System

Abstract

A system is provided.SOLUTION: A system including sensor means for detecting the speed and position of a pedestrian, artificial intelligence means for analyzing the detected speed and position data, control means for adjusting the green time of a signal based on the analysis results, support means for providing audio or visual support to the pedestrian based on the analysis results, and warning means for detecting abnormal conditions and alerting surrounding vehicles and pedestrians.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] There is a need to provide an environment that reduces the fear and anxiety felt by elderly people and people with walking difficulties when crossing busy intersections, enabling them to cross safely. Conventional traffic signal control at intersections is uniform and not adjusted to suit the individual circumstances of pedestrians, which can lead to danger for elderly people and people with walking difficulties, as they are unable to cross the intersection. Furthermore, the lack of audio and visual support for these people makes them prone to feeling anxious and stressed. Furthermore, there is no means in place to quickly notify those around them in the event of an emergency. The system provided by the present invention takes specific measures to solve these problems. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system including the following means.

[0006] First, a sensor means is installed to detect pedestrian speed and location, and pedestrian movement is monitored in real time. Next, an artificial intelligence means is used to analyze the detected speed and location data to determine whether the pedestrian is elderly or has difficulty walking. A control means is provided to automatically adjust the green light time of a traffic light based on this, and to extend the green light time as necessary. Furthermore, a support means is incorporated to provide audio or visual support to pedestrians based on the analysis results, ensuring their safety. Finally, a warning means is provided to detect abnormal conditions and issue alerts to surrounding vehicles and pedestrians, allowing for a rapid response when an abnormal situation occurs.

[0007] In this way, a system that combines sensor means, artificial intelligence means, control means, support means, and warning means can ensure the safety of elderly people and people with walking difficulties, reduce their anxiety, and enable them to cross intersections with peace of mind.

[0008] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[0009] "Artificial intelligence means" refers to algorithms and software that analyze detected speed and location data and identify elderly people and people with mobility impairments.

[0010] "Control means" refers to devices and systems for adjusting the green light time of traffic lights based on the analysis results of the artificial intelligence means.

[0011] "Support means" means equipment and systems for providing audio or visual on-site guidance to pedestrians based on the analysis results.

[0012] "Warning means" refers to devices and systems that detect abnormal conditions and issue alerts to surrounding vehicles and pedestrians.

[0013] A "pedestrian" is a human being passing through an intersection, and includes specific groups such as the elderly and people with mobility difficulties.

[0014] "Speed" is a parameter that indicates the distance traveled by a pedestrian per unit time.

[0015] "Position" is data indicating the physical position where a pedestrian currently exists within an intersection.

[0016] "Signal" means a traffic signal used to control traffic at an intersection.

[0017] A "green light" is a signal condition that indicates the time period during which pedestrians are permitted to cross an intersection safely. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. The system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, and a warning means.

[0040] System configuration

[0041] 1. Sensor means

[0042] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[0043] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[0044] 2. Artificial Intelligence Means

[0045] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[0046] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[0047] 3. Control Measures

[0048] The server operates the traffic light control module based on the results of the AI ​​analysis, specifically extending the green light time as needed.

[0049] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[0050] 4. Support measures

[0051] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[0052] The device adjusts the lighting within the intersection to visually alert pedestrians.

[0053] 5. Warning measures

[0054] The server monitors pedestrians' movements for any abnormalities and generates a warning signal if it detects any abnormalities.

[0055] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[0056] Program processing and specific examples

[0057] Photographing pedestrians by sensor means and preprocessing

[0058] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[0059] The server converts the pre-processed video into an input format for the AI ​​module.

[0060] Analysis of pedestrian speed and position using artificial intelligence means.

[0061] The server uses an AI module to detect pedestrians in the video and calculate the location coordinates and movement speed of each pedestrian.

[0062] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[0063] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[0064] The server uses specific criteria from the analysis results to identify elderly people and people with walking difficulties, and calculates the walking time required for those people.

[0065] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[0066] Support means audio guidance and lighting support

[0067] The server provides audio guidance and visual support at the appropriate time based on the pedestrian's location information.

[0068] The device operates the speaker system and lighting system to convey messages to pedestrians such as "Watch out for extended green lights."

[0069] Detect anomalies and issue alerts using warning methods

[0070] The server monitors pedestrians' movements for any abnormalities and detects any abnormalities such as sudden stops or falls.

[0071] When an abnormality is detected, the device generates a warning signal to notify vehicles and other pedestrians around the intersection.

[0072] Specific examples

[0073] Example 1:

[0074] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[0075] The server receives the camera footage and analyzes it using an AI module.

[0076] The device identifies elderly people and extends the green light time.

[0077] The server provides voice guidance regarding "extended green light."

[0078] Seniors can cross the intersection safely.

[0079] Example 2:

[0080] At 5pm, a person fell while trying to pass through an intersection.

[0081] The server detects an anomaly and generates an alert.

[0082] The device sends an alert to those around the intersection and issues an emergency stop signal.

[0083] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[0084] In this way, the system is highly integrated and offers a range of functions to ensure the safety of the elderly and those with mobility impairments.

[0085] The processing flow will be explained below.

[0086] Step 1:

[0087] The server acquires video data in real time from cameras installed at intersections, which are transmitted to the server via sensor means and passed to an image processing module for pre-processing.

[0088] Step 2:

[0089] The server performs preprocessing on the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, enabling the AI ​​to accurately recognize pedestrians.

[0090] Step 3:

[0091] The server inputs the preprocessed video data into the AI ​​module to detect pedestrians, which then calculates their location coordinates and movement speed in real time.

[0092] Step 4:

[0093] The server analyzes the data of detected pedestrians and identifies elderly people and those with walking difficulties, using information such as the pedestrian's speed, movement patterns, and posture stability.

[0094] Step 5:

[0095] The server calculates the walking time required for identified elderly people or people with walking difficulties, based on the speed of the pedestrian and the length of the intersection.

[0096] Step 6:

[0097] The terminal sets a new green signal time in the signal control module based on the analysis result received from the server, adding the required extension time to the current green signal time and setting the new green signal time in the traffic light.

[0098] Step 7:

[0099] The server generates voice guidance at appropriate times based on the pedestrian's location information, such as "The green light will be extended by 10 seconds from here" via a speaker system.

[0100] Step 8:

[0101] The device adjusts lighting within the intersection and provides visual support, drawing pedestrians' attention to safely cross the intersection.

[0102] Step 9:

[0103] The server monitors pedestrians' movements to see if there are any abnormalities. If the server detects any abnormal movements such as a sudden stop or a fall, it will recognize this as an abnormal situation.

[0104] Step 10:

[0105] When an abnormal condition is detected, the device generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection. Specifically, an emergency stop signal or an audio warning is issued.

[0106] Step 11:

[0107] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and take appropriate action, thereby ensuring safety when an abnormal situation occurs.

[0108] Example 1

[0109] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0110] When elderly people or people with walking difficulties cross intersections, they often lack the time to cross safely. In such cases, the risk of an accident increases. In addition, improper control of traffic signals can have a significant impact on other pedestrians and vehicles. Furthermore, rapid response is required in the event of pedestrians suddenly stopping or falling, or other abnormal behavior. It is necessary to solve these issues and ensure that all traffic participants can use intersections safely.

[0111] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0112] In this invention, the server includes a sensor for capturing pedestrian video in real time, a processing unit for preprocessing the captured video to detect the speed and location of pedestrians, an artificial intelligence unit for detecting pedestrians based on the preprocessed video data and analyzing their location and speed, a determination unit for identifying elderly people or people with walking difficulties and calculating the required walking time, a control unit for extending the green light time based on the calculated walking time, a support unit for providing audio guidance and visual support, a monitoring unit for detecting abnormal pedestrian behavior and generating a warning signal, and a notification unit for notifying the generated warning signal. This allows for an increase in the time required to safely cross an intersection as needed, allowing elderly people and people with walking difficulties to use the intersection safely. Furthermore, by quickly responding to abnormal behavior, the risk of accidents can be reduced.

[0113] "Sensor means" refers to a high resolution camera or other sensing device for acquiring video data in real time.

[0114] "Processing means" refers to a data processing device for pre-processing the acquired video data and detecting the velocity and position.

[0115] "Artificial intelligence means" refers to machine learning algorithms and models that analyze pre-processed video data and identify the location and speed of pedestrians.

[0116] "Determination means" refers to a device or algorithm that determines whether an elderly person or a person with walking difficulty is present based on the analysis results and calculates the walking time required for that person.

[0117] The "control means" refers to a traffic light control device that appropriately extends the green light time of a traffic light at an intersection based on the calculated walking time.

[0118] "Support means" refers to devices that provide audio guidance and visual support to pedestrians crossing an intersection.

[0119] "Monitoring means" refers to devices or systems that monitor pedestrian movement and detect abnormal behavior such as sudden stops or falls.

[0120] "Notification means" refers to a device for notifying vehicles and other pedestrians around the intersection of the generated warning signal.

[0121] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. This system is implemented by combining a sensor means, a processing means, an artificial intelligence means, a determination means, a control means, a support means, a monitoring means, and a notification means.

[0122] Program Generation and Processing Description

[0123] 1. Sensor means

[0124] The server acquires pedestrian video data in real time using high-resolution cameras installed at intersections. The cameras have a resolution of 1080p and capture video at 30 frames per second, enabling high-quality video acquisition.

[0125] 2. Processing Methods

[0126] The server preprocesses the acquired video data. Specifically, it uses the OpenCV library to remove noise from the video frames and correct the frame rate. For example, it uses a Gaussian filter to remove noise and stabilize the video frames.

[0127] 3. Artificial Intelligence Means

[0128] The server inputs the preprocessed video data into a machine learning algorithm (e.g., a CNN model using TensorFlow or PyTorch) to detect the location coordinates and movement speed of pedestrians. Specifically, it uses a pre-trained model such as ResNet to identify the location and speed by outputting the bounding box of the pedestrian.

[0129] 4. Judgment means

[0130] The server then uses the analysis results to determine whether a person is elderly or has difficulty walking. Criteria for this include walking speed of 0.5 m / s or less, and specific posture characteristics (e.g., leaning forward, using a cane). This improves the accuracy of detecting elderly people and people with difficulty walking.

[0131] 5. Control Measures

[0132] Based on the results of the judgment, the terminal accesses the intersection's signal control system and appropriately extends the green light time. For example, it sends the new green light extension time to a Siemens signal controller, which then controls the traffic lights.

[0133] 6. Support Measures

[0134] The server uses the Google Text-to-Speech API to generate an audio message that says, "The green light will be extended by 10 seconds," which is then played over the intersection's speakers. Additionally, as a visual aid, LED lights of a specific color flash to warn pedestrians.

[0135] The terminal controls Philips smart LED lights and adjusts the lighting within the intersection appropriately, providing visual support.

[0136] 7. Monitoring measures

[0137] The server analyzes the video data collected in real time and detects abnormal behavior such as sudden stops or falls by pedestrians. For example, it runs an algorithm that monitors sudden posture changes or sudden stops in real time.

[0138] 8. Means of notification

[0139] If the server detects any abnormal behavior, it generates a warning signal. This can be generated in various forms, such as an emergency stop signal or an audio warning. It also generates an audio warning message, "Caution, a pedestrian has fallen," and notifies those around it via speakers or LED displays.

[0140] The device then notifies the generated warning signal to vehicles and other pedestrians around the intersection, enabling a rapid response in the event of an abnormality.

[0141] Specific examples

[0142] Example 1: Elderly people crossing an intersection

[0143] The user (elderly person) arrives at the intersection at 11:00 AM.

[0144] The server acquires video data in real time from a high-resolution camera and performs preprocessing using OpenCV.

[0145] The server inputs the video data into a pre-trained TensorFlow model to detect elderly people and determine their walking speed as 0.4 m / s.

[0146] The terminal accesses the traffic light control system and extends the green light time from 30 seconds to 35 seconds.

[0147] The server uses the Google Text-to-Speech API to announce, "The green light will be extended by 10 seconds," and plays it over the speaker. It also makes the smart LED light flash blue to warn the driver.

[0148] The user (elderly person) can cross the intersection safely.

[0149] Example prompt sentence:

[0150] Give a concrete example of an elderly person crossing an intersection. Explain in detail how the system works to assist the elderly person.

[0151] Example 2: Pedestrian falls

[0152] A user (pedestrian) tries to cross an intersection at 5pm.

[0153] The server detects sudden falls by pedestrians in real time and identifies abnormalities.

[0154] The device generates a warning signal and issues a warning via a speaker or LED display board saying, "Caution, a pedestrian has fallen."

[0155] Other users (pedestrians and drivers) receive a warning and take safety measures.

[0156] Example prompt sentence:

[0157] Explain how the system detects and alerts a pedestrian if they fall at an intersection.

[0158] In this way, the system of the present invention combines various means to provide a comprehensive solution for elderly people and people with mobility impairments to safely use intersections.

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1:

[0161] The server acquires video data in real time from a high-resolution camera installed at an intersection. It receives high-resolution video (1080p, 30 frames per second) as input and obtains video data for preprocessing as output. The camera can provide clear video both day and night. Specifically, the video stream from the camera is sent to the server using the RTSP protocol.

[0162] Step 2:

[0163] The server preprocesses the captured video data. It receives the captured video data as input, performs noise removal and frame rate correction, and outputs analyzable video data. Specifically, it uses the OpenCV library to apply a Gaussian filter to remove noise and smooth the frames, thereby improving the accuracy of pedestrian detection.

[0164] Step 3:

[0165] The server inputs the preprocessed video data into a machine learning algorithm. It receives the preprocessed video data as input and outputs data to identify the location coordinates and movement speed of pedestrians. Specifically, it uses a CNN model such as ResNet using TensorFlow or PyTorch to calculate the bounding box (location coordinates) and speed of pedestrians.

[0166] Step 4:

[0167] The server determines whether a person is elderly or has difficulty walking based on the analysis results. It receives the pedestrian's location coordinates and movement speed data as input, and outputs the data identifying the person as elderly or has difficulty walking as the result of the determination. Specifically, it determines whether a pedestrian with a walking speed of 0.5 m / s or less is elderly, and then executes the determination algorithm taking into account specific posture characteristics.

[0168] Step 5:

[0169] Based on the judgment result, the terminal sends signal information to the signal control system to extend the green light time. It receives the judgment result as input and outputs signal control data to set the new green light time. Specifically, it sends an instruction to the Siemens signal controller to extend the green light time from 30 seconds to 35 seconds.

[0170] Step 6:

[0171] The server starts the voice guidance system and generates a voice message. It receives the judgment result and the new green light time data as input, and generates and outputs the voice guidance "The green light will be extended by 10 seconds." Specifically, it uses the Google Text-to-Speech API to generate the voice message and plays it from the speaker.

[0172] Step 7:

[0173] The device adjusts the lighting as a visual aid, receiving data on the new green light duration as input and outputting lighting control data to flash LED lights of a specific color. Specifically, the Philips smart LED lights flash blue to alert pedestrians.

[0174] Step 8:

[0175] The server monitors pedestrian movements in real time and detects abnormal behavior. It receives real-time video data as input and outputs a warning signal if an abnormality is detected. Specifically, it runs algorithms to detect sudden stops and falls and identify abnormalities.

