehicle's onboard computer, which adjusts the vehicle's speed and selects its route.

[0206] Specific scenarios

[0207] A specific scenario is shown below.

[0208] A system in which monitoring devices are installed at an intersection and data from these monitoring devices is used to control traffic lights.

[0209] 1. The monitoring device captures video every second and sends it to the server.

[0210] 2. The server receives the captured video data and inputs it into the generative AI model.

[0211] 3. The AI ​​model detects vehicles and pedestrians and identifies the location and number of each object.

[0212] 4. The server aggregates the analysis results and calculates the average traffic volume.

[0213] 5. Set the green light to 30 seconds for the direction with heavy traffic and 15 seconds for the direction with light traffic, and send this information to the traffic light control device and the onboard computer of the autonomous vehicle.

[0214] 6. The traffic light controller controls the traffic light based on the new timing settings.

[0215] 7. The onboard computer of an autonomous vehicle will adjust speed and select a route based on the received signal change timing.

[0216] Prompt Sentence Examples

[0217] Prompt: "Identify the number and location of vehicles and pedestrians in this image."

[0218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0219] Step 1:

[0220] The terminal (monitoring device) captures video data every second. The video data is recorded as a still image and temporarily saved in the terminal. This video data is the input and becomes the first captured image.

[0221] Step 2:

[0222] The device compresses the captured video data and sends it to the server, where the compression process is performed to transfer the video data efficiently. The input is the captured video data, and the output is the compressed video data.

[0223] Step 3:

[0224] The server receives the compressed video data sent from the terminal. The received data is temporarily stored. The input is the compressed video data, and the output is the video data stored on the server.

[0225] Step 4:

[0226] The server inputs the received video data into a generative AI model (e.g., YOLO or Faster R-CNN) and performs image analysis. The generative AI model detects vehicles and pedestrians and outputs the location information (bounding box coordinates) and classification (vehicle or pedestrian) of each object. The input is the video data, and the output is the detection results.

[0227] Step 5:

[0228] The server aggregates the detection results from the generative AI model and calculates traffic volume for multiple timestamps. Specifically, it calculates the number of vehicles and pedestrians over the past few seconds and averages them. The input is the detection results, and the output is the aggregated traffic volume data.

[0229] Step 6:

[0230] The server calculates the optimal signal change timing based on traffic volume data. For example, it sets a longer green light time for directions with a high volume of vehicles, and also takes into account the timing when there are a lot of pedestrians. The input is traffic volume data, and the output is the calculated signal change timing.

[0231] Step 7:

[0232] The server sends the calculated signal change timing to the traffic light control device and the on-board computer of the autonomous vehicle. The input is the calculated signal change timing, and the output is the completion of transmission to the traffic light control device and the on-board computer.

[0233] Step 8:

[0234] The traffic light control device controls traffic signals based on the new signal change timing received from the server. Specifically, it adaptively changes the lighting state of each signal according to the timing. The input is the signal change timing, and the output is the updated traffic signal.

[0235] Step 9:

[0236] The onboard computer of an autonomous vehicle adjusts speed and selects a route based on the signal change timing received from the server. Specifically, it calculates the optimal speed taking into account the received signal change timing and controls the vehicle to match that speed. It also re-plans the route as necessary. The input is the signal change timing, and the output is speed adjustment and route selection.

[0237] 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.

[0238] This invention is a system that realizes more advanced and flexible traffic management by incorporating an emotion engine in addition to a traffic volume analysis system using surveillance cameras and generative AI, and reflecting the results of user emotion recognition in signal control. This system not only keeps traffic flow smooth, but also makes it possible to provide more appropriate reactions and warnings to traffic conditions.

[0239] System configuration

[0240] The system consists of the following elements:

[0241] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[0242] Server: A device that receives video data and analyzes it using generative AI. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[0243] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0244] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[0245] Explanation of program processing

[0246] Acquiring camera footage

[0247] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second). The captured images are recorded as still images.

[0248] The terminal compresses the captured image data and sends it to the server.

[0249] Image analysis

[0250] The server receives the image data sent from the terminal.

[0251] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[0252] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0253] Determining signal timing

[0254] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[0255] The server calculates the timing of the next traffic light change based on traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[0256] User Emotion Recognition

[0257] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[0258] The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[0259] Emotion-based traffic light control adjustment

[0260] The server can further fine-tune the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow.

[0261] The server transmits the final signal change timing information to the signal control device.

[0262] Traffic light control

[0263] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[0264] Specific examples

[0265] scenario

[0266] An environment in which three surveillance cameras are installed at an intersection and a traffic manager (user) monitors the system.

[0267] Camera footage acquisition:

[0268] The terminal (surveillance camera) captures video every second and sends it to the server.

[0269] Image analysis:

[0270] The server receives the captured video data and inputs it into a generative AI model.

[0271] The AI ​​model detects five vehicles and two pedestrians.

[0272] Determining signal timing:

[0273] The server aggregates the analysis results and calculates the average traffic volume.

[0274] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[0275] User Emotion Recognition:

[0276] The server recognizes the emotions of the traffic manager (user) through the user interface.

[0277] The emotion engine recognizes that the user is feeling a little stressed.

[0278] Emotion-based adjustment of traffic light control:

[0279] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[0280] The server transmits the final signal change timing information to the signal control device.

[0281] Signal Control:

[0282] The traffic light controller controls the traffic light based on the new timing settings.

[0283] The present invention makes it possible to optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[0284] The processing flow will be explained below.

[0285] Step 1:

[0286] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[0287] Step 2:

[0288] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[0289] Step 3:

[0290] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[0291] Step 4:

[0292] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[0293] Step 5:

[0294] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0295] Step 6:

[0296] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[0297] Step 7:

[0298] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[0299] Step 8:

[0300] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[0301] Step 9:

[0302] The server analyzes the emotion recognition results and outputs the user's emotional state (e.g., anger, sadness, joy).

[0303] Step 10:

[0304] The server fine-tunes the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server will change the timing of traffic lights to further smooth traffic flow.

[0305] Step 11:

[0306] The server sends the final signal change timing information to the signal controller using HTTP or other protocols.

[0307] Step 12:

[0308] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[0309] Step 13:

[0310] Users (traffic managers) can monitor the system's operating status and signal fluctuations in real time, and can manually intervene and change settings as needed.

[0311] With this detailed processing flow, the present invention can optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[0312] Example 2

[0313] 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."

[0314] Conventional traffic management systems have difficulty adaptively controlling traffic signals in response to changes in traffic volume, often preventing smooth traffic flow. Furthermore, traffic signal control does not take into account the emotions of traffic managers, requiring flexible responses in real time. Furthermore, analysis based on video data from individual surveillance cameras makes it difficult to comprehensively grasp the traffic situation across all intersecting roads. To solve these issues, a new system with advanced analytical capabilities and emotion recognition functions is needed.

[0315] 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.

[0316] In this invention, the server includes means for receiving image data acquired from the monitoring device, means for analyzing the received image data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to the signal control device, means for recognizing the user's emotion, and means for adjusting the signal change timing based on the recognized emotion. This enables real-time analysis of traffic conditions and flexible signal control, and also enables signal adjustment that reflects the user's emotion, enabling more advanced and smoother traffic management overall.

[0317] A "surveillance device" is a device that periodically captures images of roads and intersections.

[0318] "Image data" refers to video information of roads and intersections captured by a monitoring device.

[0319] The "server" is a device that analyzes the received image data, detects vehicles and pedestrians, and performs the calculations and adjustments necessary for traffic light control.

[0320] "Detection" is the process of identifying specific objects (e.g., vehicles or pedestrians) from image data and extracting their location information.

[0321] "Signal change timing" refers to the time allocation for an intersection's traffic lights to switch between red, green, and yellow.

[0322] A "signal control device" is a device that controls the display of traffic signals based on instructions from a server.

[0323] "User emotion" refers to the emotional state, such as joy, anger, or stress, that a traffic manager feels while operating the system.

[0324] "Recognition" is the process of analyzing and identifying a user's emotional state.

[0325] "Adjusting change timing" refers to recalculating and optimizing the existing signal change timing based on user sentiment.

[0326] "Traffic conditions" refers to the flow and volume of vehicles and pedestrians on a particular road or intersection.

[0327] "Real-time" refers to the time frame in which the system responds immediately without delay.

[0328] The present invention is a system that incorporates an emotion engine in addition to a traffic volume analysis system that uses a monitoring device and a generative AI model, thereby reflecting the results of user emotion recognition in signal control and achieving more advanced and flexible traffic management. The following describes in detail the embodiments of the present invention.

[0329] System configuration

[0330] The system consists of the following elements:

[0331] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video.

[0332] Server: A device that receives video data and analyzes it using a generative AI model. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[0333] Signal control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0334] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[0335] Acquiring camera footage

[0336] The terminal (monitoring device) captures video of roads and intersections at regular intervals (for example, every second). The captured video is recorded as a still image. The terminal compresses the captured image data and sends it to the server.

[0337] Image analysis

[0338] The server receives image data sent from the device. The server inputs the received video data into a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The generative AI model identifies the location and number of vehicles and pedestrians in the image and outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0339] Determining signal timing

[0340] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).The server then calculates the timing of the next traffic light change based on the traffic volume data.For example, it may set the green light to 30 seconds for directions with a high volume of vehicles, and 15 seconds for directions with a low volume of vehicles.

[0341] User Emotion Recognition

[0342] The server uses an emotion engine to recognize the emotions of the user (traffic manager). This emotion recognition is performed by analyzing camera footage and audio data obtained through the user interface. The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[0343] Emotion-based traffic light control adjustment

[0344] The server can fine-tune the timing of traffic light control based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow. The server then sends the final traffic light change timing information to the traffic light control device.

[0345] Traffic light control

[0346] The traffic signal control device controls the display of traffic signals based on the new signal change timing received from the server, which enables adaptive changes of traffic signals in real time.

[0347] Specific examples

[0348] scenario

[0349] An environment in which three monitoring devices are installed at an intersection and a traffic manager (user) monitors the system.

[0350] Camera footage acquisition:

[0351] The terminal (monitoring device) captures video every second and sends it to the server.

[0352] Image analysis:

[0353] The server receives the captured video data and inputs it into a generative AI model.

[0354] The AI ​​model detects five vehicles and two pedestrians.

[0355] Determining signal timing:

[0356] The server aggregates the analysis results and calculates the average traffic volume.

[0357] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[0358] User Emotion Recognition:

[0359] The server recognizes the emotions of the traffic manager (user) through the user interface.

[0360] The emotion engine recognizes that the user is feeling a little stressed.

[0361] Emotion-based adjustment of traffic light control:

[0362] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[0363] The server transmits the final signal change timing information to the signal control device.

[0364] Signal Control:

[0365] The signal controller controls the signal based on the new timing settings.

[0366] Prompt Sentence Examples

[0367] "How many vehicles and pedestrians are in this footage?"

[0368] "Please provide location information for each vehicle and pedestrian."

[0369] This invention makes it possible to optimize traffic flow and realize advanced signal control that takes into account user emotions.

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] Processing Steps

[0372] Step 1: Acquire camera footage

[0373] Terminal (monitoring device):

[0374] Specific operation: The device captures video of roads and intersections every second. This captured video is recorded as a still image.

[0375] Input: Surrounding image (real-time road and intersection conditions)

[0376] Output: Collected still image data

[0377] The device will automatically activate the shutter and continuously capture the latest footage, temporarily storing it in its internal memory.

[0378] Step 2: Sending image data

[0379] Terminal (monitoring device):

[0380] Specific operation: The device reduces the captured still image data in a compressed format (e.g., JPEG, PNG) and sends it to the server.

[0381] Input: Collected still image data

[0382] Output: Compressed image data

[0383] Compression reduces the amount of data and begins the process of sending it over the network to the server.

[0384] Step 3: Image analysis

[0385] server:

[0386] Specific operation: The server receives image data sent from the device and inputs it into a generative AI model (e.g., YOLO, Faster R-CNN).

[0387] Input: Compressed image data

[0388] Output: Object detection results (position and class of each object)

[0389] The server uses a deep learning model to identify the location and number of vehicles and pedestrians in the image, resulting in bounding box coordinates and class information.

[0390] Step 4: Determine signal timing

[0391] server:

[0392] Specific operation: The server aggregates the analysis results within a certain time range (e.g., 10 seconds) and calculates traffic volume data.

[0393] Input: Object detection results (last 10 seconds of data)

[0394] Output: Optimal signal timing settings

[0395] The server queries the analysis results temporarily stored in a database, calculates the average number of vehicles and pedestrians, and then determines signal timing based on traffic volume data and generates new settings.

[0396] Step 5: Recognizing User Emotions

[0397] server:

[0398] Specific operation: The server recognizes the emotions of the traffic manager (user) through the user interface.

[0399] Input: Camera footage, audio data (user's facial expressions and voice)

[0400] Output: User's emotional state (e.g., happy, angry, stressed)

[0401] The server inputs data collected by the webcam and microphone into an emotion engine to classify and recognize the user's emotional state.

[0402] Step 6: Adjust traffic light control based on emotions

[0403] server:

[0404] Specific operation: The server fine-tunes the timing of traffic light control based on the user's emotion recognition results.

[0405] Input: User's emotional state, initial signal timing settings

[0406] Output: Adjusted signal timing settings

[0407] The server recalculates existing traffic light timing settings and makes adjustments, such as setting green lights longer if the user is feeling stressed.

[0408] Step 7: Controlling the Signal

[0409] Signal Control Equipment:

[0410] Specific operation: The signal controller operates the signal based on the new signal timing settings received from the server.

[0411] Input: Adjusted signal timing settings

[0412] Output: Change traffic light display

[0413] The signal controller implements the new timing settings and physically switches the traffic lights to update the traffic signals in real time.

[0414] (Application example 2)

[0415] 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."

[0416] Current traffic management systems primarily focus on analyzing traffic volume and optimizing signal control, without taking into account the emotional state of users. This invention aims to improve traffic management sophistication and flexibility by recognizing users' emotional states in real time and adjusting signal control based on that information, thereby not only maintaining smoother traffic flow but also reducing the stress of traffic managers. This technology can also be applied to brick-and-mortar stores where congestion is expected, improving the quality of service within the store.

[0417] The identification process 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 receiving video data acquired from a surveillance camera, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for controlling signals based on the received signal change timing, means including an emotion engine for recognizing the user's emotional state, and means for adjusting signal control based on the recognized emotional state. This enables flexible and advanced signal control based on the emotional state of the traffic manager, thereby maintaining smooth traffic flow and contributing to reducing stress for the traffic manager. Furthermore, even in physical stores, service quality can be improved by recognizing and responding to customers' emotional states in real time.

[0418] Key Word Definitions

[0419] A "surveillance camera" is a device that captures images of specific areas such as roads, intersections, and inside stores in real time and transmits the data to a server.

[0420] "Video data" is digital data containing image information captured by a surveillance camera.

[0421] The "receiving means" is a device or process that has the function of allowing the server to acquire the video data transmitted from the surveillance camera.

[0422] "Means for analysis" refers to algorithms and programs for detecting vehicles and pedestrians based on received video data.

[0423] "Vehicle and pedestrian detection" is the process of identifying the locations of vehicles and pedestrians based on video data.

[0424] "Signal change timing" refers to the time setting for changing the traffic signal display to red, yellow, green, etc.

[0425] "Calculation means" refers to an algorithm or program for determining the optimal timing for signal change based on the analysis results.

[0426] A "traffic light control device" is a device that operates traffic signals based on the signal change timing transmitted from the server.

[0427] The "control means" refers to a function that enables the traffic light control device to actually change the display of the traffic light in accordance with the signal change timing instructed.

[0428] An "emotion engine" is a system that analyzes and recognizes the emotional state expressed by a user (e.g., a traffic manager or a store clerk) through video and audio.

[0429] "Emotional state" refers to a range of emotions (e.g., anger, sadness, joy, stress, etc.) exhibited by a user.

[0430] "Means for adjusting" refers to a process or function by which the server changes or fine-tunes the signal control timing based on the emotional state recognized by the emotion engine.

[0431] MODE FOR CARRYING OUT THE INVENTION

[0432] The present invention aims to improve traffic management and services in brick-and-mortar stores by using a system that combines surveillance cameras, generative AI, and an emotion engine. Details of practical embodiments for carrying out the present invention are provided below.

[0433] System configuration

[0434] This system consists of the following elements:

[0435] 1. Surveillance cameras:

[0436] Surveillance cameras are installed in specific areas (e.g., intersections or inside stores), capture video in real time, and send it to a server.

[0437] 2. Server:

[0438] The server receives and analyzes the video data sent from the surveillance camera.

[0439] The generative AI used for analysis uses image recognition models (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians and recognize the emotional state of customers.

[0440] To recognize the customer's emotional state, video and audio are analyzed through an emotion engine.

[0441] The server calculates the signal change timing and transmits it to the signal control device.