[0176] Step 9:

[0177] The terminal notifies the generated warning signal. It receives abnormality detection data as input and outputs notification data to issue an emergency stop signal or voice warning. Specifically, it uses a speaker or LED display board to send out a warning message such as "Caution, a pedestrian has fallen" to notify surrounding vehicles and other pedestrians.

[0178] Through this series of steps, the system can provide support for elderly people and people with mobility impairments to cross intersections safely and respond quickly to abnormal behavior.

[0179] (Application example 1)

[0180] 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."

[0181] The goal is to solve the problem of insufficient support to prevent unexpected situations and accidents when elderly people and people with walking difficulties cross intersections safely, and the problem of a lack of technology for autonomous vehicles to properly recognize these pedestrians and drive safely. Furthermore, there is a need to build an integrated system to ensure the safety of pedestrians and facilitate the operation of autonomous vehicles.

[0182] 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.

[0183] In this invention, the server includes a sensor means for detecting the speed and position of pedestrians, an artificial intelligence means for analyzing the detected speed and position data, and a control means for adjusting the green light time of a traffic light based on the analysis results. This enables a means for identifying elderly people or people with walking difficulty in an autonomous vehicle and adjusting the vehicle speed, a means for acquiring camera images of the vehicle in real time and detecting pedestrians using an AI module, and a voice output means for providing a voice alert to pedestrians.

[0184] "Sensor means" refers to a device installed to detect the speed and position of a pedestrian.

[0185] "Artificial intelligence means" refers to AI technology used to analyze detected speed and location data and determine the attributes and status of pedestrians.

[0186] The "control means" is a system that adjusts the green light time of traffic lights based on the analysis results of the artificial intelligence means, thereby ensuring the safety of pedestrians.

[0187] "Support means" refers to means for providing audio or visual support to pedestrians based on the analysis results.

[0188] The "warning means" is a device that detects an abnormal condition and issues an alert to surrounding vehicles and pedestrians.

[0189] "Means for acquiring in real time" refers to a method for capturing video in real time using a vehicle camera and processing it immediately.

[0190] The "AI module" is software that uses artificial intelligence technology to detect pedestrians in camera footage and analyze their attributes.

[0191] "Means for identifying pedestrians" refers to a method that uses an AI module to determine whether a pedestrian is elderly or has walking difficulties.

[0192] "Means for adjusting vehicle speed" refers to a system that automatically slows or stops vehicles near intersections to ensure the safety of pedestrians.

[0193] "Audio output means" means a speaker system or other audio output device for providing an audio alert to a pedestrian.

[0194] System configuration

[0195] This invention relates to a support system for elderly people and people with walking difficulties to cross intersections safely. The system consists of the following main components:

[0196] 1. Sensor means

[0197] The server captures real-time video of pedestrians using a high-resolution camera mounted on the vehicle, which is then pre-processed to remove noise and correct the frame rate.

[0198] 2. Artificial Intelligence Means

[0199] The server uses an AI module (such as TensorFlow) to detect pedestrians from preprocessed video data, analyze the position and speed of each pedestrian, and determine whether they are elderly or have difficulty walking based on the analysis results.

[0200] 3. Control Measures

[0201] The server will adjust the green light time at intersections if it identifies elderly people or people with walking difficulties, and the autonomous vehicle will enter intersections at an appropriate speed and stop if necessary.

[0202] 4. Support measures

[0203] The server uses a voice output method (such as gTTS) to provide a voice alert such as "Pedestrians present, stop vehicle," as well as a visual warning.

[0204] 5. Warning measures

[0205] The server monitors for abnormal conditions such as sudden stops or falls by pedestrians, and if detected, generates an alert that is sent to surrounding vehicles and pedestrians.

[0206] System Operation

[0207] The system operates by combining a high-resolution camera, an AI module, and an audio output device. The camera captures video data in real time and the server pre-processes the video data. The pre-processed data is input into the AI ​​module, which analyzes pedestrian attributes (such as whether they are elderly or have difficulty walking). Based on the analysis results, the control means adjusts the green light time for the traffic light, and the support means provides audio and visual support.

[0208] Specific examples

[0209] The following is a specific example of the system.

[0210] Example 1: When there is an elderly person near an intersection

[0211] The server captures images using a high-resolution camera and uses an AI module to determine whether the person is elderly.

[0212] The control means extends the green light time of the traffic light, and the support means issues an audio alert saying "Green light extended."

[0213] Example 2: When a pedestrian falls near an intersection

[0214] The server detects abnormal pedestrian behavior and the warning means generates an alert.

[0215] Users (other pedestrians and vehicle drivers) receive an alert and take appropriate action.

[0216] Prompt Sentence Examples

[0217] "Please create the following program. This is code that will acquire video footage from a vehicle-mounted camera in real time, detect pedestrians using an AI model, and safely adjust the speed. If the pedestrian is elderly or has difficulty walking, the code will have the function of stopping the vehicle and issuing an audio alert."

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

[0219] Step 1:

[0220] The server captures video in real time using a high-resolution camera mounted on the vehicle. The captured video is pre-processed to remove noise and correct the frame rate. The input of this process is the video data from the camera, and the output is the pre-processed video data.

[0221] Step 2:

[0222] The server inputs the preprocessed video data into an AI module, which uses a deep learning framework such as TensorFlow to detect pedestrians in the video. The input is the preprocessed video data, and the output is the pedestrian's location coordinates and movement speed data.

[0223] Step 3:

[0224] The server analyzes the output data from the AI ​​module to identify elderly people and people with walking difficulties. This identification includes analyzing the pedestrian's movement speed and posture. The input is the pedestrian's position coordinates and movement speed data, and the output is information identifying elderly people and people with walking difficulties.

[0225] Step 4:

[0226] The server adjusts the green light time based on the analysis results. This adjustment includes adding the time required for identified elderly people and people with mobility impairments to cross the intersection safely. The input is the identification information, and the output is the adjusted green light time.

[0227] Step 5:

[0228] The server uses the voice output means to provide voice guidance when pedestrians cross the intersection. It uses a text-to-speech synthesis tool such as gTTS to generate a voice alert saying "Pedestrians present, stop vehicles." The input is the identification result and traffic light information, and the output is the generated voice file.

[0229] Step 6:

[0230] The device plays the generated audio alert and also generates a visual warning, such as displaying a "Watch out for pedestrians" or "Vehicle stopped" message on the vehicle's dashboard. The inputs are the audio file and the visual warning message, and the outputs are the audio alert and the display message.

[0231] Step 7:

[0232] The server monitors pedestrians' abnormal behavior in real time and detects sudden stops or falls. If an abnormality is detected, an alert is generated through a warning means and notified to surrounding vehicles and pedestrians. The input is real-time pedestrian data, and the output is the generated alert information.

[0233] Step 8:

[0234] Users (other pedestrians or vehicle drivers) receive the alert and take appropriate action. For example, a driver may bring the vehicle to a complete stop and pay attention to the pedestrian. The input is the alert information, and the output is the appropriate user action.

[0235] 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.

[0236] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[0237] System configuration

[0238] 1. Sensor means

[0239] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[0240] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[0241] 2. Artificial Intelligence Means

[0242] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[0243] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[0244] 3. Emotion Engine

[0245] The server runs an emotion engine to analyze the pedestrian's facial expressions and body movements.

[0246] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[0247] 4. Control Measures

[0248] The server operates the traffic light control module based on the analysis results of the AI ​​and the recognition results of the emotion engine, specifically extending the green light time as necessary.

[0249] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[0250] 5. Support measures

[0251] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[0252] The device adjusts the lighting within the intersection to visually alert pedestrians.

[0253] If the emotion engine determines that the user is feeling anxious or tense based on its analysis results, it will provide more calming voice guidance or changes.

[0254] 6. Warning measures

[0255] The server monitors pedestrians' movements and emotional states for any abnormalities and generates a warning signal if it detects any abnormalities.

[0256] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[0257] Program processing and specific examples

[0258] Photographing pedestrians by sensor means and preprocessing

[0259] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[0260] The server converts the pre-processed video into an input format for the AI ​​module.

[0261] Analysis of pedestrian speed and position using artificial intelligence means.

[0262] The server uses an AI module to detect pedestrians in the video and calculates the location coordinates and movement speed of each pedestrian in real time.

[0263] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[0264] Emotion analysis using an emotion engine

[0265] The server analyzes the pedestrian's facial expressions and body movements from the video data and uses an emotion engine to recognize the pedestrian's emotional state.

[0266] Based on the analysis results, the server identifies pedestrians who are anxious or tense and sends that information to support and warning means.

[0267] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[0268] The server uses specific criteria from the analysis results of the AI ​​and emotion engine to identify elderly people and people with walking difficulties, and calculates the walking time required for each person.

[0269] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[0270] Support means audio guidance and lighting support

[0271] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. Specifically, a voice message such as "The green light will be extended by 10 seconds from here" is provided via a speaker system.

[0272] The terminal adjusts lighting within the intersection, provides visual support, and provides calming audio guidance and lighting if pedestrians become nervous.

[0273] Detect anomalies and issue alerts using warning methods

[0274] The server monitors the pedestrian's movement and emotional state for any abnormalities, detecting sudden stops, falls, and abnormal emotional states (e.g., extreme anxiety or fear).

[0275] When an abnormality is detected, the device generates a warning signal and notifies vehicles and other pedestrians around the intersection, such as an emergency stop signal or an audio warning.

[0276] Specific examples

[0277] Example 1:

[0278] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[0279] The server receives the camera footage and analyzes it using AI and an emotion engine.

[0280] The device identifies elderly people and extends the green light time.

[0281] The server provides voice guidance regarding "extended green light."

[0282] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[0283] Seniors can cross the intersection safely.

[0284] Example 2:

[0285] At 5pm, a person fell while trying to pass through an intersection.

[0286] The server detects an anomaly and generates an alert.

[0287] The device sends an alert to those around the intersection and issues an emergency stop signal.

[0288] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[0289] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[0290] In this way, the system is highly integrated and provides a range of functions to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[0291] The processing flow will be explained below.

[0292] Step 1:

[0293] The server acquires real-time video data from high-resolution cameras installed at intersections, which are captured by sensor means and sent to a pre-processing module.

[0294] Step 2:

[0295] The server pre-processes the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, and then transfers the pre-processed data to the AI ​​module.

[0296] Step 3:

[0297] The server inputs the pre-processed video data into the AI ​​module to detect the speed and location of pedestrians, which then calculates the pedestrian's location coordinates and movement speed in real time and returns this data to the server.

[0298] Step 4:

[0299] The server uses the analysis results of the AI ​​module to determine whether a pedestrian is elderly or has mobility issues, based on the pedestrian's speed, movement pattern, and posture stability.

[0300] Step 5:

[0301] The server captures the pedestrian's facial expressions and body movements and inputs them into the emotion engine, which analyzes the pedestrian's emotional state (anxiety, tension, etc.) and returns the results to the server.

[0302] Step 6:

[0303] The server uses the results of AI and emotion engine analysis to calculate the walking time required for elderly people and those with mobility issues, taking into account the pedestrian's speed and the length of the intersection.

[0304] Step 7:

[0305] The terminal sets a new green signal time in the signal control module based on the analysis results received from the server, adds the required extension time to the current green signal time, and applies the new green signal time to the traffic light.

[0306] Step 8:

[0307] The server provides audio guidance and visual support based on the pedestrian's location and emotional state. For example, if the emotion engine detects anxiety, it will play a voice message such as "Please cross safely."

[0308] Step 9:

[0309] The device adjusts the lighting within the intersection and provides visual support, changing the brightness and flashing patterns of the lights to better attract pedestrians' attention.

[0310] Step 10:

[0311] The server monitors the pedestrian's movements and emotional state for abnormalities, and if it detects an abnormal state such as a sudden stop, a fall, or extreme anxiety or fear, it activates a warning mechanism.

[0312] Step 11:

[0313] When an abnormal condition is detected, the device immediately generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection, triggering an emergency stop signal and / or an audio warning.

[0314] Step 12:

[0315] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and can take appropriate action, allowing them to respond quickly and stay safe even when an abnormal situation occurs.

[0316] Example 2

[0317] 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."

[0318] Conventional intersection safety systems mainly adjust the green light time of traffic lights and only provide basic audio guidance and visual support for pedestrians. As a result, they sometimes lack sufficient support for elderly people and people with walking difficulties to cross intersections safely. Furthermore, they lack the functionality to consider the pedestrian's mental state, which means they are unable to provide appropriate support to pedestrians who feel anxious or tense. Therefore, there is a need for a system that can solve these problems and provide comprehensive support and safety measures for elderly people and people with walking difficulties.

[0319] 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.

[0320] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, means for preprocessing detected video data, artificial intelligence means for analyzing the preprocessed video data, means for determining whether the pedestrian is elderly or has difficulty walking based on the analyzed data, means including an emotion engine for analyzing facial expressions and body movements and recognizing the pedestrian's emotional state, control means for adjusting the green light time of a traffic light based on the analysis results and the emotional data, support means for providing audio or visual support to the pedestrian based on the analysis results and the emotional data, and warning means for monitoring whether there are any abnormalities in the pedestrian's movements or emotional state and issuing a warning if an abnormality is detected. This makes it possible to comprehensively monitor the physical and mental state of pedestrians and provide comprehensive safety measures and support for the elderly and people with difficulty walking.

[0321] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[0322] "Preprocessing" refers to the process of converting acquired video data into a format that is easier to analyze by removing noise, adjusting resolution, correcting frame rate, etc.

[0323] "Artificial intelligence means" refers to algorithms or modules that analyze pre-processed video data and extract information on the speed, position, and posture of pedestrians.

[0324] The "emotion engine" is an engine that analyzes the emotional state of pedestrians from their facial expressions and body movements.

[0325] The "control means" is a mechanism for adjusting the green light time of a traffic light based on the analysis results and emotion data.

[0326] "Support means" refers to a device that provides audio guidance and visual support to pedestrians based on analysis results and emotional data.

[0327] The "warning means" is a device that monitors whether there are any abnormalities in the movements or emotional state of pedestrians, and issues a warning if an abnormality is detected.

[0328] "Elderly" generally refers to pedestrians aged 60 or over.

[0329] A "person with walking difficulties" is a person who has difficulty walking normally due to physical or health reasons.

[0330] "Green light time" is the time a signal's green light is on, ensuring pedestrians can cross an intersection.

[0331] An "abnormal state" is a state in which a pedestrian deviates from normal walking behavior, such as a sudden stop or fall, or extreme anxiety or fear.

[0332] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[0333] Sensor Means

[0334] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[0335] The device preprocesses the video data, removing noise, adjusting the resolution, and correcting the frame rate.

[0336] Artificial Intelligence Tools

[0337] The server runs an AI module that analyzes the pre-processed video data, analyzing pedestrian speed and posture, and calculating each pedestrian's location coordinates and movement speed in real time.

[0338] Based on the analyzed data, the device determines whether the pedestrian is elderly or has difficulty walking, and calculates the walking time required for that pedestrian.