[0442] The server adjusts the signal control based on the emotional state.

[0443] 3. Traffic light controller:

[0444] The traffic light control device controls the traffic light based on the signal change timing received from the server.

[0445] 4. Smart Glasses (Brick-and-mortar application):

[0446] The smart glasses are a device worn by store clerks to display feedback from the server in real time.

[0447] Major hardware and software used

[0448] Hardware:

[0449] surveillance cameras

[0450] server

[0451] Traffic light control device

[0452] Smart Glasses

[0453] software:

[0454] Generative AI models for image analysis (YOLO, Faster R-CNN, etc.)

[0455] Models for emotion recognition

[0456] Analysis and control program for servers

[0457] Program processing explanation

[0458] 1. Acquiring camera footage:

[0459] The terminal (surveillance camera) captures images of roads, intersections, and inside stores and sends the data to a server.

[0460] 2. Image and Sentiment Analysis:

[0461] The server inputs the video data received from the surveillance camera into a generative AI model to detect vehicles and pedestrians and analyze congestion levels.

[0462] At the same time, an emotion engine is used to analyze the emotional state of the user (traffic manager or store clerk), which is obtained from video and audio.

[0463] 3. Determining and coordinating signal control:

[0464] The server calculates the timing of traffic light changes based on the results of image analysis, and adjusts traffic light control based on the results of the emotion engine.

[0465] For example, if a traffic manager is feeling stressed, they will adjust the timing of traffic lights to ensure smooth traffic flow.

[0466] 4. Feedback:

[0467] The server transmits the calculated signal change timing and emotion-based adjustment results to the signal controller and the smart glasses.

[0468] The smart glasses will provide store staff with appropriate feedback in real time and be used to assist customers.

[0469] Specific examples

[0470] For example, a surveillance camera system installed at a certain intersection performs the following process.

[0471] Video capture: The surveillance camera captures video every second and sends it to the server.

[0472] Congestion analysis: The server analyzes the video data and analyzes traffic volume.

[0473] Emotion Recognition: The emotion engine recognizes the stress state of traffic managers.

[0474] Feedback: Adjust signal timing to keep traffic flowing smoothly.

[0475] In addition, even in brick-and-mortar stores, store clerks wearing smart glasses can grasp the emotional state of customers and respond quickly and appropriately.

[0476] Prompt Sentence Examples

[0477] "Analyze in-store video data to recognize the current crowding situation and the emotional state of customers. Design a system that gives real-time feedback to store staff when it is crowded or customers are stressed."

[0478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0479] Specific explanation of processing steps

[0480] Processing Steps

[0481] Step 1:

[0482] Video data is captured from a surveillance camera and sent to a server. The surveillance camera captures video every second and compresses and stores it as digital data. The camera then sends this data to the server via a network.

[0483] Step 2:

[0484] The server receives the video data transmitted from the surveillance camera via the network interface and temporarily stores the digital data in memory.

[0485] Step 3:

[0486] The received video data is input into a generative AI model to detect vehicles and pedestrians. The server inputs the digital data into a deep learning model (e.g., YOLO, Faster R-CNN), and the model outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of vehicles and pedestrians in the video.

[0487] Step 4:

[0488] The analysis results from multiple surveillance cameras are aggregated to calculate traffic volume data. The server aggregates the analysis results sent from each camera and calculates the number of vehicles and pedestrians within a specific time range (e.g., the past 10 seconds).

[0489] Step 5:

[0490] Calculates the optimal timing for signal change based on traffic volume data. The server uses a specific algorithm to calculate the timing for the next signal change based on the calculated traffic volume data. For example, it sets a longer green light time for directions with heavy traffic volume.

[0491] Step 6:

[0492] The server activates an emotion engine to recognize the user's emotional state and obtains the analysis results. The server inputs the video and audio data obtained from the user interface or smart glasses into the emotion engine and obtains the user's emotional state (e.g., anger, joy, stress, etc.).

[0493] Step 7:

[0494] The server adjusts traffic light control based on the recognized emotional state. Based on the acquired emotional state information, the server recalculates the timing of traffic light changes and makes fine adjustments as needed. For example, if the operator is feeling stressed, the green light time will be extended to allow traffic to flow more smoothly.

[0495] Step 8:

[0496] The calculated signal change timing and the emotion-based adjustment result are sent to the traffic light control device. The server then sends the final signal change timing data to the traffic light control device, which then controls the traffic light according to the instructions.

[0497] Step 9:

[0498] The analysis results and recommended actions are displayed as feedback on the smart glasses. The server sends the analysis results and recommended actions (e.g., "The customer is angry" or "The store is crowded") as feedback to the smart glasses, and displays them in real time.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] [Second embodiment]

[0503] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0504] 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.

[0505] 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).

[0506] 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.

[0507] 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.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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.

[0513] In the smart glasses 214, 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.

[0514] 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."

[0515] The present invention is a system that uses surveillance cameras and generative AI to analyze traffic volume and control traffic signals at appropriate times. This system aims to smooth traffic flow, alleviate congestion, and reduce carbon dioxide emissions. A specific embodiment of this system is described below.

[0516] System configuration

[0517] The system consists of the following elements:

[0518] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[0519] Server: A device that receives video data and analyzes it using generative AI.

[0520] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0521] Explanation of program processing

[0522] Acquiring camera footage

[0523] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[0524] The terminal compresses the captured image data and sends it to the server.

[0525] Image analysis

[0526] The server receives the image data sent from the terminal.

[0527] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[0528] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0529] Determining signal timing

[0530] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range, for example, the average traffic volume for the past 10 seconds.

[0531] The server calculates the timing of the next traffic light change based on traffic volume data, for example, setting a longer green light time for directions with a higher volume of vehicles and taking into account the timing of pedestrians if they are present.

[0532] The server transmits the calculation results to the traffic light control device.

[0533] Traffic light control

[0534] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[0535] Specific examples

[0536] scenario

[0537] Three surveillance cameras are installed at an intersection, and the data from these cameras is used to control traffic lights.

[0538] Camera footage acquisition:

[0539] The terminal (surveillance camera) captures video every second and sends it to the server.

[0540] Image analysis:

[0541] The server receives the captured video data and inputs it into a generative AI model.

[0542] The AI ​​model detects five vehicles and two pedestrians.

[0543] Determining signal timing:

[0544] The server aggregates the analysis results and calculates the average traffic volume.

[0545] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[0546] Signal Control:

[0547] The server transmits timing information to the traffic light controller.

[0548] The terminal (traffic light controller) controls the signal based on the new timing settings.

[0549] This invention can optimize traffic flow, alleviate congestion, and reduce carbon dioxide emissions.

[0550] The processing flow will be explained below.

[0551] Step 1:

[0552] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[0553] Step 2:

[0554] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[0555] Step 3:

[0556] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[0557] Step 4:

[0558] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[0559] Step 5:

[0560] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0561] Step 6:

[0562] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[0563] Step 7:

[0564] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[0565] Step 8:

[0566] The server transmits the calculated signal change timing information to the traffic light controller using HTTP or other protocols.

[0567] Step 9:

[0568] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[0569] Step 10:

[0570] Users (traffic managers) can monitor the system's operating status and signal fluctuations, and can also manually intervene and change settings as needed.

[0571] Example 1

[0572] 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."

[0573] Conventional traffic signal control systems change signals at fixed timing, making it difficult to respond to changes in traffic volume in real time. As a result, traffic congestion in specific directions and overall traffic congestion are likely to occur, making efficient traffic management difficult. Furthermore, conventional systems do not realize adaptive signal control that reduces environmental impact and facilitates traffic flow.

[0574] 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.

[0575] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and using a generative AI model to detect vehicles and pedestrians, means for aggregating the detection results and calculating traffic volume, means for calculating optimal signal change timing based on the calculated traffic volume, means for transmitting the calculated signal change timing to a display control device, and means for controlling signals based on the received signal change timing, thereby enabling adaptive signal control in line with changes in traffic volume in real time.

[0576] A "monitoring device" is a device that monitors a specific area such as a road or intersection and periodically captures video data.

[0577] "Video data" refers to still images or video files captured by surveillance devices and used for traffic monitoring and analysis.

[0578] The "receiving means" refers to a communication interface or software function that allows the server to receive the video data transmitted from the monitoring device.

[0579] A "generative AI model" is an algorithm that uses deep learning techniques to detect and identify specific objects in image data, and is used to detect vehicles and pedestrians in traffic.

[0580] The "means for analyzing" is a software function in the server for detecting vehicles and pedestrians in the received video data using a generative AI model.

[0581] "Detection results" are the results of analysis by the generative AI model, and are information about the location and number of vehicles and pedestrians within a specific time period.

[0582] The "means for calculating traffic volume" is a software function in the server for aggregating the detection results and calculating the traffic volume (total number of vehicles and pedestrians) within a specific time range.

[0583] "Signal change timing" refers to the time at which a traffic signal changes from green to red or vice versa, and is calculated based on traffic volume data.

[0584] A "display control device" is a control unit that operates traffic lights and changes the signals at the appropriate times.

[0585] The "control means" is a function for changing the state of a signal based on the signal change timing received by the display control device from the server.

[0586] "Adaptive signal control" is a control method that dynamically adjusts the timing of signal switching according to real-time traffic conditions, and is used to optimize traffic flow.

[0587] This invention aims to improve traffic signal control by using a monitoring device and a generative AI model to analyze traffic volume in real time and realize adaptive signal control.

[0588] Overall system configuration

[0589] The system consists of the following components:

[0590] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[0591] Server: A device that receives video data and analyzes it using a generative AI model.

[0592] Display control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0593] Program processing explanation

[0594] Acquiring camera footage

[0595] The terminal (monitoring device) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[0596] Specifically, the camera uses sensors to adjust for the surrounding lighting environment and capture video, which is then saved in a format such as JPEG.

[0597] Sending image data

[0598] The terminal (monitoring device) compresses the captured image data and sends it to the server. Standard algorithms (e.g., JPEG compression) are used for compression to reduce the amount of data. The image data is then sent to the server via Wi-Fi or a wired network.

[0599] AI-based image analysis

[0600] The server receives image data sent from the device. The received data is input to a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The server feeds the image data to the input layer of the AI ​​model and obtains the detection results from the output layer.

[0601] Traffic volume data aggregation

[0602] The server aggregates the detected vehicle and pedestrian data. For example, it calculates traffic volume by averaging the number of vehicles and pedestrians in each image for the past 10 seconds. The server stores the detection results in a buffer every hour and periodically aggregates the data in the buffer.

[0603] Determining signal timing

[0604] The server calculates the next signal change timing based on aggregated traffic volume data, extending the green light time for directions with high vehicle traffic and taking into account pedestrian traffic. The server runs traffic engineering algorithms to determine the optimal signal timing.

[0605] Signal timing transmission

[0606] The server sends the calculation results to the display control device. The communication uses a secure protocol (e.g., TLS) to ensure data integrity and safety. The server also sends timing information to the control device via TCP / IP communication.

[0607] Traffic light control

[0608] The display control device controls the traffic signal based on the new signal change timing received from the server. The traffic light control device sets a timer and changes the signal to green, yellow, or red at the determined timing. The control device operates a relay-type switch and controls the power supply to the traffic signal.

[0609] Specific examples

[0610] A specific example using this system is given below.

[0611] scenario

[0612] Three monitoring devices are installed at an intersection, and the data from these devices is used to control traffic lights.

[0613] Camera footage acquisition:

[0614] The terminal (monitoring device) captures images every second at Ryuo intersection and saves them as JPEG files.

[0615] Sending image data:

[0616] The terminal (monitoring device) sends the compressed image data to the server via Wi-Fi.

[0617] AI-powered image analysis:

[0618] The server inputs the received image data into the YOLO model and detects five vehicles and two pedestrians.

[0619] Traffic data aggregation:

[0620] The server aggregates data from the past 10 seconds and calculates the average traffic volume.

[0621] Determining signal timing:

[0622] The server sets the green light to 30 seconds for directions with a large number of vehicles and 15 seconds for directions with a small number of vehicles.

[0623] Transmitting signal timing:

[0624] The server transmits the calculation results to the display control device using a secure protocol.

[0625] Signal Control:

[0626] The display controller controls the traffic signals in real time based on the new signal timing settings.

[0627] Prompt Sentence Examples

[0628] "The number of vehicles and pedestrians is detected from the video data of the monitoring device installed at this intersection, and the timing of the traffic lights is optimized based on the results."

[0629] This system will optimize traffic flow, alleviate congestion, and reduce the burden on the environment.

[0630] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0631] Step 1: Acquire camera footage

[0632] The terminal (monitoring device) captures video of the road or intersection where it is installed every second. The input is light data from the terminal's camera sensor, and the output is still image data in JPEG format.

[0633] Specifically, the device's camera automatically adjusts exposure and white balance to capture video with optimal brightness and contrast, and the captured image is saved to internal memory.

[0634] Step 2: Compress and transmit image data

[0635] The terminal (monitoring device) compresses the captured image data and sends it to the server. The input is still image data in JPEG format, and the output is compressed image data.

[0636] Specifically, the device applies a standard compression algorithm (e.g., JPEG compression) to reduce the data volume, and then transmits the data to a server via Wi-Fi or a wired network.

[0637] Step 3: Receiving image data

[0638] The server receives image data sent from the terminal. The input is compressed image data, and the output is image data stored in an internal buffer.

[0639] Specifically, the server receives data packets using the TCP / IP protocol and stores them in its internal memory.

[0640] Step 4: Analyzing the image data

[0641] The server inputs the received image data into the generative AI model to detect vehicles and pedestrians. The input is the received image data, and the output is the location information (bounding box coordinates and class) of the detected vehicles and pedestrians.

[0642] Specifically, the server feeds image data to the input layer of an AI model (e.g., YOLO, Faster R-CNN). The AI ​​model performs image analysis through a neural network and obtains detection results from the output layer. The results are stored in the server's memory in list format.

[0643] Step 5: Aggregating traffic data

[0644] The server aggregates multiple analysis results and calculates traffic volume within a specific time range (e.g., the past 10 seconds). The input is a list of analysis results, and the output is traffic volume data (e.g., the number of vehicles and pedestrians at a certain point in time).

[0645] Specifically, the server repeatedly processes the analysis results stored in the buffer, sums up the number of vehicles and pedestrians for each result, and then calculates the average traffic volume over a certain period of time.

[0646] Step 6: Determine signal timing

[0647] The server calculates the next signal change timing based on the collected traffic volume data. The input is traffic volume data, and the output is the optimized signal change timing.

[0648] Specifically, the server runs traffic engineering algorithms, such as extending the green light time in directions with high vehicle traffic volume and taking into account pedestrian traffic timing. The results are stored in internal memory.

[0649] Step 7: Sending signal timing

[0650] The server sends the calculated signal change timing to the display control device, where the input is the optimized signal change timing and the output is the control command sent to the control device.

[0651] Specifically, the server transmits the signal timing information to the display controller using a secure communication protocol (eg, TLS).

[0652] Step 8: Controlling the Signal

[0653] The display control device controls traffic signals based on the signal change timing received from the server. The input is the signal change timing information, and the output is the actual traffic signal display status (switching between green, yellow, and red).

[0654] Specifically, the control device sets a signal timer and changes the signal appropriately at the determined timing. The control device also operates a relay-type switch to control the power supply to the signal light.

[0655] (Application example 1)

[0656] 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."

[0657] Current traffic signal control systems have difficulty detecting vehicles and pedestrians in real time and responding immediately to changes in traffic volume. Furthermore, when autonomous vehicles approach an intersection, they need to instantly obtain signal timing information and make appropriate speed adjustments and route selections. However, a system with such capabilities has not yet been realized. This limits the operational efficiency and traffic safety of autonomous vehicles.

[0658] 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.

[0659] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for transmitting the signal change timing to an onboard computer of an autonomous vehicle to adjust the vehicle's speed and select a route, and means for controlling the traffic lights based on the received signal change timing. This enables an autonomous vehicle to obtain signal timing information in real time as it approaches an intersection and to adjust its speed and select a route appropriately.

[0660] A "monitoring device" is a device that is installed on roads and intersections and periodically captures video data.

[0661] The "receiving means" is a function or device that receives video data transmitted from a monitoring device.

[0662] The "analyzing means" is a function or device for detecting vehicles and pedestrians based on the received video data.

[0663] An "on-board computer" is a computer system installed in an autonomous vehicle that controls the vehicle and performs communication.

[0664] "Signal change timing" is information that indicates the lighting time of a traffic signal and the timing of the change.

[0665] The "calculating means" is a function or device that calculates the optimal signal change timing based on the detection results.

[0666] A "traffic light control device" is a device that controls the lighting state of a traffic signal based on the calculated signal change timing.

[0667] "Speed ​​adjustment" refers to an operation or process for appropriately changing the speed of an autonomous vehicle.

[0668] "Route selection" is the process of determining the optimal route to reach a destination.

[0669] MODE FOR CARRYING OUT THE INVENTION

[0670] System configuration

[0671] The present invention is a system comprising a monitoring device, a server, an on-board computer of an autonomous driving vehicle, and a traffic light control device.

[0672] Hardware configuration

[0673] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[0674] Server: A device that receives video data, analyzes it, and calculates and transmits the signal change timing.

[0675] On-board computer: A computer system installed in an autonomous vehicle that receives signal change timing and adjusts the vehicle's speed and route selection.

[0676] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0677] Software configuration

[0678] Data reception software: Software that runs on the server to receive video data from the surveillance device.

[0679] Generative AI model: An AI model that analyzes image data and detects vehicles and pedestrians. Specific examples include YOLO and Faster R-CNN.

[0680] Signal change timing calculation software: Software that calculates the optimal signal change timing based on analysis results.

[0681] Communication software: Software for data communication between the server, traffic light control device, and on-board computer.

[0682] Data processing and calculation

[0683] The monitoring device periodically captures video data, compresses it, and sends it to a server. The server inputs the received video data into a generative AI model to detect vehicles and pedestrians. The detection results provide each object's location information (bounding box coordinates) and class type (vehicle or pedestrian). The server aggregates multiple analysis results and calculates traffic volume within a specific time range. Based on this, it calculates the optimal signal change timing and sends it to the traffic light control device. At the same time, this signal change timing is also sent to the autonomous vehicle's onboard computer, which adjusts the vehicle's speed and selects its route.

[0684] Specific scenarios

[0685] A specific scenario is shown below.

[0686] A system in which monitoring devices are installed at an intersection and data from these monitoring devices is used to control traffic lights.

[0687] 1. The monitoring device captures video every second and sends it to the server.

[0688] 2. The server receives the captured video data and inputs it into the generative AI model.

[0689] 3. The AI ​​model detects vehicles and pedestrians and identifies the location and number of each object.

[0690] 4. The server aggregates the analysis results and calculates the average traffic volume.

[0691] 5. Set the green light to 30 seconds for the direction with heavy traffic and 15 seconds for the direction with light traffic, and send this information to the traffic light control device and the onboard computer of the autonomous vehicle.

[0692] 6. The traffic light controller controls the traffic light based on the new timing settings.

[0693] 7. The onboard computer of an autonomous vehicle will adjust speed and select a route based on the received signal change timing.

[0694] Prompt Sentence Examples

[0695] Prompt: "Identify the number and location of vehicles and pedestrians in this image."

[0696] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0697] Step 1:

[0698] The terminal (monitoring device) captures video data every second. The video data is recorded as a still image and temporarily saved in the terminal. This video data is the input and becomes the first captured image.

[0699] Step 2:

[0700] The device compresses the captured video data and sends it to the server, where the compression process is performed to transfer the video data efficiently. The input is the captured video data, and the output is the compressed video data.

[0701] Step 3:

[0702] The server receives the compressed video data sent from the terminal. The received data is temporarily stored. The input is the compressed video data, and the output is the video data stored on the server.

[0703] Step 4:

[0704] The server inputs the received video data into a generative AI model (e.g., YOLO or Faster R-CNN) and performs image analysis. The generative AI model detects vehicles and pedestrians and outputs the location information (bounding box coordinates) and classification (vehicle or pedestrian) of each object. The input is the video data, and the output is the detection results.

[0705] Step 5:

[0706] The server aggregates the detection results from the generative AI model and calculates traffic volume for multiple timestamps. Specifically, it calculates the number of vehicles and pedestrians over the past few seconds and averages them. The input is the detection results, and the output is the aggregated traffic volume data.

[0707] Step 6:

[0708] The server calculates the optimal signal change timing based on traffic volume data. For example, it sets a longer green light time for directions with a high volume of vehicles, and also takes into account the timing when there are a lot of pedestrians. The input is traffic volume data, and the output is the calculated signal change timing.

[0709] Step 7:

[0710] The server sends the calculated signal change timing to the traffic light control device and the on-board computer of the autonomous vehicle. The input is the calculated signal change timing, and the output is the completion of transmission to the traffic light control device and the on-board computer.

[0711] Step 8:

[0712] The traffic light control device controls traffic signals based on the new signal change timing received from the server. Specifically, it adaptively changes the lighting state of each signal according to the timing. The input is the signal change timing, and the output is the updated traffic signal.

[0713] Step 9:

[0714] The onboard computer of an autonomous vehicle adjusts speed and selects a route based on the signal change timing received from the server. Specifically, it calculates the optimal speed taking into account the received signal change timing and controls the vehicle to match that speed. It also re-plans the route as necessary. The input is the signal change timing, and the output is speed adjustment and route selection.

[0715] 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.

[0716] This invention is a system that realizes more advanced and flexible traffic management by incorporating an emotion engine in addition to a traffic volume analysis system using surveillance cameras and generative AI, and reflecting the results of user emotion recognition in signal control. This system not only keeps traffic flow smooth, but also makes it possible to provide more appropriate reactions and warnings to traffic conditions.

[0717] System configuration

[0718] The system consists of the following elements:

[0719] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[0720] Server: A device that receives video data and analyzes it using generative AI. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[0721] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0722] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[0723] Explanation of program processing

[0724] Acquiring camera footage

[0725] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second). The captured images are recorded as still images.

[0726] The terminal compresses the captured image data and sends it to the server.

[0727] Image analysis

[0728] The server receives the image data sent from the terminal.

[0729] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[0730] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0731] Determining signal timing

[0732] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[0733] The server calculates the timing of the next traffic light change based on traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[0734] User Emotion Recognition

[0735] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[0736] The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[0737] Emotion-based traffic light control adjustment

[0738] The server can further fine-tune the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow.

[0739] The server transmits the final signal change timing information to the signal control device.

[0740] Traffic light control

[0741] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[0742] Specific examples

[0743] scenario

[0744] An environment in which three surveillance cameras are installed at an intersection and a traffic manager (user) monitors the system.

[0745] Camera footage acquisition:

[0746] The terminal (surveillance camera) captures video every second and sends it to the server.

[0747] Image analysis:

[0748] The server receives the captured video data and inputs it into a generative AI model.

[0749] The AI ​​model detects five vehicles and two pedestrians.

[0750] Determining signal timing:

[0751] The server aggregates the analysis results and calculates the average traffic volume.

[0752] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[0753] User Emotion Recognition:

[0754] The server recognizes the emotions of the traffic manager (user) through the user interface.

[0755] The emotion engine recognizes that the user is feeling a little stressed.

[0756] Emotion-based adjustment of traffic light control:

[0757] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[0758] The server transmits the final signal change timing information to the signal control device.

[0759] Signal Control:

[0760] The traffic light controller controls the traffic light based on the new timing settings.

[0761] The present invention makes it possible to optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[0762] The processing flow will be explained below.

[0763] Step 1:

[0764] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[0765] Step 2:

[0766] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[0767] Step 3:

[0768] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[0769] Step 4:

[0770] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[0771] Step 5:

[0772] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0773] Step 6:

[0774] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[0775] Step 7:

[0776] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[0777] Step 8:

[0778] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[0779] Step 9:

[0780] The server analyzes the emotion recognition results and outputs the user's emotional state (e.g., anger, sadness, joy).

[0781] Step 10:

[0782] The server fine-tunes the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server will change the timing of traffic lights to further smooth traffic flow.

[0783] Step 11:

[0784] The server sends the final signal change timing information to the signal controller using HTTP or other protocols.

[0785] Step 12:

[0786] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[0787] Step 13:

[0788] Users (traffic managers) can monitor the system's operating status and signal fluctuations in real time, and can manually intervene and change settings as needed.

[0789] With this detailed processing flow, the present invention can optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[0790] Example 2

[0791] 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."

[0792] Conventional traffic management systems have difficulty adaptively controlling traffic signals in response to changes in traffic volume, often preventing smooth traffic flow. Furthermore, traffic signal control does not take into account the emotions of traffic managers, requiring flexible responses in real time. Furthermore, analysis based on video data from individual surveillance cameras makes it difficult to comprehensively grasp the traffic situation across all intersecting roads. To solve these issues, a new system with advanced analytical capabilities and emotion recognition functions is needed.

[0793] 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.

[0794] In this invention, the server includes means for receiving image data acquired from the monitoring device, means for analyzing the received image data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to the signal control device, means for recognizing the user's emotion, and means for adjusting the signal change timing based on the recognized emotion. This enables real-time analysis of traffic conditions and flexible signal control, and also enables signal adjustment that reflects the user's emotion, enabling more advanced and smoother traffic management overall.

[0795] A "surveillance device" is a device that periodically captures images of roads and intersections.

[0796] "Image data" refers to video information of roads and intersections captured by a monitoring device.

[0797] The "server" is a device that analyzes the received image data, detects vehicles and pedestrians, and performs the calculations and adjustments necessary for traffic light control.

[0798] "Detection" is the process of identifying specific objects (e.g., vehicles or pedestrians) from image data and extracting their location information.

[0799] "Signal change timing" refers to the time allocation for an intersection's traffic lights to switch between red, green, and yellow.

[0800] A "signal control device" is a device that controls the display of traffic signals based on instructions from a server.

[0801] "User emotion" refers to the emotional state, such as joy, anger, or stress, that a traffic manager feels while operating the system.

[0802] "Recognition" is the process of analyzing and identifying a user's emotional state.

[0803] "Adjusting change timing" refers to recalculating and optimizing the existing signal change timing based on user sentiment.

[0804] "Traffic conditions" refers to the flow and volume of vehicles and pedestrians on a particular road or intersection.

[0805] "Real-time" refers to the time frame in which the system responds immediately without delay.

[0806] The present invention is a system that incorporates an emotion engine in addition to a traffic volume analysis system that uses a monitoring device and a generative AI model, thereby reflecting the results of user emotion recognition in signal control and achieving more advanced and flexible traffic management. The following describes in detail the embodiments of the present invention.

[0807] System configuration

[0808] The system consists of the following elements:

[0809] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video.

[0810] Server: A device that receives video data and analyzes it using a generative AI model. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[0811] Signal control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0812] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[0813] Acquiring camera footage

[0814] The terminal (monitoring device) captures video of roads and intersections at regular intervals (for example, every second). The captured video is recorded as a still image. The terminal compresses the captured image data and sends it to the server.

[0815] Image analysis

[0816] The server receives image data sent from the device. The server inputs the received video data into a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The generative AI model identifies the location and number of vehicles and pedestrians in the image and outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[0817] Determining signal timing

[0818] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).The server then calculates the timing of the next traffic light change based on the traffic volume data.For example, it may set the green light to 30 seconds for directions with a high volume of vehicles, and 15 seconds for directions with a low volume of vehicles.

[0819] User Emotion Recognition

[0820] The server uses an emotion engine to recognize the emotions of the user (traffic manager). This emotion recognition is performed by analyzing camera footage and audio data obtained through the user interface. The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[0821] Emotion-based traffic light control adjustment

[0822] The server can fine-tune the timing of traffic light control based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow. The server then sends the final traffic light change timing information to the traffic light control device.

[0823] Traffic light control

[0824] The traffic signal control device controls the display of traffic signals based on the new signal change timing received from the server, which enables adaptive changes of traffic signals in real time.

[0825] Specific examples

[0826] scenario

[0827] An environment in which three monitoring devices are installed at an intersection and a traffic manager (user) monitors the system.

[0828] Camera footage acquisition:

[0829] The terminal (monitoring device) captures video every second and sends it to the server.

[0830] Image analysis:

[0831] The server receives the captured video data and inputs it into a generative AI model.

[0832] The AI ​​model detects five vehicles and two pedestrians.

[0833] Determining signal timing:

[0834] The server aggregates the analysis results and calculates the average traffic volume.

[0835] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[0836] User Emotion Recognition:

[0837] The server recognizes the emotions of the traffic manager (user) through the user interface.

[0838] The emotion engine recognizes that the user is feeling a little stressed.

[0839] Emotion-based adjustment of traffic light control:

[0840] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[0841] The server transmits the final signal change timing information to the signal control device.

[0842] Signal Control:

[0843] The signal controller controls the signal based on the new timing settings.

[0844] Prompt Sentence Examples

[0845] "How many vehicles and pedestrians are in this footage?"

[0846] "Please provide location information for each vehicle and pedestrian."

[0847] This invention makes it possible to optimize traffic flow and realize advanced signal control that takes into account user emotions.

[0848] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0849] Processing Steps

[0850] Step 1: Acquire camera footage

[0851] Terminal (monitoring device):

[0852] Specific operation: The device captures video of roads and intersections every second. This captured video is recorded as a still image.

[0853] Input: Surrounding image (real-time road and intersection conditions)

[0854] Output: Collected still image data

[0855] The device will automatically activate the shutter and continuously capture the latest footage, temporarily storing it in its internal memory.

[0856] Step 2: Sending image data

[0857] Terminal (monitoring device):

[0858] Specific operation: The device reduces the captured still image data in a compressed format (e.g., JPEG, PNG) and sends it to the server.

[0859] Input: Collected still image data

[0860] Output: Compressed image data

[0861] Compression reduces the amount of data and begins the process of sending it over the network to the server.

[0862] Step 3: Image analysis

[0863] server:

[0864] Specific operation: The server receives image data sent from the device and inputs it into a generative AI model (e.g., YOLO, Faster R-CNN).

[0865] Input: Compressed image data

[0866] Output: Object detection results (position and class of each object)

[0867] The server uses a deep learning model to identify the location and number of vehicles and pedestrians in the image, resulting in bounding box coordinates and class information.

[0868] Step 4: Determine signal timing

[0869] server:

[0870] Specific operation: The server aggregates the analysis results within a certain time range (e.g., 10 seconds) and calculates traffic volume data.

[0871] Input: Object detection results (last 10 seconds of data)

[0872] Output: Optimal signal timing settings

[0873] The server queries the analysis results temporarily stored in a database, calculates the average number of vehicles and pedestrians, and then determines signal timing based on traffic volume data and generates new settings.

[0874] Step 5: Recognizing User Emotions

[0875] server:

[0876] Specific operation: The server recognizes the emotions of the traffic manager (user) through the user interface.

[0877] Input: Camera footage, audio data (user's facial expressions and voice)

[0878] Output: User's emotional state (e.g., happy, angry, stressed)

[0879] The server inputs data collected by the webcam and microphone into an emotion engine to classify and recognize the user's emotional state.

[0880] Step 6: Adjust traffic light control based on emotions

[0881] server:

[0882] Specific operation: The server fine-tunes the timing of traffic light control based on the user's emotion recognition results.

[0883] Input: User's emotional state, initial signal timing settings

[0884] Output: Adjusted signal timing settings

[0885] The server recalculates existing traffic light timing settings and makes adjustments, such as setting green lights longer if the user is feeling stressed.

[0886] Step 7: Controlling the Signal

[0887] Signal Control Equipment:

[0888] Specific operation: The signal controller operates the signal based on the new signal timing settings received from the server.

[0889] Input: Adjusted signal timing settings

[0890] Output: Change traffic light display

[0891] The signal controller implements the new timing settings and physically switches the traffic lights to update the traffic signals in real time.

[0892] (Application example 2)

[0893] 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."

[0894] Current traffic management systems primarily focus on analyzing traffic volume and optimizing signal control, without taking into account the emotional state of users. This invention aims to improve traffic management sophistication and flexibility by recognizing users' emotional states in real time and adjusting signal control based on that information, thereby not only maintaining smoother traffic flow but also reducing the stress of traffic managers. This technology can also be applied to brick-and-mortar stores where congestion is expected, improving the quality of service within the store.

[0895] The identification process 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 receiving video data acquired from a surveillance camera, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for controlling signals based on the received signal change timing, means including an emotion engine for recognizing the user's emotional state, and means for adjusting signal control based on the recognized emotional state. This enables flexible and advanced signal control based on the emotional state of the traffic manager, thereby maintaining smooth traffic flow and contributing to reducing stress for the traffic manager. Furthermore, even in physical stores, service quality can be improved by recognizing and responding to customers' emotional states in real time.

[0896] Key Word Definitions

[0897] A "surveillance camera" is a device that captures images of specific areas such as roads, intersections, and inside stores in real time and transmits the data to a server.

[0898] "Video data" is digital data containing image information captured by a surveillance camera.

[0899] The "receiving means" is a device or process that has the function of allowing the server to acquire the video data transmitted from the surveillance camera.

[0900] "Means for analysis" refers to algorithms and programs for detecting vehicles and pedestrians based on received video data.

[0901] "Vehicle and pedestrian detection" is the process of identifying the locations of vehicles and pedestrians based on video data.

[0902] "Signal change timing" refers to the time setting for changing the traffic signal display to red, yellow, green, etc.

[0903] "Calculation means" refers to an algorithm or program for determining the optimal timing for signal change based on the analysis results.

[0904] A "traffic light control device" is a device that operates traffic signals based on the signal change timing transmitted from the server.