[0339] Emotion Engine

[0340] The server runs an emotion engine that analyzes pedestrians' facial expressions and body movements.

[0341] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[0342] Control means

[0343] The server operates the traffic light control module based on the AI ​​analysis results and the emotion engine's recognition results, extending the green light time as necessary.

[0344] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[0345] Support Measures

[0346] The server provides audio guidance and visual support for walking assistance, for example, providing a voice message such as "The green light will be extended by 10 seconds from here."

[0347] The device adjusts the lighting at the intersection and visually alerts pedestrians, and if it detects that the user is feeling anxious or nervous, it provides voice guidance and changes the lighting to calm them down.

[0348] warning means

[0349] The server monitors the pedestrian's movements and emotional state for abnormalities, and generates a warning signal if it detects an abnormality, such as a sudden stop or a fall.

[0350] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[0351] Specific examples

[0352] Example 1

[0353] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[0354] The server receives the camera footage and analyzes it using AI and an emotion engine.

[0355] The device identifies elderly people and extends the green light time.

[0356] The server provides voice guidance regarding "extended green light."

[0357] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[0358] The user can cross the intersection safely.

[0359] Example 2

[0360] At 5pm, a person falls while trying to pass through an intersection.

[0361] The server detects the anomaly and generates an alert.

[0362] The device sends an alert to those around the intersection and issues an emergency stop signal.

[0363] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[0364] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[0365] As can be seen, the system is highly integrated and provides a range of features to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[0366] Prompt Sentence Examples

[0367] "Calculate the extra walking time required for an elderly person to cross safely at an intersection."

[0368] "Create appropriate audio guidance for when pedestrians are nervous."

[0369] In this way, each element of the system works together to improve pedestrian safety and provide comprehensive support that enables pedestrians to cross intersections with confidence.

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

[0371] Step 1:

[0372] The server receives real-time video from high-resolution cameras installed at intersections. The input is the camera's video data, which includes pedestrian movements and the surrounding environment. The server preprocesses this data. Preprocessing includes noise removal, resolution adjustment, and frame rate correction, and the resulting video data is suitable for analysis.

[0373] Step 2:

[0374] The terminal converts the preprocessed video data received from the server into an input data format using a preprocessing algorithm. The input is the preprocessed video data, and the data format conversion is performed to make it compatible with the pedestrian detection algorithm. The converted data is then received.

[0375] Step 3:

[0376] The server inputs the converted video data into the AI ​​module to detect and analyze pedestrians. The converted video data is input, and the AI ​​module calculates the speed and location of pedestrians in real time. As a result, the location coordinates and movement speed data of each pedestrian are output.

[0377] Step 4:

[0378] The server analyzes the location and speed data obtained from the AI ​​module and determines whether each pedestrian is elderly or has difficulty walking. The input is location coordinates and movement speed data, and the output is the determination result of whether the pedestrian is elderly or has difficulty walking.

[0379] Step 5:

[0380] The server runs an emotion engine and analyzes the facial expressions and body movements of pedestrians from the received video data. The inputs are the judgment results obtained in the previous step and the video data, and the emotion engine identifies pedestrians who are feeling anxious or nervous. The analysis results are output as data on the pedestrian's emotional state.

[0381] Step 6:

[0382] The server operates the traffic light control module based on the analysis results of the AI ​​module and the recognition results of the emotion engine. The input is the judgment result and emotional state data of elderly people and people with walking difficulties, and the output is an instruction to extend the green light time. This instruction extends the green light time as necessary.

[0383] Step 7:

[0384] The terminal receives a control signal from the server and sends it to the traffic light. The input is the control signal from the server, and the output is an update of the traffic light setting and a new green light time is set.

[0385] Step 8:

[0386] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. The input is the pedestrian's location information and emotional state data, and the output is a voice guidance message. Specifically, the server generates a voice message such as "The green light will be extended by 10 seconds from here."

[0387] Step 9:

[0388] The device adjusts the lighting in the intersection to visually alert pedestrians. The input is instructions from the server, and the output is updated lighting settings. For nervous pedestrians, lighting effects are added to calm them down.

[0389] Step 10:

[0390] The server monitors pedestrians' movements and emotional states for abnormalities, detecting sudden stops, falls, and other anomalies. The input is real-time monitored pedestrian data, and if an anomaly is detected, a warning signal is generated. The output is an anomaly detection alert, which is sent to the warning means.

[0391] Step 11:

[0392] The terminal receives the generated warning signal and notifies vehicles and other pedestrians around the intersection. The input is the warning signal from the server, and the output is the turning on of warning lights in the intersection and the sound of a warning.

[0393] (Application example 2)

[0394] 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."

[0395] The problem that this invention aims to solve is to support elderly people and people with mobility difficulties to move safely and efficiently within a physical store, and to provide appropriate support based on their emotional state, such as anxiety or tension. Another objective is to ensure safety by detecting abnormal conditions and responding quickly. This aims to provide an environment where elderly people and people with mobility difficulties can enjoy shopping with peace of mind.

[0396] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0397] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, artificial intelligence means for analyzing the detected speed and position data, control means for adjusting the green light time of traffic lights based on the analysis results, support means for providing audio or visual support to pedestrians based on the analysis results, emotion analysis means for analyzing facial expressions and body movements to recognize emotional states, support means for providing audio guidance to pedestrians to encourage stability based on their emotional states, and warning means for detecting abnormal conditions and issuing alerts to surrounding vehicles and pedestrians. This makes it possible to support the safe movement of pedestrians and provide appropriate navigation and support while reducing tension and anxiety.

[0398] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[0399] "Artificial intelligence means" refers to techniques that utilize machine learning and algorithms to analyze detected speed and location data.

[0400] "Control means" refers to a device or system for adjusting the green light time of a traffic light based on the analysis results.

[0401] "Support means" refers to devices or technologies that provide audio or visual support to pedestrians based on the analysis results.

[0402] "Warning means" refers to devices and technologies that detect abnormal conditions and issue alerts to surrounding vehicles and pedestrians.

[0403] "Emotion analysis means" refers to devices or technologies that analyze facial expressions and body movements to recognize emotional states.

[0404] "Assistance tools" are devices and technologies that provide audio guidance to pedestrians to encourage stability based on their emotional state.

[0405] To realize this invention, the system operates as an application using smart glasses. The smart glasses use the following hardware and software to assist elderly people and people with mobility impairments to move safely and comfortably within a physical store.

[0406] Hardware

[0407] Smart glasses: Equipped with a camera, microphone, speaker, and GPS module.

[0408] Server: A high-performance computer for data processing and analysis.

[0409] In-store beacon: A device for obtaining accurate location information.

[0410] software

[0411] AI module: Machine learning algorithms for analyzing pedestrian speed and location data, using frameworks such as TensorFlow and PyTorch.

[0412] Emotion Engine: A program that analyzes facial expressions and body movements to recognize emotional states. It uses Emotion API and OpenCV.

[0413] Control module: This module adjusts the green light time and provides voice guidance. It uses Node.js and Python.

[0414] Alert system: A program for detecting abnormal conditions and generating alerts.

[0415] Processing flow

[0416] 1. Real-time image acquisition and preprocessing

[0417] A camera built into the smart glasses captures images of the inside of the store in real time.

[0418] The captured video is sent to a server where noise removal and frame rate correction are performed.

[0419] 2. Analysis of pedestrian speed and position

[0420] The server uses an AI module to detect pedestrians in the video data and calculate their location coordinates and speed.

[0421] Based on the analysis results, it is determined whether the pedestrian is elderly or has difficulty walking.

[0422] 3. Facial Expression and Body Movement Analysis

[0423] The server uses an emotion engine to analyze facial expressions and body movements to recognize emotional states.

[0424] Based on the recognized emotional state, the smart glasses provide audio guidance.

[0425] 4. Navigation aids and warning systems

[0426] Provide appropriate audio and visual navigation as a means of support.

[0427] If an abnormal condition is detected, the warning system will generate an alert and notify store staff.

[0428] Specific examples

[0429] Example 1

[0430] An elderly person wearing smart glasses visits a supermarket at 2 p.m.

[0431] The smart glasses receive the camera footage, which is then analyzed by the server using an AI module and emotion engine.

[0432] As a result of the analysis, elderly people are identified and appropriate route guidance is initiated.

[0433] Voice guidance such as "The cash register is 10 meters away" is provided through the smart glasses.

[0434] If it detects that the senior is feeling anxious, it will provide additional voice prompts to calm them down.

[0435] Example 2

[0436] At 5 p.m., an elderly person fell while walking inside the store.

[0437] When the smart glasses detect an abnormality, the server generates an alert and sends a notification to the store staff.

[0438] Furthermore, the emotion engine detects when the user is feeling fear due to falling, and appropriate measures are taken quickly.

[0439] Prompt Sentence Examples

[0440] "Develop an application for smart glasses that helps seniors navigate safely and stress-free within a store. The application should include the following features:

[0441] Images captured by the built-in camera are preprocessed in real time to detect the speed and location of pedestrians.

[0442] An artificial intelligence module is used to identify elderly people and those with walking difficulties.

[0443] The emotion engine analyzes facial expressions and body movements to recognize emotional states.

[0444] Providing navigation routes and audio and visual support.

[0445] When an abnormality is detected, a warning signal is generated and staff are notified.

[0446] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0447] Step 1:

[0448] The server receives real-time video footage from inside the store captured by the camera built into the smart glasses. The input is camera video data, and the output is pre-processed video data. Specifically, the server performs processing to remove noise from the video and correct the frame rate.

[0449] Step 2:

[0450] The server inputs the preprocessed video data into the AI ​​module. The input is noise-removed and frame-rate-corrected video data, and the output is the position coordinates and speed data of detected pedestrians. Specifically, the server detects pedestrians in the video and calculates the position and speed of each pedestrian.

[0451] Step 3:

[0452] The server identifies elderly people and people with walking difficulties based on the analysis results of the AI ​​module. The input is the position coordinates and speed data of pedestrians, and the output is identification information of elderly people and people with walking difficulties. Specifically, the server analyzes speed and posture to identify elderly people and people with walking difficulties.

[0453] Step 4:

[0454] The server uses emotion analysis means to analyze facial expressions and body movements. The input is video data of pedestrians, and the output is the identification result of their emotional state. Specifically, the server analyzes facial expressions and body movements to recognize the emotional state.

[0455] Step 5:

[0456] The server generates appropriate voice guidance for the pedestrian based on the emotional state. The inputs are the emotional state identification result and the pedestrian's location information, and the output is voice guidance data. Specifically, the server generates a voice message corresponding to the emotional state and sends it to the smart glasses.

[0457] Step 6:

[0458] The server detects abnormal conditions and activates the warning system. The inputs are the pedestrian's position coordinates and speed data, and the emotional state identification results, and the output is a warning signal. Specifically, the server detects abnormal conditions such as sudden stops, falls, extreme anxiety, or fear, and generates a warning signal to notify store staff.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] [Second embodiment]

[0463] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0474] 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."

[0475] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. The system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, and a warning means.

[0476] System configuration

[0477] 1. Sensor means

[0478] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[0479] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[0480] 2. Artificial Intelligence Means

[0481] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[0482] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[0483] 3. Control Measures

[0484] The server operates the traffic light control module based on the results of the AI ​​analysis, specifically extending the green light time as needed.

[0485] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[0486] 4. Support measures

[0487] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[0488] The device adjusts the lighting within the intersection to visually alert pedestrians.

[0489] 5. Warning measures

[0490] The server monitors pedestrians' movements for any abnormalities and generates a warning signal if it detects any abnormalities.

[0491] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[0492] Program processing and specific examples

[0493] Photographing pedestrians by sensor means and preprocessing

[0494] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[0495] The server converts the pre-processed video into an input format for the AI ​​module.

[0496] Analysis of pedestrian speed and position using artificial intelligence means.

[0497] The server uses an AI module to detect pedestrians in the video and calculate the location coordinates and movement speed of each pedestrian.

[0498] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[0499] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[0500] The server uses specific criteria from the analysis results to identify elderly people and people with walking difficulties, and calculates the walking time required for those people.

[0501] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[0502] Support means audio guidance and lighting support

[0503] The server provides audio guidance and visual support at the appropriate time based on the pedestrian's location information.

[0504] The device operates the speaker system and lighting system to convey messages to pedestrians such as "Watch out for extended green lights."

[0505] Detect anomalies and issue alerts using warning methods

[0506] The server monitors pedestrians' movements for any abnormalities and detects any abnormalities such as sudden stops or falls.

[0507] When an abnormality is detected, the device generates a warning signal to notify vehicles and other pedestrians around the intersection.

[0508] Specific examples

[0509] Example 1:

[0510] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[0511] The server receives the camera footage and analyzes it using an AI module.

[0512] The device identifies elderly people and extends the green light time.

[0513] The server provides voice guidance regarding "extended green light."

[0514] Seniors can cross the intersection safely.

[0515] Example 2:

[0516] At 5pm, a person fell while trying to pass through an intersection.

[0517] The server detects an anomaly and generates an alert.

[0518] The device sends an alert to those around the intersection and issues an emergency stop signal.

[0519] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[0520] In this way, the system is highly integrated and offers a range of functions to ensure the safety of the elderly and those with mobility impairments.

[0521] The processing flow will be explained below.

[0522] Step 1:

[0523] The server acquires video data in real time from cameras installed at intersections, which are transmitted to the server via sensor means and passed to an image processing module for pre-processing.

[0524] Step 2:

[0525] The server performs preprocessing on the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, enabling the AI ​​to accurately recognize pedestrians.

[0526] Step 3:

[0527] The server inputs the preprocessed video data into the AI ​​module to detect pedestrians, which then calculates their location coordinates and movement speed in real time.

[0528] Step 4:

[0529] The server analyzes the data of detected pedestrians and identifies elderly people and those with walking difficulties, using information such as the pedestrian's speed, movement patterns, and posture stability.

[0530] Step 5:

[0531] The server calculates the walking time required for identified elderly people or people with walking difficulties, based on the speed of the pedestrian and the length of the intersection.

[0532] Step 6:

[0533] The terminal sets a new green signal time in the signal control module based on the analysis result received from the server, adding the required extension time to the current green signal time and setting the new green signal time in the traffic light.

[0534] Step 7:

[0535] The server generates voice guidance at appropriate times based on the pedestrian's location information, such as "The green light will be extended by 10 seconds from here" via a speaker system.

[0536] Step 8:

[0537] The device adjusts lighting within the intersection and provides visual support, drawing pedestrians' attention to safely cross the intersection.

[0538] Step 9:

[0539] The server monitors pedestrians' movements to see if there are any abnormalities. If the server detects any abnormal movements such as a sudden stop or a fall, it will recognize this as an abnormal situation.

[0540] Step 10:

[0541] When an abnormal condition is detected, the device generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection. Specifically, an emergency stop signal or an audio warning is issued.

[0542] Step 11:

[0543] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and take appropriate action, thereby ensuring safety when an abnormal situation occurs.

[0544] Example 1

[0545] 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."

[0546] When elderly people or people with walking difficulties cross intersections, they often lack the time to cross safely. In such cases, the risk of an accident increases. In addition, improper control of traffic signals can have a significant impact on other pedestrians and vehicles. Furthermore, rapid response is required in the event of pedestrians suddenly stopping or falling, or other abnormal behavior. It is necessary to solve these issues and ensure that all traffic participants can use intersections safely.