[0905] The "control means" refers to a function that enables the traffic light control device to actually change the display of the traffic light in accordance with the signal change timing instructed.

[0906] An "emotion engine" is a system that analyzes and recognizes the emotional state expressed by a user (e.g., a traffic manager or a store clerk) through video and audio.

[0907] "Emotional state" refers to a range of emotions (e.g., anger, sadness, joy, stress, etc.) exhibited by a user.

[0908] "Means for adjusting" refers to a process or function by which the server changes or fine-tunes the signal control timing based on the emotional state recognized by the emotion engine.

[0909] MODE FOR CARRYING OUT THE INVENTION

[0910] The present invention aims to improve traffic management and services in brick-and-mortar stores by using a system that combines surveillance cameras, generative AI, and an emotion engine. Details of practical embodiments for carrying out the present invention are provided below.

[0911] System configuration

[0912] This system consists of the following elements:

[0913] 1. Surveillance cameras:

[0914] Surveillance cameras are installed in specific areas (e.g., intersections or inside stores), capture video in real time, and send it to a server.

[0915] 2. Server:

[0916] The server receives and analyzes the video data sent from the surveillance camera.

[0917] The generative AI used for analysis uses image recognition models (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians and recognize the emotional state of customers.

[0918] To recognize the customer's emotional state, video and audio are analyzed through an emotion engine.

[0919] The server calculates the signal change timing and transmits it to the signal control device.

[0920] The server adjusts the signal control based on the emotional state.

[0921] 3. Traffic light controller:

[0922] The traffic light control device controls the traffic light based on the signal change timing received from the server.

[0923] 4. Smart Glasses (Brick-and-mortar application):

[0924] The smart glasses are a device worn by store clerks to display feedback from the server in real time.

[0925] Major hardware and software used

[0926] Hardware:

[0927] surveillance cameras

[0928] server

[0929] Traffic light control device

[0930] Smart Glasses

[0931] software:

[0932] Generative AI models for image analysis (YOLO, Faster R-CNN, etc.)

[0933] Models for emotion recognition

[0934] Analysis and control program for servers

[0935] Program processing explanation

[0936] 1. Acquiring camera footage:

[0937] The terminal (surveillance camera) captures images of roads, intersections, and inside stores and sends the data to a server.

[0938] 2. Image and Sentiment Analysis:

[0939] The server inputs the video data received from the surveillance camera into a generative AI model to detect vehicles and pedestrians and analyze congestion levels.

[0940] At the same time, an emotion engine is used to analyze the emotional state of the user (traffic manager or store clerk), which is obtained from video and audio.

[0941] 3. Determining and coordinating signal control:

[0942] The server calculates the timing of traffic light changes based on the results of image analysis, and adjusts traffic light control based on the results of the emotion engine.

[0943] For example, if a traffic manager is feeling stressed, they will adjust the timing of traffic lights to ensure smooth traffic flow.

[0944] 4. Feedback:

[0945] The server transmits the calculated signal change timing and emotion-based adjustment results to the signal controller and the smart glasses.

[0946] The smart glasses will provide store staff with appropriate feedback in real time and be used to assist customers.

[0947] Specific examples

[0948] For example, a surveillance camera system installed at a certain intersection performs the following process.

[0949] Video capture: The surveillance camera captures video every second and sends it to the server.

[0950] Congestion analysis: The server analyzes the video data and analyzes traffic volume.

[0951] Emotion Recognition: The emotion engine recognizes the stress state of traffic managers.

[0952] Feedback: Adjust signal timing to keep traffic flowing smoothly.

[0953] In addition, even in brick-and-mortar stores, store clerks wearing smart glasses can grasp the emotional state of customers and respond quickly and appropriately.

[0954] Prompt Sentence Examples

[0955] "Analyze in-store video data to recognize the current crowding situation and the emotional state of customers. Design a system that gives real-time feedback to store staff when it is crowded or customers are stressed."

[0956] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0957] Specific explanation of processing steps

[0958] Processing Steps

[0959] Step 1:

[0960] Video data is captured from a surveillance camera and sent to a server. The surveillance camera captures video every second and compresses and stores it as digital data. The camera then sends this data to the server via a network.

[0961] Step 2:

[0962] The server receives the video data transmitted from the surveillance camera via the network interface and temporarily stores the digital data in memory.

[0963] Step 3:

[0964] The received video data is input into a generative AI model to detect vehicles and pedestrians. The server inputs the digital data into a deep learning model (e.g., YOLO, Faster R-CNN), and the model outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of vehicles and pedestrians in the video.

[0965] Step 4:

[0966] The analysis results from multiple surveillance cameras are aggregated to calculate traffic volume data. The server aggregates the analysis results sent from each camera and calculates the number of vehicles and pedestrians within a specific time range (e.g., the past 10 seconds).

[0967] Step 5:

[0968] Calculates the optimal timing for signal change based on traffic volume data. The server uses a specific algorithm to calculate the timing for the next signal change based on the calculated traffic volume data. For example, it sets a longer green light time for directions with heavy traffic volume.

[0969] Step 6:

[0970] The server activates an emotion engine to recognize the user's emotional state and obtains the analysis results. The server inputs the video and audio data obtained from the user interface or smart glasses into the emotion engine and obtains the user's emotional state (e.g., anger, joy, stress, etc.).

[0971] Step 7:

[0972] The server adjusts traffic light control based on the recognized emotional state. Based on the acquired emotional state information, the server recalculates the timing of traffic light changes and makes fine adjustments as needed. For example, if the operator is feeling stressed, the green light time will be extended to allow traffic to flow more smoothly.

[0973] Step 8:

[0974] The calculated signal change timing and the emotion-based adjustment result are sent to the traffic light control device. The server then sends the final signal change timing data to the traffic light control device, which then controls the traffic light according to the instructions.

[0975] Step 9:

[0976] The analysis results and recommended actions are displayed as feedback on the smart glasses. The server sends the analysis results and recommended actions (e.g., "The customer is angry" or "The store is crowded") as feedback to the smart glasses, and displays them in real time.

[0977] 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.

[0978] 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.

[0979] 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.

[0980] [Third embodiment]

[0981] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0982] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0983] 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).

[0984] 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.

[0985] 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.

[0986] 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).

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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."

[0993] The present invention is a system that uses surveillance cameras and generative AI to analyze traffic volume and control traffic signals at appropriate times. This system aims to smooth traffic flow, alleviate congestion, and reduce carbon dioxide emissions. A specific embodiment of this system is described below.

[0994] System configuration

[0995] The system consists of the following elements:

[0996] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[0997] Server: A device that receives video data and analyzes it using generative AI.

[0998] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[0999] Explanation of program processing

[1000] Acquiring camera footage

[1001] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[1002] The terminal compresses the captured image data and sends it to the server.

[1003] Image analysis

[1004] The server receives the image data sent from the terminal.

[1005] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[1006] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1007] Determining signal timing

[1008] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range, for example, the average traffic volume for the past 10 seconds.

[1009] The server calculates the timing of the next traffic light change based on traffic volume data, for example, setting a longer green light time for directions with a higher volume of vehicles and taking into account the timing of pedestrians if they are present.

[1010] The server transmits the calculation results to the traffic light control device.

[1011] Traffic light control

[1012] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[1013] Specific examples

[1014] scenario

[1015] Three surveillance cameras are installed at an intersection, and the data from these cameras is used to control traffic lights.

[1016] Camera footage acquisition:

[1017] The terminal (surveillance camera) captures video every second and sends it to the server.

[1018] Image analysis:

[1019] The server receives the captured video data and inputs it into a generative AI model.

[1020] The AI ​​model detects five vehicles and two pedestrians.

[1021] Determining signal timing:

[1022] The server aggregates the analysis results and calculates the average traffic volume.

[1023] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[1024] Signal Control:

[1025] The server transmits timing information to the traffic light controller.

[1026] The terminal (traffic light controller) controls the signal based on the new timing settings.

[1027] This invention can optimize traffic flow, alleviate congestion, and reduce carbon dioxide emissions.

[1028] The processing flow will be explained below.

[1029] Step 1:

[1030] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[1031] Step 2:

[1032] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[1033] Step 3:

[1034] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[1035] Step 4:

[1036] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[1037] Step 5:

[1038] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1039] Step 6:

[1040] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[1041] Step 7:

[1042] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[1043] Step 8:

[1044] The server transmits the calculated signal change timing information to the traffic light controller using HTTP or other protocols.

[1045] Step 9:

[1046] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[1047] Step 10:

[1048] Users (traffic managers) can monitor the system's operating status and signal fluctuations, and can also manually intervene and change settings as needed.

[1049] Example 1

[1050] 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."

[1051] Conventional traffic signal control systems change signals at fixed timing, making it difficult to respond to changes in traffic volume in real time. As a result, traffic congestion in specific directions and overall traffic congestion are likely to occur, making efficient traffic management difficult. Furthermore, conventional systems do not realize adaptive signal control that reduces environmental impact and facilitates traffic flow.

[1052] 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.

[1053] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and using a generative AI model to detect vehicles and pedestrians, means for aggregating the detection results and calculating traffic volume, means for calculating optimal signal change timing based on the calculated traffic volume, means for transmitting the calculated signal change timing to a display control device, and means for controlling signals based on the received signal change timing, thereby enabling adaptive signal control in line with changes in traffic volume in real time.

[1054] A "monitoring device" is a device that monitors a specific area such as a road or intersection and periodically captures video data.

[1055] "Video data" refers to still images or video files captured by surveillance devices and used for traffic monitoring and analysis.

[1056] The "receiving means" refers to a communication interface or software function that allows the server to receive the video data transmitted from the monitoring device.

[1057] A "generative AI model" is an algorithm that uses deep learning techniques to detect and identify specific objects in image data, and is used to detect vehicles and pedestrians in traffic.

[1058] The "means for analyzing" is a software function in the server for detecting vehicles and pedestrians in the received video data using a generative AI model.

[1059] "Detection results" are the results of analysis by the generative AI model, and are information about the location and number of vehicles and pedestrians within a specific time period.

[1060] The "means for calculating traffic volume" is a software function in the server for aggregating the detection results and calculating the traffic volume (total number of vehicles and pedestrians) within a specific time range.

[1061] "Signal change timing" refers to the time at which a traffic signal changes from green to red or vice versa, and is calculated based on traffic volume data.

[1062] A "display control device" is a control unit that operates traffic lights and changes the signals at the appropriate times.

[1063] The "control means" is a function for changing the state of a signal based on the signal change timing received by the display control device from the server.

[1064] "Adaptive signal control" is a control method that dynamically adjusts the timing of signal switching according to real-time traffic conditions, and is used to optimize traffic flow.

[1065] This invention aims to improve traffic signal control by using a monitoring device and a generative AI model to analyze traffic volume in real time and realize adaptive signal control.

[1066] Overall system configuration

[1067] The system consists of the following components:

[1068] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[1069] Server: A device that receives video data and analyzes it using a generative AI model.

[1070] Display control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1071] Program processing explanation

[1072] Acquiring camera footage

[1073] The terminal (monitoring device) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[1074] Specifically, the camera uses sensors to adjust for the surrounding lighting environment and capture video, which is then saved in a format such as JPEG.

[1075] Sending image data

[1076] The terminal (monitoring device) compresses the captured image data and sends it to the server. Standard algorithms (e.g., JPEG compression) are used for compression to reduce the amount of data. The image data is then sent to the server via Wi-Fi or a wired network.

[1077] AI-based image analysis

[1078] The server receives image data sent from the device. The received data is input to a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The server feeds the image data to the input layer of the AI ​​model and obtains the detection results from the output layer.

[1079] Traffic volume data aggregation

[1080] The server aggregates the detected vehicle and pedestrian data. For example, it calculates traffic volume by averaging the number of vehicles and pedestrians in each image for the past 10 seconds. The server stores the detection results in a buffer every hour and periodically aggregates the data in the buffer.

[1081] Determining signal timing

[1082] The server calculates the next signal change timing based on aggregated traffic volume data, extending the green light time for directions with high vehicle traffic and taking into account pedestrian traffic. The server runs traffic engineering algorithms to determine the optimal signal timing.

[1083] Signal timing transmission

[1084] The server sends the calculation results to the display control device. The communication uses a secure protocol (e.g., TLS) to ensure data integrity and safety. The server also sends timing information to the control device via TCP / IP communication.

[1085] Traffic light control

[1086] The display control device controls the traffic signal based on the new signal change timing received from the server. The traffic light control device sets a timer and changes the signal to green, yellow, or red at the determined timing. The control device operates a relay-type switch and controls the power supply to the traffic signal.

[1087] Specific examples

[1088] A specific example using this system is given below.

[1089] scenario

[1090] Three monitoring devices are installed at an intersection, and the data from these devices is used to control traffic lights.

[1091] Camera footage acquisition:

[1092] The terminal (monitoring device) captures images every second at Ryuo intersection and saves them as JPEG files.

[1093] Sending image data:

[1094] The terminal (monitoring device) sends the compressed image data to the server via Wi-Fi.

[1095] AI-powered image analysis:

[1096] The server inputs the received image data into the YOLO model and detects five vehicles and two pedestrians.

[1097] Traffic data aggregation:

[1098] The server aggregates data from the past 10 seconds and calculates the average traffic volume.

[1099] Determining signal timing:

[1100] The server sets the green light to 30 seconds for directions with a large number of vehicles and 15 seconds for directions with a small number of vehicles.

[1101] Transmitting signal timing:

[1102] The server transmits the calculation results to the display control device using a secure protocol.

[1103] Signal Control:

[1104] The display controller controls the traffic signals in real time based on the new signal timing settings.

[1105] Prompt Sentence Examples

[1106] "The number of vehicles and pedestrians is detected from the video data of the monitoring device installed at this intersection, and the timing of the traffic lights is optimized based on the results."

[1107] This system will optimize traffic flow, alleviate congestion, and reduce the burden on the environment.

[1108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1109] Step 1: Acquire camera footage

[1110] The terminal (monitoring device) captures video of the road or intersection where it is installed every second. The input is light data from the terminal's camera sensor, and the output is still image data in JPEG format.

[1111] Specifically, the device's camera automatically adjusts exposure and white balance to capture video with optimal brightness and contrast, and the captured image is saved to internal memory.

[1112] Step 2: Compress and transmit image data

[1113] The terminal (monitoring device) compresses the captured image data and sends it to the server. The input is still image data in JPEG format, and the output is compressed image data.

[1114] Specifically, the device applies a standard compression algorithm (e.g., JPEG compression) to reduce the data volume, and then transmits the data to a server via Wi-Fi or a wired network.

[1115] Step 3: Receiving image data

[1116] The server receives image data sent from the terminal. The input is compressed image data, and the output is image data stored in an internal buffer.

[1117] Specifically, the server receives data packets using the TCP / IP protocol and stores them in its internal memory.

[1118] Step 4: Analyzing the image data

[1119] The server inputs the received image data into the generative AI model to detect vehicles and pedestrians. The input is the received image data, and the output is the location information (bounding box coordinates and class) of the detected vehicles and pedestrians.

[1120] Specifically, the server feeds image data to the input layer of an AI model (e.g., YOLO, Faster R-CNN). The AI ​​model performs image analysis through a neural network and obtains detection results from the output layer. The results are stored in the server's memory in list format.

[1121] Step 5: Aggregating traffic data

[1122] The server aggregates multiple analysis results and calculates traffic volume within a specific time range (e.g., the past 10 seconds). The input is a list of analysis results, and the output is traffic volume data (e.g., the number of vehicles and pedestrians at a certain point in time).

[1123] Specifically, the server repeatedly processes the analysis results stored in the buffer, sums up the number of vehicles and pedestrians for each result, and then calculates the average traffic volume over a certain period of time.

[1124] Step 6: Determine signal timing

[1125] The server calculates the next signal change timing based on the collected traffic volume data. The input is traffic volume data, and the output is the optimized signal change timing.

[1126] Specifically, the server runs traffic engineering algorithms, such as extending the green light time in directions with high vehicle traffic volume and taking into account pedestrian traffic timing. The results are stored in internal memory.

[1127] Step 7: Sending signal timing

[1128] The server sends the calculated signal change timing to the display control device, where the input is the optimized signal change timing and the output is the control command sent to the control device.

[1129] Specifically, the server transmits the signal timing information to the display controller using a secure communication protocol (eg, TLS).

[1130] Step 8: Controlling the Signal

[1131] The display control device controls traffic signals based on the signal change timing received from the server. The input is the signal change timing information, and the output is the actual traffic signal display status (switching between green, yellow, and red).

[1132] Specifically, the control device sets a signal timer and changes the signal appropriately at the determined timing. The control device also operates a relay-type switch to control the power supply to the signal light.

[1133] (Application example 1)

[1134] 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."