[0547] 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.

[0548] In this invention, the server includes a sensor for capturing pedestrian video in real time, a processing unit for preprocessing the captured video to detect the speed and location of pedestrians, an artificial intelligence unit for detecting pedestrians based on the preprocessed video data and analyzing their location and speed, a determination unit for identifying elderly people or people with walking difficulties and calculating the required walking time, a control unit for extending the green light time based on the calculated walking time, a support unit for providing audio guidance and visual support, a monitoring unit for detecting abnormal pedestrian behavior and generating a warning signal, and a notification unit for notifying the generated warning signal. This allows for an increase in the time required to safely cross an intersection as needed, allowing elderly people and people with walking difficulties to use the intersection safely. Furthermore, by quickly responding to abnormal behavior, the risk of accidents can be reduced.

[0549] "Sensor means" refers to a high resolution camera or other sensing device for acquiring video data in real time.

[0550] "Processing means" refers to a data processing device for pre-processing the acquired video data and detecting the velocity and position.

[0551] "Artificial intelligence means" refers to machine learning algorithms and models that analyze pre-processed video data and identify the location and speed of pedestrians.

[0552] "Determination means" refers to a device or algorithm that determines whether an elderly person or a person with walking difficulty is present based on the analysis results and calculates the walking time required for that person.

[0553] The "control means" refers to a traffic light control device that appropriately extends the green light time of a traffic light at an intersection based on the calculated walking time.

[0554] "Support means" refers to devices that provide audio guidance and visual support to pedestrians crossing an intersection.

[0555] "Monitoring means" refers to devices or systems that monitor pedestrian movement and detect abnormal behavior such as sudden stops or falls.

[0556] "Notification means" refers to a device for notifying vehicles and other pedestrians around the intersection of the generated warning signal.

[0557] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. This system is implemented by combining a sensor means, a processing means, an artificial intelligence means, a determination means, a control means, a support means, a monitoring means, and a notification means.

[0558] Program Generation and Processing Description

[0559] 1. Sensor means

[0560] The server acquires pedestrian video data in real time using high-resolution cameras installed at intersections. The cameras have a resolution of 1080p and capture video at 30 frames per second, enabling high-quality video acquisition.

[0561] 2. Processing Methods

[0562] The server preprocesses the acquired video data. Specifically, it uses the OpenCV library to remove noise from the video frames and correct the frame rate. For example, it uses a Gaussian filter to remove noise and stabilize the video frames.

[0563] 3. Artificial Intelligence Means

[0564] The server inputs the preprocessed video data into a machine learning algorithm (e.g., a CNN model using TensorFlow or PyTorch) to detect the location coordinates and movement speed of pedestrians. Specifically, it uses a pre-trained model such as ResNet to identify the location and speed by outputting the bounding box of the pedestrian.

[0565] 4. Judgment means

[0566] The server then uses the analysis results to determine whether a person is elderly or has difficulty walking. Criteria for this include walking speed of 0.5 m / s or less, and specific posture characteristics (e.g., leaning forward, using a cane). This improves the accuracy of detecting elderly people and people with difficulty walking.

[0567] 5. Control Measures

[0568] Based on the results of the judgment, the terminal accesses the intersection's signal control system and appropriately extends the green light time. For example, it sends the new green light extension time to a Siemens signal controller, which then controls the traffic lights.

[0569] 6. Support Measures

[0570] The server uses the Google Text-to-Speech API to generate an audio message that says, "The green light will be extended by 10 seconds," which is then played over the intersection's speakers. Additionally, as a visual aid, LED lights of a specific color flash to warn pedestrians.

[0571] The terminal controls Philips smart LED lights and adjusts the lighting within the intersection appropriately, providing visual support.

[0572] 7. Monitoring measures

[0573] The server analyzes the video data collected in real time and detects abnormal behavior such as sudden stops or falls by pedestrians. For example, it runs an algorithm that monitors sudden posture changes or sudden stops in real time.

[0574] 8. Means of notification

[0575] If the server detects any abnormal behavior, it generates a warning signal. This can be generated in various forms, such as an emergency stop signal or an audio warning. It also generates an audio warning message, "Caution, a pedestrian has fallen," and notifies those around it via speakers or LED displays.

[0576] The device then notifies the generated warning signal to vehicles and other pedestrians around the intersection, enabling a rapid response in the event of an abnormality.

[0577] Specific examples

[0578] Example 1: Elderly people crossing an intersection

[0579] The user (elderly person) arrives at the intersection at 11:00 AM.

[0580] The server acquires video data in real time from a high-resolution camera and performs preprocessing using OpenCV.

[0581] The server inputs the video data into a pre-trained TensorFlow model to detect elderly people and determine their walking speed as 0.4 m / s.

[0582] The terminal accesses the traffic light control system and extends the green light time from 30 seconds to 35 seconds.

[0583] The server uses the Google Text-to-Speech API to announce, "The green light will be extended by 10 seconds," and plays it over the speaker. It also makes the smart LED light flash blue to warn the driver.

[0584] The user (elderly person) can cross the intersection safely.

[0585] Example prompt sentence:

[0586] Give a concrete example of an elderly person crossing an intersection. Explain in detail how the system works to assist the elderly person.

[0587] Example 2: Pedestrian falls

[0588] A user (pedestrian) tries to cross an intersection at 5pm.

[0589] The server detects sudden falls by pedestrians in real time and identifies abnormalities.

[0590] The device generates a warning signal and issues a warning via a speaker or LED display board saying, "Caution, a pedestrian has fallen."

[0591] Other users (pedestrians and drivers) receive a warning and take safety measures.

[0592] Example prompt sentence:

[0593] Explain how the system detects and alerts a pedestrian if they fall at an intersection.

[0594] In this way, the system of the present invention combines various means to provide a comprehensive solution for elderly people and people with mobility impairments to safely use intersections.

[0595] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0596] Step 1:

[0597] The server acquires video data in real time from a high-resolution camera installed at an intersection. It receives high-resolution video (1080p, 30 frames per second) as input and obtains video data for preprocessing as output. The camera can provide clear video both day and night. Specifically, the video stream from the camera is sent to the server using the RTSP protocol.

[0598] Step 2:

[0599] The server preprocesses the captured video data. It receives the captured video data as input, performs noise removal and frame rate correction, and outputs analyzable video data. Specifically, it uses the OpenCV library to apply a Gaussian filter to remove noise and smooth the frames, thereby improving the accuracy of pedestrian detection.

[0600] Step 3:

[0601] The server inputs the preprocessed video data into a machine learning algorithm. It receives the preprocessed video data as input and outputs data to identify the location coordinates and movement speed of pedestrians. Specifically, it uses a CNN model such as ResNet using TensorFlow or PyTorch to calculate the bounding box (location coordinates) and speed of pedestrians.

[0602] Step 4:

[0603] The server determines whether a person is elderly or has difficulty walking based on the analysis results. It receives the pedestrian's location coordinates and movement speed data as input, and outputs the data identifying the person as elderly or has difficulty walking as the result of the determination. Specifically, it determines whether a pedestrian with a walking speed of 0.5 m / s or less is elderly, and then executes the determination algorithm taking into account specific posture characteristics.

[0604] Step 5:

[0605] Based on the judgment result, the terminal sends signal information to the signal control system to extend the green light time. It receives the judgment result as input and outputs signal control data to set the new green light time. Specifically, it sends an instruction to the Siemens signal controller to extend the green light time from 30 seconds to 35 seconds.

[0606] Step 6:

[0607] The server starts the voice guidance system and generates a voice message. It receives the judgment result and the new green light time data as input, and generates and outputs the voice guidance "The green light will be extended by 10 seconds." Specifically, it uses the Google Text-to-Speech API to generate the voice message and plays it from the speaker.

[0608] Step 7:

[0609] The device adjusts the lighting as a visual aid, receiving data on the new green light duration as input and outputting lighting control data to flash LED lights of a specific color. Specifically, the Philips smart LED lights flash blue to alert pedestrians.

[0610] Step 8:

[0611] The server monitors pedestrian movements in real time and detects abnormal behavior. It receives real-time video data as input and outputs a warning signal if an abnormality is detected. Specifically, it runs algorithms to detect sudden stops and falls and identify abnormalities.

[0612] Step 9:

[0613] The terminal notifies the generated warning signal. It receives abnormality detection data as input and outputs notification data to issue an emergency stop signal or voice warning. Specifically, it uses a speaker or LED display board to send out a warning message such as "Caution, a pedestrian has fallen" to notify surrounding vehicles and other pedestrians.

[0614] Through this series of steps, the system can provide support for elderly people and people with mobility impairments to cross intersections safely and respond quickly to abnormal behavior.

[0615] (Application example 1)

[0616] 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."

[0617] The goal is to solve the problem of insufficient support to prevent unexpected situations and accidents when elderly people and people with walking difficulties cross intersections safely, and the problem of a lack of technology for autonomous vehicles to properly recognize these pedestrians and drive safely. Furthermore, there is a need to build an integrated system to ensure the safety of pedestrians and facilitate the operation of autonomous vehicles.

[0618] 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.

[0619] In this invention, the server includes a sensor means for detecting the speed and position of pedestrians, an artificial intelligence means for analyzing the detected speed and position data, and a control means for adjusting the green light time of a traffic light based on the analysis results. This enables a means for identifying elderly people or people with walking difficulty in an autonomous vehicle and adjusting the vehicle speed, a means for acquiring camera images of the vehicle in real time and detecting pedestrians using an AI module, and a voice output means for providing a voice alert to pedestrians.

[0620] "Sensor means" refers to a device installed to detect the speed and position of a pedestrian.

[0621] "Artificial intelligence means" refers to AI technology used to analyze detected speed and location data and determine the attributes and status of pedestrians.

[0622] The "control means" is a system that adjusts the green light time of traffic lights based on the analysis results of the artificial intelligence means, thereby ensuring the safety of pedestrians.

[0623] "Support means" refers to means for providing audio or visual support to pedestrians based on the analysis results.

[0624] The "warning means" is a device that detects an abnormal condition and issues an alert to surrounding vehicles and pedestrians.

[0625] "Means for acquiring in real time" refers to a method for capturing video in real time using a vehicle camera and processing it immediately.

[0626] The "AI module" is software that uses artificial intelligence technology to detect pedestrians in camera footage and analyze their attributes.

[0627] "Means for identifying pedestrians" refers to a method that uses an AI module to determine whether a pedestrian is elderly or has walking difficulties.

[0628] "Means for adjusting vehicle speed" refers to a system that automatically slows or stops vehicles near intersections to ensure the safety of pedestrians.

[0629] "Audio output means" means a speaker system or other audio output device for providing an audio alert to a pedestrian.

[0630] System configuration

[0631] This invention relates to a support system for elderly people and people with walking difficulties to cross intersections safely. The system consists of the following main components:

[0632] 1. Sensor means

[0633] The server captures real-time video of pedestrians using a high-resolution camera mounted on the vehicle, which is then pre-processed to remove noise and correct the frame rate.

[0634] 2. Artificial Intelligence Means

[0635] The server uses an AI module (such as TensorFlow) to detect pedestrians from preprocessed video data, analyze the position and speed of each pedestrian, and determine whether they are elderly or have difficulty walking based on the analysis results.

[0636] 3. Control Measures

[0637] The server will adjust the green light time at intersections if it identifies elderly people or people with walking difficulties, and the autonomous vehicle will enter intersections at an appropriate speed and stop if necessary.

[0638] 4. Support measures

[0639] The server uses a voice output method (such as gTTS) to provide a voice alert such as "Pedestrians present, stop vehicle," as well as a visual warning.

[0640] 5. Warning measures

[0641] The server monitors for abnormal conditions such as sudden stops or falls by pedestrians, and if detected, generates an alert that is sent to surrounding vehicles and pedestrians.

[0642] System Operation

[0643] The system operates by combining a high-resolution camera, an AI module, and an audio output device. The camera captures video data in real time and the server pre-processes the video data. The pre-processed data is input into the AI ​​module, which analyzes pedestrian attributes (such as whether they are elderly or have difficulty walking). Based on the analysis results, the control means adjusts the green light time for the traffic light, and the support means provides audio and visual support.

[0644] Specific examples

[0645] The following is a specific example of the system.

[0646] Example 1: When there is an elderly person near an intersection

[0647] The server captures images using a high-resolution camera and uses an AI module to determine whether the person is elderly.

[0648] The control means extends the green light time of the traffic light, and the support means issues an audio alert saying "Green light extended."

[0649] Example 2: When a pedestrian falls near an intersection

[0650] The server detects abnormal pedestrian behavior and the warning means generates an alert.

[0651] Users (other pedestrians and vehicle drivers) receive an alert and take appropriate action.

[0652] Prompt Sentence Examples

[0653] "Please create the following program. This is code that will acquire video footage from a vehicle-mounted camera in real time, detect pedestrians using an AI model, and safely adjust the speed. If the pedestrian is elderly or has difficulty walking, the code will have the function of stopping the vehicle and issuing an audio alert."

[0654] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0655] Step 1:

[0656] The server captures video in real time using a high-resolution camera mounted on the vehicle. The captured video is pre-processed to remove noise and correct the frame rate. The input of this process is the video data from the camera, and the output is the pre-processed video data.

[0657] Step 2:

[0658] The server inputs the preprocessed video data into an AI module, which uses a deep learning framework such as TensorFlow to detect pedestrians in the video. The input is the preprocessed video data, and the output is the pedestrian's location coordinates and movement speed data.

[0659] Step 3:

[0660] The server analyzes the output data from the AI ​​module to identify elderly people and people with walking difficulties. This identification includes analyzing the pedestrian's movement speed and posture. The input is the pedestrian's position coordinates and movement speed data, and the output is information identifying elderly people and people with walking difficulties.

[0661] Step 4:

[0662] The server adjusts the green light time based on the analysis results. This adjustment includes adding the time required for identified elderly people and people with mobility impairments to cross the intersection safely. The input is the identification information, and the output is the adjusted green light time.

[0663] Step 5:

[0664] The server uses the voice output means to provide voice guidance when pedestrians cross the intersection. It uses a text-to-speech synthesis tool such as gTTS to generate a voice alert saying "Pedestrians present, stop vehicles." The input is the identification result and traffic light information, and the output is the generated voice file.

[0665] Step 6:

[0666] The device plays the generated audio alert and also generates a visual warning, such as displaying a "Watch out for pedestrians" or "Vehicle stopped" message on the vehicle's dashboard. The inputs are the audio file and the visual warning message, and the outputs are the audio alert and the display message.

[0667] Step 7:

[0668] The server monitors pedestrians' abnormal behavior in real time and detects sudden stops or falls. If an abnormality is detected, an alert is generated through a warning means and notified to surrounding vehicles and pedestrians. The input is real-time pedestrian data, and the output is the generated alert information.

[0669] Step 8:

[0670] Users (other pedestrians or vehicle drivers) receive the alert and take appropriate action. For example, a driver may bring the vehicle to a complete stop and pay attention to the pedestrian. The input is the alert information, and the output is the appropriate user action.