[1135] Current traffic signal control systems have difficulty detecting vehicles and pedestrians in real time and responding immediately to changes in traffic volume. Furthermore, when autonomous vehicles approach an intersection, they need to instantly obtain signal timing information and make appropriate speed adjustments and route selections. However, a system with such capabilities has not yet been realized. This limits the operational efficiency and traffic safety of autonomous vehicles.

[1136] 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.

[1137] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for transmitting the signal change timing to an onboard computer of an autonomous vehicle to adjust the vehicle's speed and select a route, and means for controlling the traffic lights based on the received signal change timing. This enables an autonomous vehicle to obtain signal timing information in real time as it approaches an intersection and to adjust its speed and select a route appropriately.

[1138] A "monitoring device" is a device that is installed on roads and intersections and periodically captures video data.

[1139] The "receiving means" is a function or device that receives video data transmitted from a monitoring device.

[1140] The "analyzing means" is a function or device for detecting vehicles and pedestrians based on the received video data.

[1141] An "on-board computer" is a computer system installed in an autonomous vehicle that controls the vehicle and performs communication.

[1142] "Signal change timing" is information that indicates the lighting time of a traffic signal and the timing of the change.

[1143] The "calculating means" is a function or device that calculates the optimal signal change timing based on the detection results.

[1144] A "traffic light control device" is a device that controls the lighting state of a traffic signal based on the calculated signal change timing.

[1145] "Speed ​​adjustment" refers to an operation or process for appropriately changing the speed of an autonomous vehicle.

[1146] "Route selection" is the process of determining the optimal route to reach a destination.

[1147] MODE FOR CARRYING OUT THE INVENTION

[1148] System configuration

[1149] The present invention is a system comprising a monitoring device, a server, an on-board computer of an autonomous driving vehicle, and a traffic light control device.

[1150] Hardware configuration

[1151] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[1152] Server: A device that receives video data, analyzes it, and calculates and transmits the signal change timing.

[1153] On-board computer: A computer system installed in an autonomous vehicle that receives signal change timing and adjusts the vehicle's speed and route selection.

[1154] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1155] Software configuration

[1156] Data reception software: Software that runs on the server to receive video data from the surveillance device.

[1157] Generative AI model: An AI model that analyzes image data and detects vehicles and pedestrians. Specific examples include YOLO and Faster R-CNN.

[1158] Signal change timing calculation software: Software that calculates the optimal signal change timing based on analysis results.

[1159] Communication software: Software for data communication between the server, traffic light control device, and on-board computer.

[1160] Data processing and calculation

[1161] The monitoring device periodically captures video data, compresses it, and sends it to a server. The server inputs the received video data into a generative AI model to detect vehicles and pedestrians. The detection results provide each object's location information (bounding box coordinates) and class type (vehicle or pedestrian). The server aggregates multiple analysis results and calculates traffic volume within a specific time range. Based on this, it calculates the optimal signal change timing and sends it to the traffic light control device. At the same time, this signal change timing is also sent to the autonomous vehicle's onboard computer, which adjusts the vehicle's speed and selects its route.

[1162] Specific scenarios

[1163] A specific scenario is shown below.

[1164] A system in which monitoring devices are installed at an intersection and data from these monitoring devices is used to control traffic lights.

[1165] 1. The monitoring device captures video every second and sends it to the server.

[1166] 2. The server receives the captured video data and inputs it into the generative AI model.

[1167] 3. The AI ​​model detects vehicles and pedestrians and identifies the location and number of each object.

[1168] 4. The server aggregates the analysis results and calculates the average traffic volume.

[1169] 5. Set the green light to 30 seconds for the direction with heavy traffic and 15 seconds for the direction with light traffic, and send this information to the traffic light control device and the onboard computer of the autonomous vehicle.

[1170] 6. The traffic light controller controls the traffic light based on the new timing settings.

[1171] 7. The onboard computer of an autonomous vehicle will adjust speed and select a route based on the received signal change timing.

[1172] Prompt Sentence Examples

[1173] Prompt: "Identify the number and location of vehicles and pedestrians in this image."

[1174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1175] Step 1:

[1176] The terminal (monitoring device) captures video data every second. The video data is recorded as a still image and temporarily saved in the terminal. This video data is the input and becomes the first captured image.

[1177] Step 2:

[1178] The device compresses the captured video data and sends it to the server, where the compression process is performed to transfer the video data efficiently. The input is the captured video data, and the output is the compressed video data.

[1179] Step 3:

[1180] The server receives the compressed video data sent from the terminal. The received data is temporarily stored. The input is the compressed video data, and the output is the video data stored on the server.

[1181] Step 4:

[1182] The server inputs the received video data into a generative AI model (e.g., YOLO or Faster R-CNN) and performs image analysis. The generative AI model detects vehicles and pedestrians and outputs the location information (bounding box coordinates) and classification (vehicle or pedestrian) of each object. The input is the video data, and the output is the detection results.

[1183] Step 5:

[1184] The server aggregates the detection results from the generative AI model and calculates traffic volume for multiple timestamps. Specifically, it calculates the number of vehicles and pedestrians over the past few seconds and averages them. The input is the detection results, and the output is the aggregated traffic volume data.

[1185] Step 6:

[1186] The server calculates the optimal signal change timing based on traffic volume data. For example, it sets a longer green light time for directions with a high volume of vehicles, and also takes into account the timing when there are a lot of pedestrians. The input is traffic volume data, and the output is the calculated signal change timing.

[1187] Step 7:

[1188] The server sends the calculated signal change timing to the traffic light control device and the on-board computer of the autonomous vehicle. The input is the calculated signal change timing, and the output is the completion of transmission to the traffic light control device and the on-board computer.

[1189] Step 8:

[1190] The traffic light control device controls traffic signals based on the new signal change timing received from the server. Specifically, it adaptively changes the lighting state of each signal according to the timing. The input is the signal change timing, and the output is the updated traffic signal.

[1191] Step 9:

[1192] The onboard computer of an autonomous vehicle adjusts speed and selects a route based on the signal change timing received from the server. Specifically, it calculates the optimal speed taking into account the received signal change timing and controls the vehicle to match that speed. It also re-plans the route as necessary. The input is the signal change timing, and the output is speed adjustment and route selection.

[1193] 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.

[1194] This invention is a system that realizes more advanced and flexible traffic management by incorporating an emotion engine in addition to a traffic volume analysis system using surveillance cameras and generative AI, and reflecting the results of user emotion recognition in signal control. This system not only keeps traffic flow smooth, but also makes it possible to provide more appropriate reactions and warnings to traffic conditions.

[1195] System configuration

[1196] The system consists of the following elements:

[1197] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[1198] Server: A device that receives video data and analyzes it using generative AI. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[1199] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1200] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[1201] Explanation of program processing

[1202] Acquiring camera footage

[1203] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second). The captured images are recorded as still images.

[1204] The terminal compresses the captured image data and sends it to the server.

[1205] Image analysis

[1206] The server receives the image data sent from the terminal.

[1207] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[1208] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1209] Determining signal timing

[1210] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[1211] The server calculates the timing of the next traffic light change based on traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[1212] User Emotion Recognition

[1213] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[1214] The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[1215] Emotion-based traffic light control adjustment

[1216] The server can further fine-tune the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow.

[1217] The server transmits the final signal change timing information to the signal control device.

[1218] Traffic light control

[1219] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[1220] Specific examples

[1221] scenario

[1222] An environment in which three surveillance cameras are installed at an intersection and a traffic manager (user) monitors the system.

[1223] Camera footage acquisition:

[1224] The terminal (surveillance camera) captures video every second and sends it to the server.

[1225] Image analysis:

[1226] The server receives the captured video data and inputs it into a generative AI model.

[1227] The AI ​​model detects five vehicles and two pedestrians.

[1228] Determining signal timing:

[1229] The server aggregates the analysis results and calculates the average traffic volume.

[1230] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[1231] User Emotion Recognition:

[1232] The server recognizes the emotions of the traffic manager (user) through the user interface.

[1233] The emotion engine recognizes that the user is feeling a little stressed.

[1234] Emotion-based adjustment of traffic light control:

[1235] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[1236] The server transmits the final signal change timing information to the signal control device.

[1237] Signal Control:

[1238] The traffic light controller controls the traffic light based on the new timing settings.

[1239] The present invention makes it possible to optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[1240] The processing flow will be explained below.

[1241] Step 1:

[1242] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[1243] Step 2:

[1244] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[1245] Step 3:

[1246] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[1247] Step 4:

[1248] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[1249] Step 5:

[1250] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1251] Step 6:

[1252] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[1253] Step 7:

[1254] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[1255] Step 8:

[1256] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[1257] Step 9:

[1258] The server analyzes the emotion recognition results and outputs the user's emotional state (e.g., anger, sadness, joy).

[1259] Step 10:

[1260] The server fine-tunes the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server will change the timing of traffic lights to further smooth traffic flow.

[1261] Step 11:

[1262] The server sends the final signal change timing information to the signal controller using HTTP or other protocols.

[1263] Step 12:

[1264] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[1265] Step 13:

[1266] Users (traffic managers) can monitor the system's operating status and signal fluctuations in real time, and can manually intervene and change settings as needed.

[1267] With this detailed processing flow, the present invention can optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[1268] Example 2

[1269] 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."

[1270] Conventional traffic management systems have difficulty adaptively controlling traffic signals in response to changes in traffic volume, often preventing smooth traffic flow. Furthermore, traffic signal control does not take into account the emotions of traffic managers, requiring flexible responses in real time. Furthermore, analysis based on video data from individual surveillance cameras makes it difficult to comprehensively grasp the traffic situation across all intersecting roads. To solve these issues, a new system with advanced analytical capabilities and emotion recognition functions is needed.

[1271] 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.

[1272] In this invention, the server includes means for receiving image data acquired from the monitoring device, means for analyzing the received image data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to the signal control device, means for recognizing the user's emotion, and means for adjusting the signal change timing based on the recognized emotion. This enables real-time analysis of traffic conditions and flexible signal control, and also enables signal adjustment that reflects the user's emotion, enabling more advanced and smoother traffic management overall.

[1273] A "surveillance device" is a device that periodically captures images of roads and intersections.

[1274] "Image data" refers to video information of roads and intersections captured by a monitoring device.

[1275] The "server" is a device that analyzes the received image data, detects vehicles and pedestrians, and performs the calculations and adjustments necessary for traffic light control.

[1276] "Detection" is the process of identifying specific objects (e.g., vehicles or pedestrians) from image data and extracting their location information.

[1277] "Signal change timing" refers to the time allocation for an intersection's traffic lights to switch between red, green, and yellow.

[1278] A "signal control device" is a device that controls the display of traffic signals based on instructions from a server.

[1279] "User emotion" refers to the emotional state, such as joy, anger, or stress, that a traffic manager feels while operating the system.

[1280] "Recognition" is the process of analyzing and identifying a user's emotional state.

[1281] "Adjusting change timing" refers to recalculating and optimizing the existing signal change timing based on user sentiment.

[1282] "Traffic conditions" refers to the flow and volume of vehicles and pedestrians on a particular road or intersection.

[1283] "Real-time" refers to the time frame in which the system responds immediately without delay.

[1284] The present invention is a system that incorporates an emotion engine in addition to a traffic volume analysis system that uses a monitoring device and a generative AI model, thereby reflecting the results of user emotion recognition in signal control and achieving more advanced and flexible traffic management. The following describes in detail the embodiments of the present invention.

[1285] System configuration

[1286] The system consists of the following elements:

[1287] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video.

[1288] Server: A device that receives video data and analyzes it using a generative AI model. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[1289] Signal control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1290] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[1291] Acquiring camera footage

[1292] The terminal (monitoring device) captures video of roads and intersections at regular intervals (for example, every second). The captured video is recorded as a still image. The terminal compresses the captured image data and sends it to the server.

[1293] Image analysis

[1294] The server receives image data sent from the device. The server inputs the received video data into a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The generative AI model identifies the location and number of vehicles and pedestrians in the image and outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1295] Determining signal timing

[1296] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).The server then calculates the timing of the next traffic light change based on the traffic volume data.For example, it may set the green light to 30 seconds for directions with a high volume of vehicles, and 15 seconds for directions with a low volume of vehicles.

[1297] User Emotion Recognition

[1298] The server uses an emotion engine to recognize the emotions of the user (traffic manager). This emotion recognition is performed by analyzing camera footage and audio data obtained through the user interface. The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[1299] Emotion-based traffic light control adjustment

[1300] The server can fine-tune the timing of traffic light control based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow. The server then sends the final traffic light change timing information to the traffic light control device.

[1301] Traffic light control

[1302] The traffic signal control device controls the display of traffic signals based on the new signal change timing received from the server, which enables adaptive changes of traffic signals in real time.

[1303] Specific examples

[1304] scenario

[1305] An environment in which three monitoring devices are installed at an intersection and a traffic manager (user) monitors the system.

[1306] Camera footage acquisition:

[1307] The terminal (monitoring device) captures video every second and sends it to the server.

[1308] Image analysis:

[1309] The server receives the captured video data and inputs it into a generative AI model.

[1310] The AI ​​model detects five vehicles and two pedestrians.

[1311] Determining signal timing:

[1312] The server aggregates the analysis results and calculates the average traffic volume.

[1313] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[1314] User Emotion Recognition:

[1315] The server recognizes the emotions of the traffic manager (user) through the user interface.

[1316] The emotion engine recognizes that the user is feeling a little stressed.

[1317] Emotion-based adjustment of traffic light control:

[1318] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[1319] The server transmits the final signal change timing information to the signal control device.

[1320] Signal Control:

[1321] The signal controller controls the signal based on the new timing settings.

[1322] Prompt Sentence Examples

[1323] "How many vehicles and pedestrians are in this footage?"

[1324] "Please provide location information for each vehicle and pedestrian."

[1325] This invention makes it possible to optimize traffic flow and realize advanced signal control that takes into account user emotions.

[1326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1327] Processing Steps

[1328] Step 1: Acquire camera footage

[1329] Terminal (monitoring device):

[1330] Specific operation: The device captures video of roads and intersections every second. This captured video is recorded as a still image.

[1331] Input: Surrounding image (real-time road and intersection conditions)

[1332] Output: Collected still image data

[1333] The device will automatically activate the shutter and continuously capture the latest footage, temporarily storing it in its internal memory.

[1334] Step 2: Sending image data

[1335] Terminal (monitoring device):

[1336] Specific operation: The device reduces the captured still image data in a compressed format (e.g., JPEG, PNG) and sends it to the server.

[1337] Input: Collected still image data

[1338] Output: Compressed image data

[1339] Compression reduces the amount of data and begins the process of sending it over the network to the server.

[1340] Step 3: Image analysis

[1341] server:

[1342] Specific operation: The server receives image data sent from the device and inputs it into a generative AI model (e.g., YOLO, Faster R-CNN).

[1343] Input: Compressed image data

[1344] Output: Object detection results (position and class of each object)

[1345] The server uses a deep learning model to identify the location and number of vehicles and pedestrians in the image, resulting in bounding box coordinates and class information.

[1346] Step 4: Determine signal timing

[1347] server:

[1348] Specific operation: The server aggregates the analysis results within a certain time range (e.g., 10 seconds) and calculates traffic volume data.

[1349] Input: Object detection results (last 10 seconds of data)

[1350] Output: Optimal signal timing settings

[1351] The server queries the analysis results temporarily stored in a database, calculates the average number of vehicles and pedestrians, and then determines signal timing based on traffic volume data and generates new settings.

[1352] Step 5: Recognizing User Emotions

[1353] server:

[1354] Specific operation: The server recognizes the emotions of the traffic manager (user) through the user interface.

[1355] Input: Camera footage, audio data (user's facial expressions and voice)

[1356] Output: User's emotional state (e.g., happy, angry, stressed)

[1357] The server inputs data collected by the webcam and microphone into an emotion engine to classify and recognize the user's emotional state.

[1358] Step 6: Adjust traffic light control based on emotions

[1359] server:

[1360] Specific operation: The server fine-tunes the timing of traffic light control based on the user's emotion recognition results.

[1361] Input: User's emotional state, initial signal timing settings

[1362] Output: Adjusted signal timing settings

[1363] The server recalculates existing traffic light timing settings and makes adjustments, such as setting green lights longer if the user is feeling stressed.

[1364] Step 7: Controlling the Signal

[1365] Signal Control Equipment:

[1366] Specific operation: The signal controller operates the signal based on the new signal timing settings received from the server.

[1367] Input: Adjusted signal timing settings

[1368] Output: Change traffic light display

[1369] The signal controller implements the new timing settings and physically switches the traffic lights to update the traffic signals in real time.

[1370] (Application example 2)

[1371] 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."

[1372] Current traffic management systems primarily focus on analyzing traffic volume and optimizing signal control, without taking into account the emotional state of users. This invention aims to improve traffic management sophistication and flexibility by recognizing users' emotional states in real time and adjusting signal control based on that information, thereby not only maintaining smoother traffic flow but also reducing the stress of traffic managers. This technology can also be applied to brick-and-mortar stores where congestion is expected, improving the quality of service within the store.

[1373] The identification process 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 receiving video data acquired from a surveillance camera, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for controlling signals based on the received signal change timing, means including an emotion engine for recognizing the user's emotional state, and means for adjusting signal control based on the recognized emotional state. This enables flexible and advanced signal control based on the emotional state of the traffic manager, thereby maintaining smooth traffic flow and contributing to reducing stress for the traffic manager. Furthermore, even in physical stores, service quality can be improved by recognizing and responding to customers' emotional states in real time.

[1374] Key Word Definitions

[1375] A "surveillance camera" is a device that captures images of specific areas such as roads, intersections, and inside stores in real time and transmits the data to a server.

[1376] "Video data" is digital data containing image information captured by a surveillance camera.

[1377] The "receiving means" is a device or process that has the function of allowing the server to acquire the video data transmitted from the surveillance camera.

[1378] "Means for analysis" refers to algorithms and programs for detecting vehicles and pedestrians based on received video data.

[1379] "Vehicle and pedestrian detection" is the process of identifying the locations of vehicles and pedestrians based on video data.

[1380] "Signal change timing" refers to the time setting for changing the traffic signal display to red, yellow, green, etc.

[1381] "Calculation means" refers to an algorithm or program for determining the optimal timing for signal change based on the analysis results.

[1382] A "traffic light control device" is a device that operates traffic signals based on the signal change timing transmitted from the server.

[1383] The "control means" refers to a function that enables the traffic light control device to actually change the display of the traffic light in accordance with the signal change timing instructed.

[1384] An "emotion engine" is a system that analyzes and recognizes the emotional state expressed by a user (e.g., a traffic manager or a store clerk) through video and audio.

[1385] "Emotional state" refers to a range of emotions (e.g., anger, sadness, joy, stress, etc.) exhibited by a user.

[1386] "Means for adjusting" refers to a process or function by which the server changes or fine-tunes the signal control timing based on the emotional state recognized by the emotion engine.

[1387] MODE FOR CARRYING OUT THE INVENTION

[1388] The present invention aims to improve traffic management and services in brick-and-mortar stores by using a system that combines surveillance cameras, generative AI, and an emotion engine. Details of practical embodiments for carrying out the present invention are provided below.

[1389] System configuration

[1390] This system consists of the following elements:

[1391] 1. Surveillance cameras:

[1392] Surveillance cameras are installed in specific areas (e.g., intersections or inside stores), capture video in real time, and send it to a server.

[1393] 2. Server:

[1394] The server receives and analyzes the video data sent from the surveillance camera.

[1395] The generative AI used for analysis uses image recognition models (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians and recognize the emotional state of customers.

[1396] To recognize the customer's emotional state, video and audio are analyzed through an emotion engine.

[1397] The server calculates the signal change timing and transmits it to the signal control device.

[1398] The server adjusts the signal control based on the emotional state.

[1399] 3. Traffic light controller:

[1400] The traffic light control device controls the traffic light based on the signal change timing received from the server.

[1401] 4. Smart Glasses (Brick-and-mortar application):

[1402] The smart glasses are a device worn by store clerks to display feedback from the server in real time.

[1403] Major hardware and software used

[1404] Hardware:

[1405] surveillance cameras

[1406] server

[1407] Traffic light control device

[1408] Smart Glasses

[1409] software:

[1410] Generative AI models for image analysis (YOLO, Faster R-CNN, etc.)

[1411] Models for emotion recognition

[1412] Analysis and control program for servers

[1413] Program processing explanation

[1414] 1. Acquiring camera footage:

[1415] The terminal (surveillance camera) captures images of roads, intersections, and inside stores and sends the data to a server.

[1416] 2. Image and Sentiment Analysis:

[1417] The server inputs the video data received from the surveillance camera into a generative AI model to detect vehicles and pedestrians and analyze congestion levels.

[1418] At the same time, an emotion engine is used to analyze the emotional state of the user (traffic manager or store clerk), which is obtained from video and audio.

[1419] 3. Determining and coordinating signal control:

[1420] The server calculates the timing of traffic light changes based on the results of image analysis, and adjusts traffic light control based on the results of the emotion engine.

[1421] For example, if a traffic manager is feeling stressed, they will adjust the timing of traffic lights to ensure smooth traffic flow.

[1422] 4. Feedback:

[1423] The server transmits the calculated signal change timing and emotion-based adjustment results to the signal controller and the smart glasses.

[1424] The smart glasses will provide store staff with appropriate feedback in real time and be used to assist customers.

[1425] Specific examples

[1426] For example, a surveillance camera system installed at a certain intersection performs the following process.

[1427] Video capture: The surveillance camera captures video every second and sends it to the server.

[1428] Congestion analysis: The server analyzes the video data and analyzes traffic volume.

[1429] Emotion Recognition: The emotion engine recognizes the stress state of traffic managers.

[1430] Feedback: Adjust signal timing to keep traffic flowing smoothly.

[1431] In addition, even in brick-and-mortar stores, store clerks wearing smart glasses can grasp the emotional state of customers and respond quickly and appropriately.

[1432] Prompt Sentence Examples

[1433] "Analyze in-store video data to recognize the current crowding situation and the emotional state of customers. Design a system that gives real-time feedback to store staff when it is crowded or customers are stressed."

[1434] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1435] Specific explanation of processing steps

[1436] Processing Steps

[1437] Step 1:

[1438] Video data is captured from a surveillance camera and sent to a server. The surveillance camera captures video every second and compresses and stores it as digital data. The camera then sends this data to the server via a network.

[1439] Step 2:

[1440] The server receives the video data transmitted from the surveillance camera via the network interface and temporarily stores the digital data in memory.

[1441] Step 3:

[1442] The received video data is input into a generative AI model to detect vehicles and pedestrians. The server inputs the digital data into a deep learning model (e.g., YOLO, Faster R-CNN), and the model outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of vehicles and pedestrians in the video.

[1443] Step 4:

[1444] The analysis results from multiple surveillance cameras are aggregated to calculate traffic volume data. The server aggregates the analysis results sent from each camera and calculates the number of vehicles and pedestrians within a specific time range (e.g., the past 10 seconds).

[1445] Step 5:

[1446] Calculates the optimal timing for signal change based on traffic volume data. The server uses a specific algorithm to calculate the timing for the next signal change based on the calculated traffic volume data. For example, it sets a longer green light time for directions with heavy traffic volume.

[1447] Step 6:

[1448] The server activates an emotion engine to recognize the user's emotional state and obtains the analysis results. The server inputs the video and audio data obtained from the user interface or smart glasses into the emotion engine and obtains the user's emotional state (e.g., anger, joy, stress, etc.).

[1449] Step 7:

[1450] The server adjusts traffic light control based on the recognized emotional state. Based on the acquired emotional state information, the server recalculates the timing of traffic light changes and makes fine adjustments as needed. For example, if the operator is feeling stressed, the green light time will be extended to allow traffic to flow more smoothly.

[1451] Step 8:

[1452] The calculated signal change timing and the emotion-based adjustment result are sent to the traffic light control device. The server then sends the final signal change timing data to the traffic light control device, which then controls the traffic light according to the instructions.

[1453] Step 9:

[1454] The analysis results and recommended actions are displayed as feedback on the smart glasses. The server sends the analysis results and recommended actions (e.g., "The customer is angry" or "The store is crowded") as feedback to the smart glasses, and displays them in real time.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] [Fourth embodiment]

[1459] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1460] 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.

[1461] 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).

[1462] 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.

[1463] 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.

[1464] 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).

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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."

[1472] The present invention is a system that uses surveillance cameras and generative AI to analyze traffic volume and control traffic signals at appropriate times. This system aims to smooth traffic flow, alleviate congestion, and reduce carbon dioxide emissions. A specific embodiment of this system is described below.

[1473] System configuration

[1474] The system consists of the following elements:

[1475] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[1476] Server: A device that receives video data and analyzes it using generative AI.

[1477] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1478] Explanation of program processing

[1479] Acquiring camera footage

[1480] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[1481] The terminal compresses the captured image data and sends it to the server.

[1482] Image analysis

[1483] The server receives the image data sent from the terminal.

[1484] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[1485] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1486] Determining signal timing

[1487] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range, for example, the average traffic volume for the past 10 seconds.

[1488] The server calculates the timing of the next traffic light change based on traffic volume data, for example, setting a longer green light time for directions with a higher volume of vehicles and taking into account the timing of pedestrians if they are present.

[1489] The server transmits the calculation results to the traffic light control device.

[1490] Traffic light control

[1491] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[1492] Specific examples

[1493] scenario

[1494] Three surveillance cameras are installed at an intersection, and the data from these cameras is used to control traffic lights.

[1495] Camera footage acquisition:

[1496] The terminal (surveillance camera) captures video every second and sends it to the server.

[1497] Image analysis:

[1498] The server receives the captured video data and inputs it into a generative AI model.

[1499] The AI ​​model detects five vehicles and two pedestrians.

[1500] Determining signal timing:

[1501] The server aggregates the analysis results and calculates the average traffic volume.

[1502] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[1503] Signal Control:

[1504] The server transmits timing information to the traffic light controller.

[1505] The terminal (traffic light controller) controls the signal based on the new timing settings.

[1506] This invention can optimize traffic flow, alleviate congestion, and reduce carbon dioxide emissions.

[1507] The processing flow will be explained below.

[1508] Step 1:

[1509] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[1510] Step 2:

[1511] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[1512] Step 3:

[1513] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[1514] Step 4:

[1515] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[1516] Step 5:

[1517] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1518] Step 6:

[1519] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[1520] Step 7:

[1521] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[1522] Step 8:

[1523] The server transmits the calculated signal change timing information to the traffic light controller using HTTP or other protocols.

[1524] Step 9:

[1525] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[1526] Step 10:

[1527] Users (traffic managers) can monitor the system's operating status and signal fluctuations, and can also manually intervene and change settings as needed.

[1528] Example 1

[1529] 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."

[1530] Conventional traffic signal control systems change signals at fixed timing, making it difficult to respond to changes in traffic volume in real time. As a result, traffic congestion in specific directions and overall traffic congestion are likely to occur, making efficient traffic management difficult. Furthermore, conventional systems do not realize adaptive signal control that reduces environmental impact and facilitates traffic flow.

[1531] 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.

[1532] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and using a generative AI model to detect vehicles and pedestrians, means for aggregating the detection results and calculating traffic volume, means for calculating optimal signal change timing based on the calculated traffic volume, means for transmitting the calculated signal change timing to a display control device, and means for controlling signals based on the received signal change timing, thereby enabling adaptive signal control in line with changes in traffic volume in real time.

[1533] A "monitoring device" is a device that monitors a specific area such as a road or intersection and periodically captures video data.

[1534] "Video data" refers to still images or video files captured by surveillance devices and used for traffic monitoring and analysis.

[1535] The "receiving means" refers to a communication interface or software function that allows the server to receive the video data transmitted from the monitoring device.

[1536] A "generative AI model" is an algorithm that uses deep learning techniques to detect and identify specific objects in image data, and is used to detect vehicles and pedestrians in traffic.

[1537] The "means for analyzing" is a software function in the server for detecting vehicles and pedestrians in the received video data using a generative AI model.

[1538] "Detection results" are the results of analysis by the generative AI model, and are information about the location and number of vehicles and pedestrians within a specific time period.

[1539] The "means for calculating traffic volume" is a software function in the server for aggregating the detection results and calculating the traffic volume (total number of vehicles and pedestrians) within a specific time range.

[1540] "Signal change timing" refers to the time at which a traffic signal changes from green to red or vice versa, and is calculated based on traffic volume data.

[1541] A "display control device" is a control unit that operates traffic lights and changes the signals at the appropriate times.

[1542] The "control means" is a function for changing the state of a signal based on the signal change timing received by the display control device from the server.

[1543] "Adaptive signal control" is a control method that dynamically adjusts the timing of signal switching according to real-time traffic conditions, and is used to optimize traffic flow.

[1544] This invention aims to improve traffic signal control by using a monitoring device and a generative AI model to analyze traffic volume in real time and realize adaptive signal control.

[1545] Overall system configuration

[1546] The system consists of the following components:

[1547] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[1548] Server: A device that receives video data and analyzes it using a generative AI model.

[1549] Display control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1550] Program processing explanation

[1551] Acquiring camera footage

[1552] The terminal (monitoring device) captures images of roads and intersections at regular intervals (for example, every second), and these images are recorded as still images.

[1553] Specifically, the camera uses sensors to adjust for the surrounding lighting environment and capture video, which is then saved in a format such as JPEG.

[1554] Sending image data

[1555] The terminal (monitoring device) compresses the captured image data and sends it to the server. Standard algorithms (e.g., JPEG compression) are used for compression to reduce the amount of data. The image data is then sent to the server via Wi-Fi or a wired network.

[1556] AI-based image analysis

[1557] The server receives image data sent from the device. The received data is input to a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The server feeds the image data to the input layer of the AI ​​model and obtains the detection results from the output layer.

[1558] Traffic volume data aggregation

[1559] The server aggregates the detected vehicle and pedestrian data. For example, it calculates traffic volume by averaging the number of vehicles and pedestrians in each image for the past 10 seconds. The server stores the detection results in a buffer every hour and periodically aggregates the data in the buffer.

[1560] Determining signal timing

[1561] The server calculates the next signal change timing based on aggregated traffic volume data, extending the green light time for directions with high vehicle traffic and taking into account pedestrian traffic. The server runs traffic engineering algorithms to determine the optimal signal timing.

[1562] Signal timing transmission

[1563] The server sends the calculation results to the display control device. The communication uses a secure protocol (e.g., TLS) to ensure data integrity and safety. The server also sends timing information to the control device via TCP / IP communication.

[1564] Traffic light control

[1565] The display control device controls the traffic signal based on the new signal change timing received from the server. The traffic light control device sets a timer and changes the signal to green, yellow, or red at the determined timing. The control device operates a relay-type switch and controls the power supply to the traffic signal.

[1566] Specific examples

[1567] A specific example using this system is given below.

[1568] scenario

[1569] Three monitoring devices are installed at an intersection, and the data from these devices is used to control traffic lights.

[1570] Camera footage acquisition:

[1571] The terminal (monitoring device) captures images every second at Ryuo intersection and saves them as JPEG files.

[1572] Sending image data:

[1573] The terminal (monitoring device) sends the compressed image data to the server via Wi-Fi.

[1574] AI-powered image analysis:

[1575] The server inputs the received image data into the YOLO model and detects five vehicles and two pedestrians.

[1576] Traffic data aggregation:

[1577] The server aggregates data from the past 10 seconds and calculates the average traffic volume.

[1578] Determining signal timing:

[1579] The server sets the green light to 30 seconds for directions with a large number of vehicles and 15 seconds for directions with a small number of vehicles.

[1580] Transmitting signal timing:

[1581] The server transmits the calculation results to the display control device using a secure protocol.

[1582] Signal Control:

[1583] The display controller controls the traffic signals in real time based on the new signal timing settings.

[1584] Prompt Sentence Examples

[1585] "The number of vehicles and pedestrians is detected from the video data of the monitoring device installed at this intersection, and the timing of the traffic lights is optimized based on the results."

[1586] This system will optimize traffic flow, alleviate congestion, and reduce the burden on the environment.

[1587] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1588] Step 1: Acquire camera footage

[1589] The terminal (monitoring device) captures video of the road or intersection where it is installed every second. The input is light data from the terminal's camera sensor, and the output is still image data in JPEG format.

[1590] Specifically, the device's camera automatically adjusts exposure and white balance to capture video with optimal brightness and contrast, and the captured image is saved to internal memory.

[1591] Step 2: Compress and transmit image data

[1592] The terminal (monitoring device) compresses the captured image data and sends it to the server. The input is still image data in JPEG format, and the output is compressed image data.

[1593] Specifically, the device applies a standard compression algorithm (e.g., JPEG compression) to reduce the data volume, and then transmits the data to a server via Wi-Fi or a wired network.

[1594] Step 3: Receiving image data

[1595] The server receives image data sent from the terminal. The input is compressed image data, and the output is image data stored in an internal buffer.

[1596] Specifically, the server receives data packets using the TCP / IP protocol and stores them in its internal memory.

[1597] Step 4: Analyzing the image data

[1598] The server inputs the received image data into the generative AI model to detect vehicles and pedestrians. The input is the received image data, and the output is the location information (bounding box coordinates and class) of the detected vehicles and pedestrians.

[1599] Specifically, the server feeds image data to the input layer of an AI model (e.g., YOLO, Faster R-CNN). The AI ​​model performs image analysis through a neural network and obtains detection results from the output layer. The results are stored in the server's memory in list format.

[1600] Step 5: Aggregating traffic data

[1601] The server aggregates multiple analysis results and calculates traffic volume within a specific time range (e.g., the past 10 seconds). The input is a list of analysis results, and the output is traffic volume data (e.g., the number of vehicles and pedestrians at a certain point in time).