[0671] 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.

[0672] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[0673] System configuration

[0674] 1. Sensor means

[0675] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[0676] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[0677] 2. Artificial Intelligence Means

[0678] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[0679] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[0680] 3. Emotion Engine

[0681] The server runs an emotion engine to analyze the pedestrian's facial expressions and body movements.

[0682] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[0683] 4. Control Measures

[0684] The server operates the traffic light control module based on the analysis results of the AI ​​and the recognition results of the emotion engine, specifically extending the green light time as necessary.

[0685] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[0686] 5. Support measures

[0687] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[0688] The device adjusts the lighting within the intersection to visually alert pedestrians.

[0689] If the emotion engine determines that the user is feeling anxious or tense based on its analysis results, it will provide more calming voice guidance or changes.

[0690] 6. Warning measures

[0691] The server monitors pedestrians' movements and emotional states for any abnormalities and generates a warning signal if it detects any abnormalities.

[0692] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[0693] Program processing and specific examples

[0694] Photographing pedestrians by sensor means and preprocessing

[0695] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[0696] The server converts the pre-processed video into an input format for the AI ​​module.

[0697] Analysis of pedestrian speed and position using artificial intelligence means.

[0698] The server uses an AI module to detect pedestrians in the video and calculates the location coordinates and movement speed of each pedestrian in real time.

[0699] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[0700] Emotion analysis using an emotion engine

[0701] The server analyzes the pedestrian's facial expressions and body movements from the video data and uses an emotion engine to recognize the pedestrian's emotional state.

[0702] Based on the analysis results, the server identifies pedestrians who are anxious or tense and sends that information to support and warning means.

[0703] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[0704] The server uses specific criteria from the analysis results of the AI ​​and emotion engine to identify elderly people and people with walking difficulties, and calculates the walking time required for each person.

[0705] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[0706] Support means audio guidance and lighting support

[0707] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. Specifically, a voice message such as "The green light will be extended by 10 seconds from here" is provided via a speaker system.

[0708] The terminal adjusts lighting within the intersection, provides visual support, and provides calming audio guidance and lighting if pedestrians become nervous.

[0709] Detect anomalies and issue alerts using warning methods

[0710] The server monitors the pedestrian's movement and emotional state for any abnormalities, detecting sudden stops, falls, and abnormal emotional states (e.g., extreme anxiety or fear).

[0711] When an abnormality is detected, the device generates a warning signal and notifies vehicles and other pedestrians around the intersection, such as an emergency stop signal or an audio warning.

[0712] Specific examples

[0713] Example 1:

[0714] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[0715] The server receives the camera footage and analyzes it using AI and an emotion engine.

[0716] The device identifies elderly people and extends the green light time.

[0717] The server provides voice guidance regarding "extended green light."

[0718] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[0719] Seniors can cross the intersection safely.

[0720] Example 2:

[0721] At 5pm, a person fell while trying to pass through an intersection.

[0722] The server detects an anomaly and generates an alert.

[0723] The device sends an alert to those around the intersection and issues an emergency stop signal.

[0724] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[0725] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[0726] In this way, the system is highly integrated and provides a range of functions to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[0727] The processing flow will be explained below.

[0728] Step 1:

[0729] The server acquires real-time video data from high-resolution cameras installed at intersections, which are captured by sensor means and sent to a pre-processing module.

[0730] Step 2:

[0731] The server pre-processes the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, and then transfers the pre-processed data to the AI ​​module.

[0732] Step 3:

[0733] The server inputs the pre-processed video data into the AI ​​module to detect the speed and location of pedestrians, which then calculates the pedestrian's location coordinates and movement speed in real time and returns this data to the server.

[0734] Step 4:

[0735] The server uses the analysis results of the AI ​​module to determine whether a pedestrian is elderly or has mobility issues, based on the pedestrian's speed, movement pattern, and posture stability.

[0736] Step 5:

[0737] The server captures the pedestrian's facial expressions and body movements and inputs them into the emotion engine, which analyzes the pedestrian's emotional state (anxiety, tension, etc.) and returns the results to the server.

[0738] Step 6:

[0739] The server uses the results of AI and emotion engine analysis to calculate the walking time required for elderly people and those with mobility issues, taking into account the pedestrian's speed and the length of the intersection.

[0740] Step 7:

[0741] The terminal sets a new green signal time in the signal control module based on the analysis results received from the server, adds the required extension time to the current green signal time, and applies the new green signal time to the traffic light.

[0742] Step 8:

[0743] The server provides audio guidance and visual support based on the pedestrian's location and emotional state. For example, if the emotion engine detects anxiety, it will play a voice message such as "Please cross safely."

[0744] Step 9:

[0745] The device adjusts the lighting within the intersection and provides visual support, changing the brightness and flashing patterns of the lights to better attract pedestrians' attention.

[0746] Step 10:

[0747] The server monitors the pedestrian's movements and emotional state for abnormalities, and if it detects an abnormal state such as a sudden stop, a fall, or extreme anxiety or fear, it activates a warning mechanism.

[0748] Step 11:

[0749] When an abnormal condition is detected, the device immediately generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection, triggering an emergency stop signal and / or an audio warning.

[0750] Step 12:

[0751] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and can take appropriate action, allowing them to respond quickly and stay safe even when an abnormal situation occurs.

[0752] Example 2

[0753] 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."

[0754] Conventional intersection safety systems mainly adjust the green light time of traffic lights and only provide basic audio guidance and visual support for pedestrians. As a result, they sometimes lack sufficient support for elderly people and people with walking difficulties to cross intersections safely. Furthermore, they lack the functionality to consider the pedestrian's mental state, which means they are unable to provide appropriate support to pedestrians who feel anxious or tense. Therefore, there is a need for a system that can solve these problems and provide comprehensive support and safety measures for elderly people and people with walking difficulties.

[0755] 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.

[0756] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, means for preprocessing detected video data, artificial intelligence means for analyzing the preprocessed video data, means for determining whether the pedestrian is elderly or has difficulty walking based on the analyzed data, means including an emotion engine for analyzing facial expressions and body movements and recognizing the pedestrian's emotional state, control means for adjusting the green light time of a traffic light based on the analysis results and the emotional data, support means for providing audio or visual support to the pedestrian based on the analysis results and the emotional data, and warning means for monitoring whether there are any abnormalities in the pedestrian's movements or emotional state and issuing a warning if an abnormality is detected. This makes it possible to comprehensively monitor the physical and mental state of pedestrians and provide comprehensive safety measures and support for the elderly and people with difficulty walking.

[0757] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[0758] "Preprocessing" refers to the process of converting acquired video data into a format that is easier to analyze by removing noise, adjusting resolution, correcting frame rate, etc.

[0759] "Artificial intelligence means" refers to algorithms or modules that analyze pre-processed video data and extract information on the speed, position, and posture of pedestrians.

[0760] The "emotion engine" is an engine that analyzes the emotional state of pedestrians from their facial expressions and body movements.

[0761] The "control means" is a mechanism for adjusting the green light time of a traffic light based on the analysis results and emotion data.

[0762] "Support means" refers to a device that provides audio guidance and visual support to pedestrians based on analysis results and emotional data.

[0763] The "warning means" is a device that monitors whether there are any abnormalities in the movements or emotional state of pedestrians, and issues a warning if an abnormality is detected.

[0764] "Elderly" generally refers to pedestrians aged 60 or over.

[0765] A "person with walking difficulties" is a person who has difficulty walking normally due to physical or health reasons.

[0766] "Green light time" is the time a signal's green light is on, ensuring pedestrians can cross an intersection.

[0767] An "abnormal state" is a state in which a pedestrian deviates from normal walking behavior, such as a sudden stop or fall, or extreme anxiety or fear.

[0768] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[0769] Sensor Means

[0770] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[0771] The device preprocesses the video data, removing noise, adjusting the resolution, and correcting the frame rate.

[0772] Artificial Intelligence Tools

[0773] The server runs an AI module that analyzes the pre-processed video data, analyzing pedestrian speed and posture, and calculating each pedestrian's location coordinates and movement speed in real time.

[0774] Based on the analyzed data, the device determines whether the pedestrian is elderly or has difficulty walking, and calculates the walking time required for that pedestrian.

[0775] Emotion Engine

[0776] The server runs an emotion engine that analyzes pedestrians' facial expressions and body movements.

[0777] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[0778] Control means

[0779] The server operates the traffic light control module based on the AI ​​analysis results and the emotion engine's recognition results, extending the green light time as necessary.

[0780] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[0781] Support Measures

[0782] The server provides audio guidance and visual support for walking assistance, for example, providing a voice message such as "The green light will be extended by 10 seconds from here."

[0783] The device adjusts the lighting at the intersection and visually alerts pedestrians, and if it detects that the user is feeling anxious or nervous, it provides voice guidance and changes the lighting to calm them down.

[0784] warning means

[0785] The server monitors the pedestrian's movements and emotional state for abnormalities, and generates a warning signal if it detects an abnormality, such as a sudden stop or a fall.

[0786] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[0787] Specific examples

[0788] Example 1

[0789] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[0790] The server receives the camera footage and analyzes it using AI and an emotion engine.

[0791] The device identifies elderly people and extends the green light time.

[0792] The server provides voice guidance regarding "extended green light."

[0793] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[0794] The user can cross the intersection safely.

[0795] Example 2

[0796] At 5pm, a person falls while trying to pass through an intersection.

[0797] The server detects the anomaly and generates an alert.

[0798] The device sends an alert to those around the intersection and issues an emergency stop signal.

[0799] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[0800] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[0801] As can be seen, the system is highly integrated and provides a range of features to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[0802] Prompt Sentence Examples

[0803] "Calculate the extra walking time required for an elderly person to cross safely at an intersection."

[0804] "Create appropriate audio guidance for when pedestrians are nervous."

[0805] In this way, each element of the system works together to improve pedestrian safety and provide comprehensive support that enables pedestrians to cross intersections with confidence.

[0806] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0807] Step 1:

[0808] The server receives real-time video from high-resolution cameras installed at intersections. The input is the camera's video data, which includes pedestrian movements and the surrounding environment. The server preprocesses this data. Preprocessing includes noise removal, resolution adjustment, and frame rate correction, and the resulting video data is suitable for analysis.

[0809] Step 2:

[0810] The terminal converts the preprocessed video data received from the server into an input data format using a preprocessing algorithm. The input is the preprocessed video data, and the data format conversion is performed to make it compatible with the pedestrian detection algorithm. The converted data is then received.

[0811] Step 3:

[0812] The server inputs the converted video data into the AI ​​module to detect and analyze pedestrians. The converted video data is input, and the AI ​​module calculates the speed and location of pedestrians in real time. As a result, the location coordinates and movement speed data of each pedestrian are output.

[0813] Step 4:

[0814] The server analyzes the location and speed data obtained from the AI ​​module and determines whether each pedestrian is elderly or has difficulty walking. The input is location coordinates and movement speed data, and the output is the determination result of whether the pedestrian is elderly or has difficulty walking.

[0815] Step 5:

[0816] The server runs an emotion engine and analyzes the facial expressions and body movements of pedestrians from the received video data. The inputs are the judgment results obtained in the previous step and the video data, and the emotion engine identifies pedestrians who are feeling anxious or nervous. The analysis results are output as data on the pedestrian's emotional state.

[0817] Step 6:

[0818] The server operates the traffic light control module based on the analysis results of the AI ​​module and the recognition results of the emotion engine. The input is the judgment result and emotional state data of elderly people and people with walking difficulties, and the output is an instruction to extend the green light time. This instruction extends the green light time as necessary.

[0819] Step 7:

[0820] The terminal receives a control signal from the server and sends it to the traffic light. The input is the control signal from the server, and the output is an update of the traffic light setting and a new green light time is set.

[0821] Step 8:

[0822] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. The input is the pedestrian's location information and emotional state data, and the output is a voice guidance message. Specifically, the server generates a voice message such as "The green light will be extended by 10 seconds from here."

[0823] Step 9:

[0824] The device adjusts the lighting in the intersection to visually alert pedestrians. The input is instructions from the server, and the output is updated lighting settings. For nervous pedestrians, lighting effects are added to calm them down.

[0825] Step 10:

[0826] The server monitors pedestrians' movements and emotional states for abnormalities, detecting sudden stops, falls, and other anomalies. The input is real-time monitored pedestrian data, and if an anomaly is detected, a warning signal is generated. The output is an anomaly detection alert, which is sent to the warning means.

[0827] Step 11:

[0828] The terminal receives the generated warning signal and notifies vehicles and other pedestrians around the intersection. The input is the warning signal from the server, and the output is the turning on of warning lights in the intersection and the sound of a warning.

[0829] (Application example 2)

[0830] 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."

[0831] The problem that this invention aims to solve is to support elderly people and people with mobility difficulties to move safely and efficiently within a physical store, and to provide appropriate support based on their emotional state, such as anxiety or tension. Another objective is to ensure safety by detecting abnormal conditions and responding quickly. This aims to provide an environment where elderly people and people with mobility difficulties can enjoy shopping with peace of mind.

[0832] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0833] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, artificial intelligence means for analyzing the detected speed and position data, control means for adjusting the green light time of traffic lights based on the analysis results, support means for providing audio or visual support to pedestrians based on the analysis results, emotion analysis means for analyzing facial expressions and body movements to recognize emotional states, support means for providing audio guidance to pedestrians to encourage stability based on their emotional states, and warning means for detecting abnormal conditions and issuing alerts to surrounding vehicles and pedestrians. This makes it possible to support the safe movement of pedestrians and provide appropriate navigation and support while reducing tension and anxiety.

[0834] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[0835] "Artificial intelligence means" refers to techniques that utilize machine learning and algorithms to analyze detected speed and location data.

[0836] "Control means" refers to a device or system for adjusting the green light time of a traffic light based on the analysis results.

[0837] "Support means" refers to devices or technologies that provide audio or visual support to pedestrians based on the analysis results.

[0838] "Warning means" refers to devices and technologies that detect abnormal conditions and issue alerts to surrounding vehicles and pedestrians.

[0839] "Emotion analysis means" refers to devices or technologies that analyze facial expressions and body movements to recognize emotional states.

[0840] "Assistance tools" are devices and technologies that provide audio guidance to pedestrians to encourage stability based on their emotional state.

[0841] To realize this invention, the system operates as an application using smart glasses. The smart glasses use the following hardware and software to assist elderly people and people with mobility impairments to move safely and comfortably within a physical store.

[0842] Hardware

[0843] Smart glasses: Equipped with a camera, microphone, speaker, and GPS module.

[0844] Server: A high-performance computer for data processing and analysis.

[0845] In-store beacon: A device for obtaining accurate location information.

[0846] software

[0847] AI module: Machine learning algorithms for analyzing pedestrian speed and location data, using frameworks such as TensorFlow and PyTorch.

[0848] Emotion Engine: A program that analyzes facial expressions and body movements to recognize emotional states. It uses Emotion API and OpenCV.

[0849] Control module: This module adjusts the green light time and provides voice guidance. It uses Node.js and Python.

[0850] Alert system: A program for detecting abnormal conditions and generating alerts.

[0851] Processing flow

[0852] 1. Real-time image acquisition and preprocessing

[0853] A camera built into the smart glasses captures images of the inside of the store in real time.

[0854] The captured video is sent to a server where noise removal and frame rate correction are performed.

[0855] 2. Analysis of pedestrian speed and position

[0856] The server uses an AI module to detect pedestrians in the video data and calculate their location coordinates and speed.

[0857] Based on the analysis results, it is determined whether the pedestrian is elderly or has difficulty walking.

[0858] 3. Facial Expression and Body Movement Analysis

[0859] The server uses an emotion engine to analyze facial expressions and body movements to recognize emotional states.

[0860] Based on the recognized emotional state, the smart glasses provide audio guidance.

[0861] 4. Navigation aids and warning systems

[0862] Provide appropriate audio and visual navigation as a means of support.

[0863] If an abnormal condition is detected, the warning system will generate an alert and notify store staff.

[0864] Specific examples

[0865] Example 1

[0866] An elderly person wearing smart glasses visits a supermarket at 2 p.m.

[0867] The smart glasses receive the camera footage, which is then analyzed by the server using an AI module and emotion engine.

[0868] As a result of the analysis, elderly people are identified and appropriate route guidance is initiated.

[0869] Voice guidance such as "The cash register is 10 meters away" is provided through the smart glasses.

[0870] If it detects that the senior is feeling anxious, it will provide additional voice prompts to calm them down.

[0871] Example 2

[0872] At 5 p.m., an elderly person fell while walking inside the store.

[0873] When the smart glasses detect an abnormality, the server generates an alert and sends a notification to the store staff.

[0874] Furthermore, the emotion engine detects when the user is feeling fear due to falling, and appropriate measures are taken quickly.

[0875] Prompt Sentence Examples

[0876] "Develop an application for smart glasses that helps seniors navigate safely and stress-free within a store. The application should include the following features:

[0877] Images captured by the built-in camera are preprocessed in real time to detect the speed and location of pedestrians.

[0878] An artificial intelligence module is used to identify elderly people and those with walking difficulties.

[0879] The emotion engine analyzes facial expressions and body movements to recognize emotional states.

[0880] Providing navigation routes and audio and visual support.

[0881] When an abnormality is detected, a warning signal is generated and staff are notified.

[0882] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0883] Step 1:

[0884] The server receives real-time video footage from inside the store captured by the camera built into the smart glasses. The input is camera video data, and the output is pre-processed video data. Specifically, the server performs processing to remove noise from the video and correct the frame rate.

[0885] Step 2:

[0886] The server inputs the preprocessed video data into the AI ​​module. The input is noise-removed and frame-rate-corrected video data, and the output is the position coordinates and speed data of detected pedestrians. Specifically, the server detects pedestrians in the video and calculates the position and speed of each pedestrian.

[0887] Step 3:

[0888] The server identifies elderly people and people with walking difficulties based on the analysis results of the AI ​​module. The input is the position coordinates and speed data of pedestrians, and the output is identification information of elderly people and people with walking difficulties. Specifically, the server analyzes speed and posture to identify elderly people and people with walking difficulties.

[0889] Step 4:

[0890] The server uses emotion analysis means to analyze facial expressions and body movements. The input is video data of pedestrians, and the output is the identification result of their emotional state. Specifically, the server analyzes facial expressions and body movements to recognize the emotional state.

[0891] Step 5:

[0892] The server generates appropriate voice guidance for the pedestrian based on the emotional state. The inputs are the emotional state identification result and the pedestrian's location information, and the output is voice guidance data. Specifically, the server generates a voice message corresponding to the emotional state and sends it to the smart glasses.

[0893] Step 6:

[0894] The server detects abnormal conditions and activates the warning system. The inputs are the pedestrian's position coordinates and speed data, and the emotional state identification results, and the output is a warning signal. Specifically, the server detects abnormal conditions such as sudden stops, falls, extreme anxiety, or fear, and generates a warning signal to notify store staff.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] [Third embodiment]

[0899] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0900] 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.

[0901] 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).

[0902] 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.

[0903] 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.

[0904] 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).

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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."

[0911] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. The system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, and a warning means.

[0912] System configuration

[0913] 1. Sensor means

[0914] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[0915] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[0916] 2. Artificial Intelligence Means

[0917] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[0918] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[0919] 3. Control Measures

[0920] The server operates the traffic light control module based on the results of the AI ​​analysis, specifically extending the green light time as needed.

[0921] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[0922] 4. Support measures

[0923] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[0924] The device adjusts the lighting within the intersection to visually alert pedestrians.

[0925] 5. Warning measures

[0926] The server monitors pedestrians' movements for any abnormalities and generates a warning signal if it detects any abnormalities.

[0927] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[0928] Program processing and specific examples

[0929] Photographing pedestrians by sensor means and preprocessing

[0930] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[0931] The server converts the pre-processed video into an input format for the AI ​​module.

[0932] Analysis of pedestrian speed and position using artificial intelligence means.

[0933] The server uses an AI module to detect pedestrians in the video and calculate the location coordinates and movement speed of each pedestrian.

[0934] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[0935] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[0936] The server uses specific criteria from the analysis results to identify elderly people and people with walking difficulties, and calculates the walking time required for those people.

[0937] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[0938] Support means audio guidance and lighting support

[0939] The server provides audio guidance and visual support at the appropriate time based on the pedestrian's location information.

[0940] The device operates the speaker system and lighting system to convey messages to pedestrians such as "Watch out for extended green lights."

[0941] Detect anomalies and issue alerts using warning methods

[0942] The server monitors pedestrians' movements for any abnormalities and detects any abnormalities such as sudden stops or falls.

[0943] When an abnormality is detected, the device generates a warning signal to notify vehicles and other pedestrians around the intersection.

[0944] Specific examples

[0945] Example 1:

[0946] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[0947] The server receives the camera footage and analyzes it using an AI module.

[0948] The device identifies elderly people and extends the green light time.

[0949] The server provides voice guidance regarding "extended green light."

[0950] Seniors can cross the intersection safely.

[0951] Example 2:

[0952] At 5pm, a person fell while trying to pass through an intersection.

[0953] The server detects an anomaly and generates an alert.

[0954] The device sends an alert to those around the intersection and issues an emergency stop signal.

[0955] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[0956] In this way, the system is highly integrated and offers a range of functions to ensure the safety of the elderly and those with mobility impairments.

[0957] The processing flow will be explained below.

[0958] Step 1:

[0959] The server acquires video data in real time from cameras installed at intersections, which are transmitted to the server via sensor means and passed to an image processing module for pre-processing.

[0960] Step 2:

[0961] The server performs preprocessing on the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, enabling the AI ​​to accurately recognize pedestrians.

[0962] Step 3:

[0963] The server inputs the preprocessed video data into the AI ​​module to detect pedestrians, which then calculates their location coordinates and movement speed in real time.

[0964] Step 4:

[0965] The server analyzes the data of detected pedestrians and identifies elderly people and those with walking difficulties, using information such as the pedestrian's speed, movement patterns, and posture stability.

[0966] Step 5:

[0967] The server calculates the walking time required for identified elderly people or people with walking difficulties, based on the speed of the pedestrian and the length of the intersection.

[0968] Step 6:

[0969] The terminal sets a new green signal time in the signal control module based on the analysis result received from the server, adding the required extension time to the current green signal time and setting the new green signal time in the traffic light.

[0970] Step 7:

[0971] The server generates voice guidance at appropriate times based on the pedestrian's location information, such as "The green light will be extended by 10 seconds from here" via a speaker system.

[0972] Step 8:

[0973] The device adjusts lighting within the intersection and provides visual support, drawing pedestrians' attention to safely cross the intersection.

[0974] Step 9:

[0975] The server monitors pedestrians' movements to see if there are any abnormalities. If the server detects any abnormal movements such as a sudden stop or a fall, it will recognize this as an abnormal situation.

[0976] Step 10:

[0977] When an abnormal condition is detected, the device generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection. Specifically, an emergency stop signal or an audio warning is issued.

[0978] Step 11:

[0979] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and take appropriate action, thereby ensuring safety when an abnormal situation occurs.

[0980] Example 1

[0981] 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."

[0982] When elderly people or people with walking difficulties cross intersections, they often lack the time to cross safely. In such cases, the risk of an accident increases. In addition, improper control of traffic signals can have a significant impact on other pedestrians and vehicles. Furthermore, rapid response is required in the event of pedestrians suddenly stopping or falling, or other abnormal behavior. It is necessary to solve these issues and ensure that all traffic participants can use intersections safely.

[0983] 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.

[0984] In this invention, the server includes a sensor for capturing pedestrian video in real time, a processing unit for preprocessing the captured video to detect the speed and location of pedestrians, an artificial intelligence unit for detecting pedestrians based on the preprocessed video data and analyzing their location and speed, a determination unit for identifying elderly people or people with walking difficulties and calculating the required walking time, a control unit for extending the green light time based on the calculated walking time, a support unit for providing audio guidance and visual support, a monitoring unit for detecting abnormal pedestrian behavior and generating a warning signal, and a notification unit for notifying the generated warning signal. This allows for an increase in the time required to safely cross an intersection as needed, allowing elderly people and people with walking difficulties to use the intersection safely. Furthermore, by quickly responding to abnormal behavior, the risk of accidents can be reduced.

[0985] "Sensor means" refers to a high resolution camera or other sensing device for acquiring video data in real time.

[0986] "Processing means" refers to a data processing device for pre-processing the acquired video data and detecting the velocity and position.

[0987] "Artificial intelligence means" refers to machine learning algorithms and models that analyze pre-processed video data and identify the location and speed of pedestrians.

[0988] "Determination means" refers to a device or algorithm that determines whether an elderly person or a person with walking difficulty is present based on the analysis results and calculates the walking time required for that person.

[0989] The "control means" refers to a traffic light control device that appropriately extends the green light time of a traffic light at an intersection based on the calculated walking time.

[0990] "Support means" refers to devices that provide audio guidance and visual support to pedestrians crossing an intersection.

[0991] "Monitoring means" refers to devices or systems that monitor pedestrian movement and detect abnormal behavior such as sudden stops or falls.

[0992] "Notification means" refers to a device for notifying vehicles and other pedestrians around the intersection of the generated warning signal.

[0993] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. This system is implemented by combining a sensor means, a processing means, an artificial intelligence means, a determination means, a control means, a support means, a monitoring means, and a notification means.

[0994] Program Generation and Processing Description

[0995] 1. Sensor means

[0996] The server acquires pedestrian video data in real time using high-resolution cameras installed at intersections. The cameras have a resolution of 1080p and capture video at 30 frames per second, enabling high-quality video acquisition.

[0997] 2. Processing Methods

[0998] The server preprocesses the acquired video data. Specifically, it uses the OpenCV library to remove noise from the video frames and correct the frame rate. For example, it uses a Gaussian filter to remove noise and stabilize the video frames.

[0999] 3. Artificial Intelligence Means

[1000] The server inputs the preprocessed video data into a machine learning algorithm (e.g., a CNN model using TensorFlow or PyTorch) to detect the location coordinates and movement speed of pedestrians. Specifically, it uses a pre-trained model such as ResNet to identify the location and speed by outputting the bounding box of the pedestrian.

[1001] 4. Judgment means

[1002] The server then uses the analysis results to determine whether a person is elderly or has difficulty walking. Criteria for this include walking speed of 0.5 m / s or less, and specific posture characteristics (e.g., leaning forward, using a cane). This improves the accuracy of detecting elderly people and people with difficulty walking.

[1003] 5. Control Measures

[1004] Based on the results of the judgment, the terminal accesses the intersection's signal control system and appropriately extends the green light time. For example, it sends the new green light extension time to a Siemens signal controller, which then controls the traffic lights.

[1005] 6. Support Measures

[1006] The server uses the Google Text-to-Speech API to generate an audio message that says, "The green light will be extended by 10 seconds," which is then played over the intersection's speakers. Additionally, as a visual aid, LED lights of a specific color flash to warn pedestrians.

[1007] The terminal controls Philips smart LED lights and adjusts the lighting within the intersection appropriately, providing visual support.

[1008] 7. Monitoring measures

[1009] The server analyzes the video data collected in real time and detects abnormal behavior such as sudden stops or falls by pedestrians. For example, it runs an algorithm that monitors sudden posture changes or sudden stops in real time.

[1010] 8. Means of notification

[1011] If the server detects any abnormal behavior, it generates a warning signal. This can be generated in various forms, such as an emergency stop signal or an audio warning. It also generates an audio warning message, "Caution, a pedestrian has fallen," and notifies those around it via speakers or LED displays.

[1012] The device then notifies the generated warning signal to vehicles and other pedestrians around the intersection, enabling a rapid response in the event of an abnormality.

[1013] Specific examples

[1014] Example 1: Elderly people crossing an intersection

[1015] The user (elderly person) arrives at the intersection at 11:00 AM.

[1016] The server acquires video data in real time from a high-resolution camera and performs preprocessing using OpenCV.

[1017] The server inputs the video data into a pre-trained TensorFlow model to detect elderly people and determine their walking speed as 0.4 m / s.

[1018] The terminal accesses the traffic light control system and extends the green light time from 30 seconds to 35 seconds.

[1019] The server uses the Google Text-to-Speech API to announce, "The green light will be extended by 10 seconds," and plays it over the speaker. It also makes the smart LED light flash blue to warn the driver.

[1020] The user (elderly person) can cross the intersection safely.

[1021] Example prompt sentence:

[1022] Give a concrete example of an elderly person crossing an intersection. Explain in detail how the system works to assist the elderly person.

[1023] Example 2: Pedestrian falls

[1024] A user (pedestrian) tries to cross an intersection at 5pm.

[1025] The server detects sudden falls by pedestrians in real time and identifies abnormalities.

[1026] The device generates a warning signal and issues a warning via a speaker or LED display board saying, "Caution, a pedestrian has fallen."

[1027] Other users (pedestrians and drivers) receive a warning and take safety measures.

[1028] Example prompt sentence:

[1029] Explain how the system detects and alerts a pedestrian if they fall at an intersection.

[1030] In this way, the system of the present invention combines various means to provide a comprehensive solution for elderly people and people with mobility impairments to safely use intersections.

[1031] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1032] Step 1:

[1033] The server acquires video data in real time from a high-resolution camera installed at an intersection. It receives high-resolution video (1080p, 30 frames per second) as input and obtains video data for preprocessing as output. The camera can provide clear video both day and night. Specifically, the video stream from the camera is sent to the server using the RTSP protocol.

[1034] Step 2:

[1035] The server preprocesses the captured video data. It receives the captured video data as input, performs noise removal and frame rate correction, and outputs analyzable video data. Specifically, it uses the OpenCV library to apply a Gaussian filter to remove noise and smooth the frames, thereby improving the accuracy of pedestrian detection.

[1036] Step 3:

[1037] The server inputs the preprocessed video data into a machine learning algorithm. It receives the preprocessed video data as input and outputs data to identify the location coordinates and movement speed of pedestrians. Specifically, it uses a CNN model such as ResNet using TensorFlow or PyTorch to calculate the bounding box (location coordinates) and speed of pedestrians.