[1602] Specifically, the server repeatedly processes the analysis results stored in the buffer, sums up the number of vehicles and pedestrians for each result, and then calculates the average traffic volume over a certain period of time.

[1603] Step 6: Determine signal timing

[1604] The server calculates the next signal change timing based on the collected traffic volume data. The input is traffic volume data, and the output is the optimized signal change timing.

[1605] Specifically, the server runs traffic engineering algorithms, such as extending the green light time in directions with high vehicle traffic volume and taking into account pedestrian traffic timing. The results are stored in internal memory.

[1606] Step 7: Sending signal timing

[1607] The server sends the calculated signal change timing to the display control device, where the input is the optimized signal change timing and the output is the control command sent to the control device.

[1608] Specifically, the server transmits the signal timing information to the display controller using a secure communication protocol (eg, TLS).

[1609] Step 8: Controlling the Signal

[1610] The display control device controls traffic signals based on the signal change timing received from the server. The input is the signal change timing information, and the output is the actual traffic signal display status (switching between green, yellow, and red).

[1611] Specifically, the control device sets a signal timer and changes the signal appropriately at the determined timing. The control device also operates a relay-type switch to control the power supply to the signal light.

[1612] (Application example 1)

[1613] 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."

[1614] Current traffic signal control systems have difficulty detecting vehicles and pedestrians in real time and responding immediately to changes in traffic volume. Furthermore, when autonomous vehicles approach an intersection, they need to instantly obtain signal timing information and make appropriate speed adjustments and route selections. However, a system with such capabilities has not yet been realized. This limits the operational efficiency and traffic safety of autonomous vehicles.

[1615] 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.

[1616] In this invention, the server includes means for receiving video data acquired from a monitoring device, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for transmitting the signal change timing to an onboard computer of an autonomous vehicle to adjust the vehicle's speed and select a route, and means for controlling the traffic lights based on the received signal change timing. This enables an autonomous vehicle to obtain signal timing information in real time as it approaches an intersection and to adjust its speed and select a route appropriately.

[1617] A "monitoring device" is a device that is installed on roads and intersections and periodically captures video data.

[1618] The "receiving means" is a function or device that receives video data transmitted from a monitoring device.

[1619] The "analyzing means" is a function or device for detecting vehicles and pedestrians based on the received video data.

[1620] An "on-board computer" is a computer system installed in an autonomous vehicle that controls the vehicle and performs communication.

[1621] "Signal change timing" is information that indicates the lighting time of a traffic signal and the timing of the change.

[1622] The "calculating means" is a function or device that calculates the optimal signal change timing based on the detection results.

[1623] A "traffic light control device" is a device that controls the lighting state of a traffic signal based on the calculated signal change timing.

[1624] "Speed ​​adjustment" refers to an operation or process for appropriately changing the speed of an autonomous vehicle.

[1625] "Route selection" is the process of determining the optimal route to reach a destination.

[1626] MODE FOR CARRYING OUT THE INVENTION

[1627] System configuration

[1628] The present invention is a system comprising a monitoring device, a server, an on-board computer of an autonomous driving vehicle, and a traffic light control device.

[1629] Hardware configuration

[1630] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video data.

[1631] Server: A device that receives video data, analyzes it, and calculates and transmits the signal change timing.

[1632] On-board computer: A computer system installed in an autonomous vehicle that receives signal change timing and adjusts the vehicle's speed and route selection.

[1633] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1634] Software configuration

[1635] Data reception software: Software that runs on the server to receive video data from the surveillance device.

[1636] Generative AI model: An AI model that analyzes image data and detects vehicles and pedestrians. Specific examples include YOLO and Faster R-CNN.

[1637] Signal change timing calculation software: Software that calculates the optimal signal change timing based on analysis results.

[1638] Communication software: Software for data communication between the server, traffic light control device, and on-board computer.

[1639] Data processing and calculation

[1640] The monitoring device periodically captures video data, compresses it, and sends it to a server. The server inputs the received video data into a generative AI model to detect vehicles and pedestrians. The detection results provide each object's location information (bounding box coordinates) and class type (vehicle or pedestrian). The server aggregates multiple analysis results and calculates traffic volume within a specific time range. Based on this, it calculates the optimal signal change timing and sends it to the traffic light control device. At the same time, this signal change timing is also sent to the autonomous vehicle's onboard computer, which adjusts the vehicle's speed and selects its route.

[1641] Specific scenarios

[1642] A specific scenario is shown below.

[1643] A system in which monitoring devices are installed at an intersection and data from these monitoring devices is used to control traffic lights.

[1644] 1. The monitoring device captures video every second and sends it to the server.

[1645] 2. The server receives the captured video data and inputs it into the generative AI model.

[1646] 3. The AI ​​model detects vehicles and pedestrians and identifies the location and number of each object.

[1647] 4. The server aggregates the analysis results and calculates the average traffic volume.

[1648] 5. Set the green light to 30 seconds for the direction with heavy traffic and 15 seconds for the direction with light traffic, and send this information to the traffic light control device and the onboard computer of the autonomous vehicle.

[1649] 6. The traffic light controller controls the traffic light based on the new timing settings.

[1650] 7. The onboard computer of an autonomous vehicle will adjust speed and select a route based on the received signal change timing.

[1651] Prompt Sentence Examples

[1652] Prompt: "Identify the number and location of vehicles and pedestrians in this image."

[1653] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1654] Step 1:

[1655] The terminal (monitoring device) captures video data every second. The video data is recorded as a still image and temporarily saved in the terminal. This video data is the input and becomes the first captured image.

[1656] Step 2:

[1657] The device compresses the captured video data and sends it to the server, where the compression process is performed to transfer the video data efficiently. The input is the captured video data, and the output is the compressed video data.

[1658] Step 3:

[1659] The server receives the compressed video data sent from the terminal. The received data is temporarily stored. The input is the compressed video data, and the output is the video data stored on the server.

[1660] Step 4:

[1661] The server inputs the received video data into a generative AI model (e.g., YOLO or Faster R-CNN) and performs image analysis. The generative AI model detects vehicles and pedestrians and outputs the location information (bounding box coordinates) and classification (vehicle or pedestrian) of each object. The input is the video data, and the output is the detection results.

[1662] Step 5:

[1663] The server aggregates the detection results from the generative AI model and calculates traffic volume for multiple timestamps. Specifically, it calculates the number of vehicles and pedestrians over the past few seconds and averages them. The input is the detection results, and the output is the aggregated traffic volume data.

[1664] Step 6:

[1665] The server calculates the optimal signal change timing based on traffic volume data. For example, it sets a longer green light time for directions with a high volume of vehicles, and also takes into account the timing when there are a lot of pedestrians. The input is traffic volume data, and the output is the calculated signal change timing.

[1666] Step 7:

[1667] The server sends the calculated signal change timing to the traffic light control device and the on-board computer of the autonomous vehicle. The input is the calculated signal change timing, and the output is the completion of transmission to the traffic light control device and the on-board computer.

[1668] Step 8:

[1669] The traffic light control device controls traffic signals based on the new signal change timing received from the server. Specifically, it adaptively changes the lighting state of each signal according to the timing. The input is the signal change timing, and the output is the updated traffic signal.

[1670] Step 9:

[1671] The onboard computer of an autonomous vehicle adjusts speed and selects a route based on the signal change timing received from the server. Specifically, it calculates the optimal speed taking into account the received signal change timing and controls the vehicle to match that speed. It also re-plans the route as necessary. The input is the signal change timing, and the output is speed adjustment and route selection.

[1672] 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.

[1673] This invention is a system that realizes more advanced and flexible traffic management by incorporating an emotion engine in addition to a traffic volume analysis system using surveillance cameras and generative AI, and reflecting the results of user emotion recognition in signal control. This system not only keeps traffic flow smooth, but also makes it possible to provide more appropriate reactions and warnings to traffic conditions.

[1674] System configuration

[1675] The system consists of the following elements:

[1676] Surveillance camera: A device installed on roads or intersections that periodically captures video.

[1677] Server: A device that receives video data and analyzes it using generative AI. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[1678] Traffic light control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1679] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[1680] Explanation of program processing

[1681] Acquiring camera footage

[1682] The device (surveillance camera) captures images of roads and intersections at regular intervals (for example, every second). The captured images are recorded as still images.

[1683] The terminal compresses the captured image data and sends it to the server.

[1684] Image analysis

[1685] The server receives the image data sent from the terminal.

[1686] The server inputs the received video data into a generative AI to detect vehicles and pedestrians. The generative AI uses deep learning models (e.g., YOLO, Faster R-CNN) to identify the location and number of vehicles and pedestrians in the image.

[1687] As the analysis results, the server outputs the position information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1688] Determining signal timing

[1689] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[1690] The server calculates the timing of the next traffic light change based on traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[1691] User Emotion Recognition

[1692] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[1693] The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[1694] Emotion-based traffic light control adjustment

[1695] The server can further fine-tune the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow.

[1696] The server transmits the final signal change timing information to the signal control device.

[1697] Traffic light control

[1698] The traffic light control device controls the display of traffic lights based on the new signal change timing received from the server, which enables adaptive changes of traffic lights in real time.

[1699] Specific examples

[1700] scenario

[1701] An environment in which three surveillance cameras are installed at an intersection and a traffic manager (user) monitors the system.

[1702] Camera footage acquisition:

[1703] The terminal (surveillance camera) captures video every second and sends it to the server.

[1704] Image analysis:

[1705] The server receives the captured video data and inputs it into a generative AI model.

[1706] The AI ​​model detects five vehicles and two pedestrians.

[1707] Determining signal timing:

[1708] The server aggregates the analysis results and calculates the average traffic volume.

[1709] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[1710] User Emotion Recognition:

[1711] The server recognizes the emotions of the traffic manager (user) through the user interface.

[1712] The emotion engine recognizes that the user is feeling a little stressed.

[1713] Emotion-based adjustment of traffic light control:

[1714] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[1715] The server transmits the final signal change timing information to the signal control device.

[1716] Signal Control:

[1717] The traffic light controller controls the traffic light based on the new timing settings.

[1718] The present invention makes it possible to optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[1719] The processing flow will be explained below.

[1720] Step 1:

[1721] The device (surveillance camera) captures video of the intersection or road at regular intervals (for example, every second). The captured video is recorded as a still image.

[1722] Step 2:

[1723] The device compresses the captured image data and sends it to the server using a protocol such as an HTTP POST request.

[1724] Step 3:

[1725] The server receives the image data sent from the device, analyzes the HTTP request, and saves the image file in the appropriate directory.

[1726] Step 4:

[1727] The server inputs the received image data into a generative AI model, which uses deep learning algorithms (e.g., YOLO, Faster R-CNN) to identify the locations of vehicles and pedestrians in the image.

[1728] Step 5:

[1729] The server analyzes the detection results output by the AI ​​model and obtains the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1730] Step 6:

[1731] The server aggregates multiple analysis results and calculates traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).

[1732] Step 7:

[1733] The server calculates the optimal timing for changing traffic lights based on calculated traffic volume data. For example, the server may set the green light to 30 seconds for directions with a high volume of vehicles and 15 seconds for directions with a low volume of vehicles.

[1734] Step 8:

[1735] The server uses an emotion engine to recognize the emotions of the user (traffic manager) by analyzing camera images and audio data obtained through the user interface.

[1736] Step 9:

[1737] The server analyzes the emotion recognition results and outputs the user's emotional state (e.g., anger, sadness, joy).

[1738] Step 10:

[1739] The server fine-tunes the timing of traffic lights based on the user's emotion recognition results. For example, if the user is feeling stressed, the server will change the timing of traffic lights to further smooth traffic flow.

[1740] Step 11:

[1741] The server sends the final signal change timing information to the signal controller using HTTP or other protocols.

[1742] Step 12:

[1743] The traffic light controller appropriately controls the traffic light based on the traffic light change timing information received from the server, and changes the traffic light according to the new timing setting.

[1744] Step 13:

[1745] Users (traffic managers) can monitor the system's operating status and signal fluctuations in real time, and can manually intervene and change settings as needed.

[1746] With this detailed processing flow, the present invention can optimize traffic flow and realize advanced signal control that takes user emotions into consideration.

[1747] Example 2

[1748] 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."

[1749] Conventional traffic management systems have difficulty adaptively controlling traffic signals in response to changes in traffic volume, often preventing smooth traffic flow. Furthermore, traffic signal control does not take into account the emotions of traffic managers, requiring flexible responses in real time. Furthermore, analysis based on video data from individual surveillance cameras makes it difficult to comprehensively grasp the traffic situation across all intersecting roads. To solve these issues, a new system with advanced analytical capabilities and emotion recognition functions is needed.

[1750] 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.

[1751] In this invention, the server includes means for receiving image data acquired from the monitoring device, means for analyzing the received image data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to the signal control device, means for recognizing the user's emotion, and means for adjusting the signal change timing based on the recognized emotion. This enables real-time analysis of traffic conditions and flexible signal control, and also enables signal adjustment that reflects the user's emotion, enabling more advanced and smoother traffic management overall.

[1752] A "surveillance device" is a device that periodically captures images of roads and intersections.

[1753] "Image data" refers to video information of roads and intersections captured by a monitoring device.

[1754] The "server" is a device that analyzes the received image data, detects vehicles and pedestrians, and performs the calculations and adjustments necessary for traffic light control.

[1755] "Detection" is the process of identifying specific objects (e.g., vehicles or pedestrians) from image data and extracting their location information.

[1756] "Signal change timing" refers to the time allocation for an intersection's traffic lights to switch between red, green, and yellow.

[1757] A "signal control device" is a device that controls the display of traffic signals based on instructions from a server.

[1758] "User emotion" refers to the emotional state, such as joy, anger, or stress, that a traffic manager feels while operating the system.

[1759] "Recognition" is the process of analyzing and identifying a user's emotional state.

[1760] "Adjusting change timing" refers to recalculating and optimizing the existing signal change timing based on user sentiment.

[1761] "Traffic conditions" refers to the flow and volume of vehicles and pedestrians on a particular road or intersection.

[1762] "Real-time" refers to the time frame in which the system responds immediately without delay.

[1763] The present invention is a system that incorporates an emotion engine in addition to a traffic volume analysis system that uses a monitoring device and a generative AI model, thereby reflecting the results of user emotion recognition in signal control and achieving more advanced and flexible traffic management. The following describes in detail the embodiments of the present invention.

[1764] System configuration

[1765] The system consists of the following elements:

[1766] Surveillance equipment: Equipment installed on roads and intersections that periodically captures video.

[1767] Server: A device that receives video data and analyzes it using a generative AI model. It also uses an emotion engine to recognize user emotions and reflects the results in traffic light control.

[1768] Signal control device: A device that receives instructions from the server and controls traffic signals appropriately.

[1769] User interface: An interface that allows traffic managers to monitor the system status and intervene if necessary.

[1770] Acquiring camera footage

[1771] The terminal (monitoring device) captures video of roads and intersections at regular intervals (for example, every second). The captured video is recorded as a still image. The terminal compresses the captured image data and sends it to the server.

[1772] Image analysis

[1773] The server receives image data sent from the device. The server inputs the received video data into a generative AI model (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians. The generative AI model identifies the location and number of vehicles and pedestrians in the image and outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of each object.

[1774] Determining signal timing

[1775] The server aggregates the results of multiple analyses and calculates the traffic volume (number of vehicles and pedestrians) within a specific time range (e.g., the past 10 seconds).The server then calculates the timing of the next traffic light change based on the traffic volume data.For example, it may set the green light to 30 seconds for directions with a high volume of vehicles, and 15 seconds for directions with a low volume of vehicles.

[1776] User Emotion Recognition

[1777] The server uses an emotion engine to recognize the emotions of the user (traffic manager). This emotion recognition is performed by analyzing camera footage and audio data obtained through the user interface. The results of emotion recognition are output as emotional states such as anger, sadness, and joy.

[1778] Emotion-based traffic light control adjustment

[1779] The server can fine-tune the timing of traffic light control based on the user's emotion recognition results. For example, if the user is feeling stressed, the server can change the timing to further smooth traffic flow. The server then sends the final traffic light change timing information to the traffic light control device.

[1780] Traffic light control

[1781] The traffic signal control device controls the display of traffic signals based on the new signal change timing received from the server, which enables adaptive changes of traffic signals in real time.

[1782] Specific examples

[1783] scenario

[1784] An environment in which three monitoring devices are installed at an intersection and a traffic manager (user) monitors the system.

[1785] Camera footage acquisition:

[1786] The terminal (monitoring device) captures video every second and sends it to the server.

[1787] Image analysis:

[1788] The server receives the captured video data and inputs it into a generative AI model.

[1789] The AI ​​model detects five vehicles and two pedestrians.

[1790] Determining signal timing:

[1791] The server aggregates the analysis results and calculates the average traffic volume.

[1792] The green light will be set to 30 seconds in the direction of heavy traffic and 15 seconds in the direction of light traffic.