[1038] Step 4:

[1039] The server determines whether a person is elderly or has difficulty walking based on the analysis results. It receives the pedestrian's location coordinates and movement speed data as input, and outputs the data identifying the person as elderly or has difficulty walking as the result of the determination. Specifically, it determines whether a pedestrian with a walking speed of 0.5 m / s or less is elderly, and then executes the determination algorithm taking into account specific posture characteristics.

[1040] Step 5:

[1041] Based on the judgment result, the terminal sends signal information to the signal control system to extend the green light time. It receives the judgment result as input and outputs signal control data to set the new green light time. Specifically, it sends an instruction to the Siemens signal controller to extend the green light time from 30 seconds to 35 seconds.

[1042] Step 6:

[1043] The server starts the voice guidance system and generates a voice message. It receives the judgment result and the new green light time data as input, and generates and outputs the voice guidance "The green light will be extended by 10 seconds." Specifically, it uses the Google Text-to-Speech API to generate the voice message and plays it from the speaker.

[1044] Step 7:

[1045] The device adjusts the lighting as a visual aid, receiving data on the new green light duration as input and outputting lighting control data to flash LED lights of a specific color. Specifically, the Philips smart LED lights flash blue to alert pedestrians.

[1046] Step 8:

[1047] The server monitors pedestrian movements in real time and detects abnormal behavior. It receives real-time video data as input and outputs a warning signal if an abnormality is detected. Specifically, it runs algorithms to detect sudden stops and falls and identify abnormalities.

[1048] Step 9:

[1049] The terminal notifies the generated warning signal. It receives abnormality detection data as input and outputs notification data to issue an emergency stop signal or voice warning. Specifically, it uses a speaker or LED display board to send out a warning message such as "Caution, a pedestrian has fallen" to notify surrounding vehicles and other pedestrians.

[1050] Through this series of steps, the system can provide support for elderly people and people with mobility impairments to cross intersections safely and respond quickly to abnormal behavior.

[1051] (Application example 1)

[1052] 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."

[1053] The goal is to solve the problem of insufficient support to prevent unexpected situations and accidents when elderly people and people with walking difficulties cross intersections safely, and the problem of a lack of technology for autonomous vehicles to properly recognize these pedestrians and drive safely. Furthermore, there is a need to build an integrated system to ensure the safety of pedestrians and facilitate the operation of autonomous vehicles.

[1054] 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.

[1055] In this invention, the server includes a sensor means for detecting the speed and position of pedestrians, an artificial intelligence means for analyzing the detected speed and position data, and a control means for adjusting the green light time of a traffic light based on the analysis results. This enables a means for identifying elderly people or people with walking difficulty in an autonomous vehicle and adjusting the vehicle speed, a means for acquiring camera images of the vehicle in real time and detecting pedestrians using an AI module, and a voice output means for providing a voice alert to pedestrians.

[1056] "Sensor means" refers to a device installed to detect the speed and position of a pedestrian.

[1057] "Artificial intelligence means" refers to AI technology used to analyze detected speed and location data and determine the attributes and status of pedestrians.

[1058] The "control means" is a system that adjusts the green light time of traffic lights based on the analysis results of the artificial intelligence means, thereby ensuring the safety of pedestrians.

[1059] "Support means" refers to means for providing audio or visual support to pedestrians based on the analysis results.

[1060] The "warning means" is a device that detects an abnormal condition and issues an alert to surrounding vehicles and pedestrians.

[1061] "Means for acquiring in real time" refers to a method for capturing video in real time using a vehicle camera and processing it immediately.

[1062] The "AI module" is software that uses artificial intelligence technology to detect pedestrians in camera footage and analyze their attributes.

[1063] "Means for identifying pedestrians" refers to a method that uses an AI module to determine whether a pedestrian is elderly or has walking difficulties.

[1064] "Means for adjusting vehicle speed" refers to a system that automatically slows or stops vehicles near intersections to ensure the safety of pedestrians.

[1065] "Audio output means" means a speaker system or other audio output device for providing an audio alert to a pedestrian.

[1066] System configuration

[1067] This invention relates to a support system for elderly people and people with walking difficulties to cross intersections safely. The system consists of the following main components:

[1068] 1. Sensor means

[1069] The server captures real-time video of pedestrians using a high-resolution camera mounted on the vehicle, which is then pre-processed to remove noise and correct the frame rate.

[1070] 2. Artificial Intelligence Means

[1071] The server uses an AI module (such as TensorFlow) to detect pedestrians from preprocessed video data, analyze the position and speed of each pedestrian, and determine whether they are elderly or have difficulty walking based on the analysis results.

[1072] 3. Control Measures

[1073] The server will adjust the green light time at intersections if it identifies elderly people or people with walking difficulties, and the autonomous vehicle will enter intersections at an appropriate speed and stop if necessary.

[1074] 4. Support measures

[1075] The server uses a voice output method (such as gTTS) to provide a voice alert such as "Pedestrians present, stop vehicle," as well as a visual warning.

[1076] 5. Warning measures

[1077] The server monitors for abnormal conditions such as sudden stops or falls by pedestrians, and if detected, generates an alert that is sent to surrounding vehicles and pedestrians.

[1078] System Operation

[1079] The system operates by combining a high-resolution camera, an AI module, and an audio output device. The camera captures video data in real time and the server pre-processes the video data. The pre-processed data is input into the AI ​​module, which analyzes pedestrian attributes (such as whether they are elderly or have difficulty walking). Based on the analysis results, the control means adjusts the green light time for the traffic light, and the support means provides audio and visual support.

[1080] Specific examples

[1081] The following is a specific example of the system.

[1082] Example 1: When there is an elderly person near an intersection

[1083] The server captures images using a high-resolution camera and uses an AI module to determine whether the person is elderly.

[1084] The control means extends the green light time of the traffic light, and the support means issues an audio alert saying "Green light extended."

[1085] Example 2: When a pedestrian falls near an intersection

[1086] The server detects abnormal pedestrian behavior and the warning means generates an alert.

[1087] Users (other pedestrians and vehicle drivers) receive an alert and take appropriate action.

[1088] Prompt Sentence Examples

[1089] "Please create the following program. This is code that will acquire video footage from a vehicle-mounted camera in real time, detect pedestrians using an AI model, and safely adjust the speed. If the pedestrian is elderly or has difficulty walking, the code will have the function of stopping the vehicle and issuing an audio alert."

[1090] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1091] Step 1:

[1092] The server captures video in real time using a high-resolution camera mounted on the vehicle. The captured video is pre-processed to remove noise and correct the frame rate. The input of this process is the video data from the camera, and the output is the pre-processed video data.

[1093] Step 2:

[1094] The server inputs the preprocessed video data into an AI module, which uses a deep learning framework such as TensorFlow to detect pedestrians in the video. The input is the preprocessed video data, and the output is the pedestrian's location coordinates and movement speed data.

[1095] Step 3:

[1096] The server analyzes the output data from the AI ​​module to identify elderly people and people with walking difficulties. This identification includes analyzing the pedestrian's movement speed and posture. The input is the pedestrian's position coordinates and movement speed data, and the output is information identifying elderly people and people with walking difficulties.

[1097] Step 4:

[1098] The server adjusts the green light time based on the analysis results. This adjustment includes adding the time required for identified elderly people and people with mobility impairments to cross the intersection safely. The input is the identification information, and the output is the adjusted green light time.

[1099] Step 5:

[1100] The server uses the voice output means to provide voice guidance when pedestrians cross the intersection. It uses a text-to-speech synthesis tool such as gTTS to generate a voice alert saying "Pedestrians present, stop vehicles." The input is the identification result and traffic light information, and the output is the generated voice file.

[1101] Step 6:

[1102] The device plays the generated audio alert and also generates a visual warning, such as displaying a "Watch out for pedestrians" or "Vehicle stopped" message on the vehicle's dashboard. The inputs are the audio file and the visual warning message, and the outputs are the audio alert and the display message.

[1103] Step 7:

[1104] The server monitors pedestrians' abnormal behavior in real time and detects sudden stops or falls. If an abnormality is detected, an alert is generated through a warning means and notified to surrounding vehicles and pedestrians. The input is real-time pedestrian data, and the output is the generated alert information.

[1105] Step 8:

[1106] Users (other pedestrians or vehicle drivers) receive the alert and take appropriate action. For example, a driver may bring the vehicle to a complete stop and pay attention to the pedestrian. The input is the alert information, and the output is the appropriate user action.

[1107] 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.

[1108] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[1109] System configuration

[1110] 1. Sensor means

[1111] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[1112] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[1113] 2. Artificial Intelligence Means

[1114] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[1115] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[1116] 3. Emotion Engine

[1117] The server runs an emotion engine to analyze the pedestrian's facial expressions and body movements.

[1118] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[1119] 4. Control Measures

[1120] The server operates the traffic light control module based on the analysis results of the AI ​​and the recognition results of the emotion engine, specifically extending the green light time as necessary.

[1121] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[1122] 5. Support measures

[1123] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[1124] The device adjusts the lighting within the intersection to visually alert pedestrians.

[1125] If the emotion engine determines that the user is feeling anxious or tense based on its analysis results, it will provide more calming voice guidance or changes.

[1126] 6. Warning measures

[1127] The server monitors pedestrians' movements and emotional states for any abnormalities and generates a warning signal if it detects any abnormalities.

[1128] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[1129] Program processing and specific examples

[1130] Photographing pedestrians by sensor means and preprocessing

[1131] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[1132] The server converts the pre-processed video into an input format for the AI ​​module.

[1133] Analysis of pedestrian speed and position using artificial intelligence means.

[1134] The server uses an AI module to detect pedestrians in the video and calculates the location coordinates and movement speed of each pedestrian in real time.

[1135] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[1136] Emotion analysis using an emotion engine

[1137] The server analyzes the pedestrian's facial expressions and body movements from the video data and uses an emotion engine to recognize the pedestrian's emotional state.

[1138] Based on the analysis results, the server identifies pedestrians who are anxious or tense and sends that information to support and warning means.

[1139] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[1140] The server uses specific criteria from the analysis results of the AI ​​and emotion engine to identify elderly people and people with walking difficulties, and calculates the walking time required for each person.

[1141] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[1142] Support means audio guidance and lighting support

[1143] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. Specifically, a voice message such as "The green light will be extended by 10 seconds from here" is provided via a speaker system.

[1144] The terminal adjusts lighting within the intersection, provides visual support, and provides calming audio guidance and lighting if pedestrians become nervous.

[1145] Detect anomalies and issue alerts using warning methods

[1146] The server monitors the pedestrian's movement and emotional state for any abnormalities, detecting sudden stops, falls, and abnormal emotional states (e.g., extreme anxiety or fear).

[1147] When an abnormality is detected, the device generates a warning signal and notifies vehicles and other pedestrians around the intersection, such as an emergency stop signal or an audio warning.

[1148] Specific examples

[1149] Example 1:

[1150] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[1151] The server receives the camera footage and analyzes it using AI and an emotion engine.

[1152] The device identifies elderly people and extends the green light time.

[1153] The server provides voice guidance regarding "extended green light."

[1154] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[1155] Seniors can cross the intersection safely.

[1156] Example 2:

[1157] At 5pm, a person fell while trying to pass through an intersection.

[1158] The server detects an anomaly and generates an alert.

[1159] The device sends an alert to those around the intersection and issues an emergency stop signal.

[1160] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[1161] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[1162] In this way, the system is highly integrated and provides a range of functions to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[1163] The processing flow will be explained below.

[1164] Step 1:

[1165] The server acquires real-time video data from high-resolution cameras installed at intersections, which are captured by sensor means and sent to a pre-processing module.

[1166] Step 2:

[1167] The server pre-processes the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, and then transfers the pre-processed data to the AI ​​module.

[1168] Step 3:

[1169] The server inputs the pre-processed video data into the AI ​​module to detect the speed and location of pedestrians, which then calculates the pedestrian's location coordinates and movement speed in real time and returns this data to the server.

[1170] Step 4:

[1171] The server uses the analysis results of the AI ​​module to determine whether a pedestrian is elderly or has mobility issues, based on the pedestrian's speed, movement pattern, and posture stability.

[1172] Step 5:

[1173] The server captures the pedestrian's facial expressions and body movements and inputs them into the emotion engine, which analyzes the pedestrian's emotional state (anxiety, tension, etc.) and returns the results to the server.

[1174] Step 6:

[1175] The server uses the results of AI and emotion engine analysis to calculate the walking time required for elderly people and those with mobility issues, taking into account the pedestrian's speed and the length of the intersection.

[1176] Step 7:

[1177] The terminal sets a new green signal time in the signal control module based on the analysis results received from the server, adds the required extension time to the current green signal time, and applies the new green signal time to the traffic light.

[1178] Step 8:

[1179] The server provides audio guidance and visual support based on the pedestrian's location and emotional state. For example, if the emotion engine detects anxiety, it will play a voice message such as "Please cross safely."

[1180] Step 9:

[1181] The device adjusts the lighting within the intersection and provides visual support, changing the brightness and flashing patterns of the lights to better attract pedestrians' attention.

[1182] Step 10:

[1183] The server monitors the pedestrian's movements and emotional state for abnormalities, and if it detects an abnormal state such as a sudden stop, a fall, or extreme anxiety or fear, it activates a warning mechanism.

[1184] Step 11:

[1185] When an abnormal condition is detected, the device immediately generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection, triggering an emergency stop signal and / or an audio warning.

[1186] Step 12:

[1187] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and can take appropriate action, allowing them to respond quickly and stay safe even when an abnormal situation occurs.

[1188] Example 2

[1189] 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."

[1190] Conventional intersection safety systems mainly adjust the green light time of traffic lights and only provide basic audio guidance and visual support for pedestrians. As a result, they sometimes lack sufficient support for elderly people and people with walking difficulties to cross intersections safely. Furthermore, they lack the functionality to consider the pedestrian's mental state, which means they are unable to provide appropriate support to pedestrians who feel anxious or tense. Therefore, there is a need for a system that can solve these problems and provide comprehensive support and safety measures for elderly people and people with walking difficulties.

[1191] 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.

[1192] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, means for preprocessing detected video data, artificial intelligence means for analyzing the preprocessed video data, means for determining whether the pedestrian is elderly or has difficulty walking based on the analyzed data, means including an emotion engine for analyzing facial expressions and body movements and recognizing the pedestrian's emotional state, control means for adjusting the green light time of a traffic light based on the analysis results and the emotional data, support means for providing audio or visual support to the pedestrian based on the analysis results and the emotional data, and warning means for monitoring whether there are any abnormalities in the pedestrian's movements or emotional state and issuing a warning if an abnormality is detected. This makes it possible to comprehensively monitor the physical and mental state of pedestrians and provide comprehensive safety measures and support for the elderly and people with difficulty walking.

[1193] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[1194] "Preprocessing" refers to the process of converting acquired video data into a format that is easier to analyze by removing noise, adjusting resolution, correcting frame rate, etc.

[1195] "Artificial intelligence means" refers to algorithms or modules that analyze pre-processed video data and extract information on the speed, position, and posture of pedestrians.

[1196] The "emotion engine" is an engine that analyzes the emotional state of pedestrians from their facial expressions and body movements.