[1793] User Emotion Recognition:

[1794] The server recognizes the emotions of the traffic manager (user) through the user interface.

[1795] The emotion engine recognizes that the user is feeling a little stressed.

[1796] Emotion-based adjustment of traffic light control:

[1797] The server will adjust the timing to reduce user stress, for example by setting green lights longer to allow traffic to flow more smoothly.

[1798] The server transmits the final signal change timing information to the signal control device.

[1799] Signal Control:

[1800] The signal controller controls the signal based on the new timing settings.

[1801] Prompt Sentence Examples

[1802] "How many vehicles and pedestrians are in this footage?"

[1803] "Please provide location information for each vehicle and pedestrian."

[1804] This invention makes it possible to optimize traffic flow and realize advanced signal control that takes into account user emotions.

[1805] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1806] Processing Steps

[1807] Step 1: Acquire camera footage

[1808] Terminal (monitoring device):

[1809] Specific operation: The device captures video of roads and intersections every second. This captured video is recorded as a still image.

[1810] Input: Surrounding image (real-time road and intersection conditions)

[1811] Output: Collected still image data

[1812] The device will automatically activate the shutter and continuously capture the latest footage, temporarily storing it in its internal memory.

[1813] Step 2: Sending image data

[1814] Terminal (monitoring device):

[1815] Specific operation: The device reduces the captured still image data in a compressed format (e.g., JPEG, PNG) and sends it to the server.

[1816] Input: Collected still image data

[1817] Output: Compressed image data

[1818] Compression reduces the amount of data and begins the process of sending it over the network to the server.

[1819] Step 3: Image analysis

[1820] server:

[1821] Specific operation: The server receives image data sent from the device and inputs it into a generative AI model (e.g., YOLO, Faster R-CNN).

[1822] Input: Compressed image data

[1823] Output: Object detection results (position and class of each object)

[1824] The server uses a deep learning model to identify the location and number of vehicles and pedestrians in the image, resulting in bounding box coordinates and class information.

[1825] Step 4: Determine signal timing

[1826] server:

[1827] Specific operation: The server aggregates the analysis results within a certain time range (e.g., 10 seconds) and calculates traffic volume data.

[1828] Input: Object detection results (last 10 seconds of data)

[1829] Output: Optimal signal timing settings

[1830] The server queries the analysis results temporarily stored in a database, calculates the average number of vehicles and pedestrians, and then determines signal timing based on traffic volume data and generates new settings.

[1831] Step 5: Recognizing User Emotions

[1832] server:

[1833] Specific operation: The server recognizes the emotions of the traffic manager (user) through the user interface.

[1834] Input: Camera footage, audio data (user's facial expressions and voice)

[1835] Output: User's emotional state (e.g., happy, angry, stressed)

[1836] The server inputs data collected by the webcam and microphone into an emotion engine to classify and recognize the user's emotional state.

[1837] Step 6: Adjust traffic light control based on emotions

[1838] server:

[1839] Specific operation: The server fine-tunes the timing of traffic light control based on the user's emotion recognition results.

[1840] Input: User's emotional state, initial signal timing settings

[1841] Output: Adjusted signal timing settings

[1842] The server recalculates existing traffic light timing settings and makes adjustments, such as setting green lights longer if the user is feeling stressed.

[1843] Step 7: Controlling the Signal

[1844] Signal Control Equipment:

[1845] Specific operation: The signal controller operates the signal based on the new signal timing settings received from the server.

[1846] Input: Adjusted signal timing settings

[1847] Output: Change traffic light display

[1848] The signal controller implements the new timing settings and physically switches the traffic lights to update the traffic signals in real time.

[1849] (Application example 2)

[1850] 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."

[1851] Current traffic management systems primarily focus on analyzing traffic volume and optimizing signal control, without taking into account the emotional state of users. This invention aims to improve traffic management sophistication and flexibility by recognizing users' emotional states in real time and adjusting signal control based on that information, thereby not only maintaining smoother traffic flow but also reducing the stress of traffic managers. This technology can also be applied to brick-and-mortar stores where congestion is expected, improving the quality of service within the store.

[1852] The identification process 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 receiving video data acquired from a surveillance camera, means for analyzing the received video data and detecting vehicles and pedestrians, means for calculating optimal signal change timing based on the detection results, means for transmitting the calculated signal change timing to a traffic light control device, means for controlling signals based on the received signal change timing, means including an emotion engine for recognizing the user's emotional state, and means for adjusting signal control based on the recognized emotional state. This enables flexible and advanced signal control based on the emotional state of the traffic manager, thereby maintaining smooth traffic flow and contributing to reducing stress for the traffic manager. Furthermore, even in physical stores, service quality can be improved by recognizing and responding to customers' emotional states in real time.

[1853] Key Word Definitions

[1854] A "surveillance camera" is a device that captures images of specific areas such as roads, intersections, and inside stores in real time and transmits the data to a server.

[1855] "Video data" is digital data containing image information captured by a surveillance camera.

[1856] The "receiving means" is a device or process that has the function of allowing the server to acquire the video data transmitted from the surveillance camera.

[1857] "Means for analysis" refers to algorithms and programs for detecting vehicles and pedestrians based on received video data.

[1858] "Vehicle and pedestrian detection" is the process of identifying the locations of vehicles and pedestrians based on video data.

[1859] "Signal change timing" refers to the time setting for changing the traffic signal display to red, yellow, green, etc.

[1860] "Calculation means" refers to an algorithm or program for determining the optimal timing for signal change based on the analysis results.

[1861] A "traffic light control device" is a device that operates traffic signals based on the signal change timing transmitted from the server.

[1862] The "control means" refers to a function that enables the traffic light control device to actually change the display of the traffic light in accordance with the signal change timing instructed.

[1863] An "emotion engine" is a system that analyzes and recognizes the emotional state expressed by a user (e.g., a traffic manager or a store clerk) through video and audio.

[1864] "Emotional state" refers to a range of emotions (e.g., anger, sadness, joy, stress, etc.) exhibited by a user.

[1865] "Means for adjusting" refers to a process or function by which the server changes or fine-tunes the signal control timing based on the emotional state recognized by the emotion engine.

[1866] MODE FOR CARRYING OUT THE INVENTION

[1867] The present invention aims to improve traffic management and services in brick-and-mortar stores by using a system that combines surveillance cameras, generative AI, and an emotion engine. Details of practical embodiments for carrying out the present invention are provided below.

[1868] System configuration

[1869] This system consists of the following elements:

[1870] 1. Surveillance cameras:

[1871] Surveillance cameras are installed in specific areas (e.g., intersections or inside stores), capture video in real time, and send it to a server.

[1872] 2. Server:

[1873] The server receives and analyzes the video data sent from the surveillance camera.

[1874] The generative AI used for analysis uses image recognition models (e.g., YOLO, Faster R-CNN) to detect vehicles and pedestrians and recognize the emotional state of customers.

[1875] To recognize the customer's emotional state, video and audio are analyzed through an emotion engine.

[1876] The server calculates the signal change timing and transmits it to the signal control device.

[1877] The server adjusts the signal control based on the emotional state.

[1878] 3. Traffic light controller:

[1879] The traffic light control device controls the traffic light based on the signal change timing received from the server.

[1880] 4. Smart Glasses (Brick-and-mortar application):

[1881] The smart glasses are a device worn by store clerks to display feedback from the server in real time.

[1882] Major hardware and software used

[1883] Hardware:

[1884] surveillance cameras

[1885] server

[1886] Traffic light control device

[1887] Smart Glasses

[1888] software:

[1889] Generative AI models for image analysis (YOLO, Faster R-CNN, etc.)

[1890] Models for emotion recognition

[1891] Analysis and control program for servers

[1892] Program processing explanation

[1893] 1. Acquiring camera footage:

[1894] The terminal (surveillance camera) captures images of roads, intersections, and inside stores and sends the data to a server.

[1895] 2. Image and Sentiment Analysis:

[1896] The server inputs the video data received from the surveillance camera into a generative AI model to detect vehicles and pedestrians and analyze congestion levels.

[1897] At the same time, an emotion engine is used to analyze the emotional state of the user (traffic manager or store clerk), which is obtained from video and audio.

[1898] 3. Determining and coordinating signal control:

[1899] The server calculates the timing of traffic light changes based on the results of image analysis, and adjusts traffic light control based on the results of the emotion engine.

[1900] For example, if a traffic manager is feeling stressed, they will adjust the timing of traffic lights to ensure smooth traffic flow.

[1901] 4. Feedback:

[1902] The server transmits the calculated signal change timing and emotion-based adjustment results to the signal controller and the smart glasses.

[1903] The smart glasses will provide store staff with appropriate feedback in real time and be used to assist customers.

[1904] Specific examples

[1905] For example, a surveillance camera system installed at a certain intersection performs the following process.

[1906] Video capture: The surveillance camera captures video every second and sends it to the server.

[1907] Congestion analysis: The server analyzes the video data and analyzes traffic volume.

[1908] Emotion Recognition: The emotion engine recognizes the stress state of traffic managers.

[1909] Feedback: Adjust signal timing to keep traffic flowing smoothly.

[1910] In addition, even in brick-and-mortar stores, store clerks wearing smart glasses can grasp the emotional state of customers and respond quickly and appropriately.

[1911] Prompt Sentence Examples

[1912] "Analyze in-store video data to recognize the current crowding situation and the emotional state of customers. Design a system that gives real-time feedback to store staff when it is crowded or customers are stressed."

[1913] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1914] Specific explanation of processing steps

[1915] Processing Steps

[1916] Step 1:

[1917] Video data is captured from a surveillance camera and sent to a server. The surveillance camera captures video every second and compresses and stores it as digital data. The camera then sends this data to the server via a network.

[1918] Step 2:

[1919] The server receives the video data transmitted from the surveillance camera via the network interface and temporarily stores the digital data in memory.

[1920] Step 3:

[1921] The received video data is input into a generative AI model to detect vehicles and pedestrians. The server inputs the digital data into a deep learning model (e.g., YOLO, Faster R-CNN), and the model outputs the location information (bounding box coordinates) and class (vehicle or pedestrian) of vehicles and pedestrians in the video.

[1922] Step 4:

[1923] The analysis results from multiple surveillance cameras are aggregated to calculate traffic volume data. The server aggregates the analysis results sent from each camera and calculates the number of vehicles and pedestrians within a specific time range (e.g., the past 10 seconds).

[1924] Step 5:

[1925] Calculates the optimal timing for signal change based on traffic volume data. The server uses a specific algorithm to calculate the timing for the next signal change based on the calculated traffic volume data. For example, it sets a longer green light time for directions with heavy traffic volume.

[1926] Step 6:

[1927] The server activates an emotion engine to recognize the user's emotional state and obtains the analysis results. The server inputs the video and audio data obtained from the user interface or smart glasses into the emotion engine and obtains the user's emotional state (e.g., anger, joy, stress, etc.).

[1928] Step 7:

[1929] The server adjusts traffic light control based on the recognized emotional state. Based on the acquired emotional state information, the server recalculates the timing of traffic light changes and makes fine adjustments as needed. For example, if the operator is feeling stressed, the green light time will be extended to allow traffic to flow more smoothly.

[1930] Step 8:

[1931] The calculated signal change timing and the emotion-based adjustment result are sent to the traffic light control device. The server then sends the final signal change timing data to the traffic light control device, which then controls the traffic light according to the instructions.

[1932] Step 9:

[1933] The analysis results and recommended actions are displayed as feedback on the smart glasses. The server sends the analysis results and recommended actions (e.g., "The customer is angry" or "The store is crowded") as feedback to the smart glasses, and displays them in real time.

[1934] 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.

[1935] 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.

[1936] 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 robot 414.

[1937] 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.

[1938] FIG. 9 illustrates 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 behaviors 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.

[1939] 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.

[1940] 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).

[1941] 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.

[1942] 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."

[1943] 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.

[1944] 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).

[1945] 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.

[1946] 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.

[1947] 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.

[1948] 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.

[1949] 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.

[1950] 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.

[1951] 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.

[1952] 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.

[1953] 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.

[1954] 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.

[1955] The following is further disclosed regarding the above embodiment.

[1956] (Claim 1)

[1957] means for receiving video data acquired from a surveillance camera;

[1958] means for analyzing the received video data and detecting vehicles and pedestrians;

[1959] means for calculating an optimal signal change timing based on the detection result;

[1960] means for transmitting the calculated signal change timing to a traffic light control device;

[1961] means for controlling a signal based on the received signal change timing;

[1962] A system including:

[1963] (Claim 2)

[1964] 2. The system according to claim 1, further comprising means for aggregating video data from a plurality of surveillance cameras and comprehensively analyzing traffic volume at each intersection.

[1965] (Claim 3)

[1966] 10. The system of claim 1, further comprising means for monitoring changes in traffic volume in real time and updating signal change timings in a timely manner.

[1967] "Example 1"

[1968] (Claim 1)

[1969] means for receiving video data acquired from a monitoring device;

[1970] means for analyzing the received video data and using a generative AI model to detect vehicles and pedestrians;

[1971] a means for aggregating the detection results and calculating traffic volume;

[1972] means for calculating optimal signal change timing based on the calculated traffic volume;

[1973] means for transmitting the calculated signal change timing to a display control device;

[1974] means for controlling a signal based on the received signal change timing;

[1975] A system including:

[1976] (Claim 2)

[1977] 2. The system according to claim 1, further comprising means for aggregating video data from a plurality of monitoring devices and comprehensively analyzing traffic volume at each intersection.

[1978] (Claim 3)

[1979] 10. The system of claim 1, further comprising means for monitoring changes in traffic volume in real time and updating signal change timings in a timely manner.

[1980] "Application Example 1"

[1981] (Claim 1)

[1982] means for receiving video data acquired from a monitoring device;

[1983] means for analyzing the received video data and detecting vehicles and pedestrians;

[1984] means for calculating an optimal signal change timing based on the detection result;

[1985] means for transmitting the calculated signal change timing to a traffic light control device;

[1986] means for transmitting signal change timing to an on-board computer of the autonomous vehicle to adjust the speed and route of the vehicle;

[1987] means for controlling a signal based on the received signal change timing;

[1988] A system including:

[1989] (Claim 2)

[1990] 2. The system according to claim 1, further comprising means for aggregating video data from a plurality of monitoring devices and comprehensively analyzing traffic volume at each intersection.

[1991] (Claim 3)

[1992] 10. The system of claim 1, further comprising means for monitoring changes in traffic volume in real time and updating signal change timings in a timely manner.

[1993] "Example 2: Combining Emotion Engines"

[1994] (Claim 1)

[1995] means for receiving image data acquired from a monitoring device;

[1996] means for analyzing the received image data and detecting vehicles and pedestrians;

[1997] means for calculating an optimal signal change timing based on the detection result;

[1998] means for transmitting the calculated signal change timing to a signal control device;

[1999] means for operating a signal based on the received signal change timing;

[2000] means for recognizing a user's emotion;

[2001] means for adjusting signal change timing based on the recognized emotion;

[2002] A system including:

[2003] (Claim 2)

[2004] 2. The system according to claim 1, further comprising means for integrating image data from a plurality of monitoring devices and comprehensively analyzing the traffic volume of each intersecting road.

[2005] (Claim 3)

[2006] 10. The system of claim 1, further comprising means for monitoring changes in traffic volume in real time and updating signal change timings in a timely manner.

[2007] "Application example 2 when combining emotion engines"

[2008] (Claim 1)

[2009] means for receiving video data acquired from a surveillance camera;

[2010] means for analyzing the received video data and detecting vehicles and pedestrians;

[2011] means for calculating an optimal signal change timing based on the detection result;

[2012] means for transmitting the calculated signal change timing to a traffic light control device;

[2013] means for controlling a signal based on the received signal change timing;

[2014] means including an emotion engine for recognizing an emotional state of a user;

[2015] means for adjusting signal control based on the recognized emotional state;

[2016] A system including:

[2017] (Claim 2)

[2018] 2. The system according to claim 1, further comprising means for aggregating video data from a plurality of surveillance cameras and comprehensively analyzing traffic volume at each intersection.

[2019] (Claim 3)

[2020] 10. The system of claim 1, further comprising means for monitoring changes in traffic volume and user emotional state in real time and updating signal change timing and adjustments based on emotional state in a timely manner. [Explanation of symbols]

[2021] 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. means for receiving video data acquired from a surveillance camera; means for analyzing the received video data and detecting vehicles and pedestrians; means for calculating an optimal signal change timing based on the detection result; means for transmitting the calculated signal change timing to a traffic light control device; means for controlling a signal based on the received signal change timing; A system including:

2. 2. The system according to claim 1, further comprising means for aggregating video data from a plurality of surveillance cameras and comprehensively analyzing traffic volume at each intersection.

3. 10. The system of claim 1, further comprising means for monitoring changes in traffic volume in real time and updating signal change timings in a timely manner.

Images