[1197] The "control means" is a mechanism for adjusting the green light time of a traffic light based on the analysis results and emotion data.

[1198] "Support means" refers to a device that provides audio guidance and visual support to pedestrians based on analysis results and emotional data.

[1199] The "warning means" is a device that monitors whether there are any abnormalities in the movements or emotional state of pedestrians, and issues a warning if an abnormality is detected.

[1200] "Elderly" generally refers to pedestrians aged 60 or over.

[1201] A "person with walking difficulties" is a person who has difficulty walking normally due to physical or health reasons.

[1202] "Green light time" is the time a signal's green light is on, ensuring pedestrians can cross an intersection.

[1203] An "abnormal state" is a state in which a pedestrian deviates from normal walking behavior, such as a sudden stop or fall, or extreme anxiety or fear.

[1204] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[1205] Sensor Means

[1206] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[1207] The device preprocesses the video data, removing noise, adjusting the resolution, and correcting the frame rate.

[1208] Artificial Intelligence Tools

[1209] The server runs an AI module that analyzes the pre-processed video data, analyzing pedestrian speed and posture, and calculating each pedestrian's location coordinates and movement speed in real time.

[1210] Based on the analyzed data, the device determines whether the pedestrian is elderly or has difficulty walking, and calculates the walking time required for that pedestrian.

[1211] Emotion Engine

[1212] The server runs an emotion engine that analyzes pedestrians' facial expressions and body movements.

[1213] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[1214] Control means

[1215] The server operates the traffic light control module based on the AI ​​analysis results and the emotion engine's recognition results, extending the green light time as necessary.

[1216] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[1217] Support Measures

[1218] The server provides audio guidance and visual support for walking assistance, for example, providing a voice message such as "The green light will be extended by 10 seconds from here."

[1219] The device adjusts the lighting at the intersection and visually alerts pedestrians, and if it detects that the user is feeling anxious or nervous, it provides voice guidance and changes the lighting to calm them down.

[1220] warning means

[1221] The server monitors the pedestrian's movements and emotional state for abnormalities, and generates a warning signal if it detects an abnormality, such as a sudden stop or a fall.

[1222] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[1223] Specific examples

[1224] Example 1

[1225] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[1226] The server receives the camera footage and analyzes it using AI and an emotion engine.

[1227] The device identifies elderly people and extends the green light time.

[1228] The server provides voice guidance regarding "extended green light."

[1229] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[1230] The user can cross the intersection safely.

[1231] Example 2

[1232] At 5pm, a person falls while trying to pass through an intersection.

[1233] The server detects the anomaly and generates an alert.

[1234] The device sends an alert to those around the intersection and issues an emergency stop signal.

[1235] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[1236] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[1237] As can be seen, the system is highly integrated and provides a range of features to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[1238] Prompt Sentence Examples

[1239] "Calculate the extra walking time required for an elderly person to cross safely at an intersection."

[1240] "Create appropriate audio guidance for when pedestrians are nervous."

[1241] In this way, each element of the system works together to improve pedestrian safety and provide comprehensive support that enables pedestrians to cross intersections with confidence.

[1242] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1243] Step 1:

[1244] The server receives real-time video from high-resolution cameras installed at intersections. The input is the camera's video data, which includes pedestrian movements and the surrounding environment. The server preprocesses this data. Preprocessing includes noise removal, resolution adjustment, and frame rate correction, and the resulting video data is suitable for analysis.

[1245] Step 2:

[1246] The terminal converts the preprocessed video data received from the server into an input data format using a preprocessing algorithm. The input is the preprocessed video data, and the data format conversion is performed to make it compatible with the pedestrian detection algorithm. The converted data is then received.

[1247] Step 3:

[1248] The server inputs the converted video data into the AI ​​module to detect and analyze pedestrians. The converted video data is input, and the AI ​​module calculates the speed and location of pedestrians in real time. As a result, the location coordinates and movement speed data of each pedestrian are output.

[1249] Step 4:

[1250] The server analyzes the location and speed data obtained from the AI ​​module and determines whether each pedestrian is elderly or has difficulty walking. The input is location coordinates and movement speed data, and the output is the determination result of whether the pedestrian is elderly or has difficulty walking.

[1251] Step 5:

[1252] The server runs an emotion engine and analyzes the facial expressions and body movements of pedestrians from the received video data. The inputs are the judgment results obtained in the previous step and the video data, and the emotion engine identifies pedestrians who are feeling anxious or nervous. The analysis results are output as data on the pedestrian's emotional state.

[1253] Step 6:

[1254] The server operates the traffic light control module based on the analysis results of the AI ​​module and the recognition results of the emotion engine. The input is the judgment result and emotional state data of elderly people and people with walking difficulties, and the output is an instruction to extend the green light time. This instruction extends the green light time as necessary.

[1255] Step 7:

[1256] The terminal receives a control signal from the server and sends it to the traffic light. The input is the control signal from the server, and the output is an update of the traffic light setting and a new green light time is set.

[1257] Step 8:

[1258] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. The input is the pedestrian's location information and emotional state data, and the output is a voice guidance message. Specifically, the server generates a voice message such as "The green light will be extended by 10 seconds from here."

[1259] Step 9:

[1260] The device adjusts the lighting in the intersection to visually alert pedestrians. The input is instructions from the server, and the output is updated lighting settings. For nervous pedestrians, lighting effects are added to calm them down.

[1261] Step 10:

[1262] The server monitors pedestrians' movements and emotional states for abnormalities, detecting sudden stops, falls, and other anomalies. The input is real-time monitored pedestrian data, and if an anomaly is detected, a warning signal is generated. The output is an anomaly detection alert, which is sent to the warning means.

[1263] Step 11:

[1264] The terminal receives the generated warning signal and notifies vehicles and other pedestrians around the intersection. The input is the warning signal from the server, and the output is the turning on of warning lights in the intersection and the sound of a warning.

[1265] (Application example 2)

[1266] 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."

[1267] The problem that this invention aims to solve is to support elderly people and people with mobility difficulties to move safely and efficiently within a physical store, and to provide appropriate support based on their emotional state, such as anxiety or tension. Another objective is to ensure safety by detecting abnormal conditions and responding quickly. This aims to provide an environment where elderly people and people with mobility difficulties can enjoy shopping with peace of mind.

[1268] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1269] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, artificial intelligence means for analyzing the detected speed and position data, control means for adjusting the green light time of traffic lights based on the analysis results, support means for providing audio or visual support to pedestrians based on the analysis results, emotion analysis means for analyzing facial expressions and body movements to recognize emotional states, support means for providing audio guidance to pedestrians to encourage stability based on their emotional states, and warning means for detecting abnormal conditions and issuing alerts to surrounding vehicles and pedestrians. This makes it possible to support the safe movement of pedestrians and provide appropriate navigation and support while reducing tension and anxiety.

[1270] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[1271] "Artificial intelligence means" refers to techniques that utilize machine learning and algorithms to analyze detected speed and location data.

[1272] "Control means" refers to a device or system for adjusting the green light time of a traffic light based on the analysis results.

[1273] "Support means" refers to devices or technologies that provide audio or visual support to pedestrians based on the analysis results.

[1274] "Warning means" refers to devices and technologies that detect abnormal conditions and issue alerts to surrounding vehicles and pedestrians.

[1275] "Emotion analysis means" refers to devices or technologies that analyze facial expressions and body movements to recognize emotional states.

[1276] "Assistance tools" are devices and technologies that provide audio guidance to pedestrians to encourage stability based on their emotional state.

[1277] To realize this invention, the system operates as an application using smart glasses. The smart glasses use the following hardware and software to assist elderly people and people with mobility impairments to move safely and comfortably within a physical store.

[1278] Hardware

[1279] Smart glasses: Equipped with a camera, microphone, speaker, and GPS module.

[1280] Server: A high-performance computer for data processing and analysis.

[1281] In-store beacon: A device for obtaining accurate location information.

[1282] software

[1283] AI module: Machine learning algorithms for analyzing pedestrian speed and location data, using frameworks such as TensorFlow and PyTorch.

[1284] Emotion Engine: A program that analyzes facial expressions and body movements to recognize emotional states. It uses Emotion API and OpenCV.

[1285] Control module: This module adjusts the green light time and provides voice guidance. It uses Node.js and Python.

[1286] Alert system: A program for detecting abnormal conditions and generating alerts.

[1287] Processing flow

[1288] 1. Real-time image acquisition and preprocessing

[1289] A camera built into the smart glasses captures images of the inside of the store in real time.

[1290] The captured video is sent to a server where noise removal and frame rate correction are performed.

[1291] 2. Analysis of pedestrian speed and position

[1292] The server uses an AI module to detect pedestrians in the video data and calculate their location coordinates and speed.

[1293] Based on the analysis results, it is determined whether the pedestrian is elderly or has difficulty walking.

[1294] 3. Facial Expression and Body Movement Analysis

[1295] The server uses an emotion engine to analyze facial expressions and body movements to recognize emotional states.

[1296] Based on the recognized emotional state, the smart glasses provide audio guidance.

[1297] 4. Navigation aids and warning systems

[1298] Provide appropriate audio and visual navigation as a means of support.

[1299] If an abnormal condition is detected, the warning system will generate an alert and notify store staff.

[1300] Specific examples

[1301] Example 1

[1302] An elderly person wearing smart glasses visits a supermarket at 2 p.m.

[1303] The smart glasses receive the camera footage, which is then analyzed by the server using an AI module and emotion engine.

[1304] As a result of the analysis, elderly people are identified and appropriate route guidance is initiated.

[1305] Voice guidance such as "The cash register is 10 meters away" is provided through the smart glasses.

[1306] If it detects that the senior is feeling anxious, it will provide additional voice prompts to calm them down.

[1307] Example 2

[1308] At 5 p.m., an elderly person fell while walking inside the store.

[1309] When the smart glasses detect an abnormality, the server generates an alert and sends a notification to the store staff.

[1310] Furthermore, the emotion engine detects when the user is feeling fear due to falling, and appropriate measures are taken quickly.

[1311] Prompt Sentence Examples

[1312] "Develop an application for smart glasses that helps seniors navigate safely and stress-free within a store. The application should include the following features:

[1313] Images captured by the built-in camera are preprocessed in real time to detect the speed and location of pedestrians.

[1314] An artificial intelligence module is used to identify elderly people and those with walking difficulties.

[1315] The emotion engine analyzes facial expressions and body movements to recognize emotional states.

[1316] Providing navigation routes and audio and visual support.

[1317] When an abnormality is detected, a warning signal is generated and staff are notified.

[1318] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1319] Step 1:

[1320] The server receives real-time video footage from inside the store captured by the camera built into the smart glasses. The input is camera video data, and the output is pre-processed video data. Specifically, the server performs processing to remove noise from the video and correct the frame rate.

[1321] Step 2:

[1322] The server inputs the preprocessed video data into the AI ​​module. The input is noise-removed and frame-rate-corrected video data, and the output is the position coordinates and speed data of detected pedestrians. Specifically, the server detects pedestrians in the video and calculates the position and speed of each pedestrian.

[1323] Step 3:

[1324] The server identifies elderly people and people with walking difficulties based on the analysis results of the AI ​​module. The input is the position coordinates and speed data of pedestrians, and the output is identification information of elderly people and people with walking difficulties. Specifically, the server analyzes speed and posture to identify elderly people and people with walking difficulties.

[1325] Step 4:

[1326] The server uses emotion analysis means to analyze facial expressions and body movements. The input is video data of pedestrians, and the output is the identification result of their emotional state. Specifically, the server analyzes facial expressions and body movements to recognize the emotional state.

[1327] Step 5:

[1328] The server generates appropriate voice guidance for the pedestrian based on the emotional state. The inputs are the emotional state identification result and the pedestrian's location information, and the output is voice guidance data. Specifically, the server generates a voice message corresponding to the emotional state and sends it to the smart glasses.

[1329] Step 6:

[1330] The server detects abnormal conditions and activates the warning system. The inputs are the pedestrian's position coordinates and speed data, and the emotional state identification results, and the output is a warning signal. Specifically, the server detects abnormal conditions such as sudden stops, falls, extreme anxiety, or fear, and generates a warning signal to notify store staff.

[1331] 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.

[1332] 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.

[1333] 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.

[1334] [Fourth embodiment]

[1335] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1336] 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.

[1337] 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).

[1338] 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.

[1339] 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.

[1340] 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).

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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."

[1348] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. The system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, and a warning means.

[1349] System configuration

[1350] 1. Sensor means

[1351] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[1352] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[1353] 2. Artificial Intelligence Means

[1354] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[1355] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[1356] 3. Control Measures

[1357] The server operates the traffic light control module based on the results of the AI ​​analysis, specifically extending the green light time as needed.

[1358] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[1359] 4. Support measures

[1360] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[1361] The device adjusts the lighting within the intersection to visually alert pedestrians.

[1362] 5. Warning measures

[1363] The server monitors pedestrians' movements for any abnormalities and generates a warning signal if it detects any abnormalities.

[1364] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[1365] Program processing and specific examples

[1366] Photographing pedestrians by sensor means and preprocessing

[1367] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[1368] The server converts the pre-processed video into an input format for the AI ​​module.

[1369] Analysis of pedestrian speed and position using artificial intelligence means.

[1370] The server uses an AI module to detect pedestrians in the video and calculate the location coordinates and movement speed of each pedestrian.

[1371] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[1372] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[1373] The server uses specific criteria from the analysis results to identify elderly people and people with walking difficulties, and calculates the walking time required for those people.

[1374] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[1375] Support means audio guidance and lighting support

[1376] The server provides audio guidance and visual support at the appropriate time based on the pedestrian's location information.

[1377] The device operates the speaker system and lighting system to convey messages to pedestrians such as "Watch out for extended green lights."

[1378] Detect anomalies and issue alerts using warning methods

[1379] The server monitors pedestrians' movements for any abnormalities and detects any abnormalities such as sudden stops or falls.

[1380] When an abnormality is detected, the device generates a warning signal to notify vehicles and other pedestrians around the intersection.

[1381] Specific examples

[1382] Example 1:

[1383] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[1384] The server receives the camera footage and analyzes it using an AI module.

[1385] The device identifies elderly people and extends the green light time.

[1386] The server provides voice guidance regarding "extended green light."

[1387] Seniors can cross the intersection safely.

[1388] Example 2:

[1389] At 5pm, a person fell while trying to pass through an intersection.

[1390] The server detects an anomaly and generates an alert.

[1391] The device sends an alert to those around the intersection and issues an emergency stop signal.

[1392] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[1393] In this way, the system is highly integrated and offers a range of functions to ensure the safety of the elderly and those with mobility impairments.

[1394] The processing flow will be explained below.

[1395] Step 1:

[1396] The server acquires video data in real time from cameras installed at intersections, which are transmitted to the server via sensor means and passed to an image processing module for pre-processing.

[1397] Step 2:

[1398] The server performs preprocessing on the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, enabling the AI ​​to accurately recognize pedestrians.

[1399] Step 3:

[1400] The server inputs the preprocessed video data into the AI ​​module to detect pedestrians, which then calculates their location coordinates and movement speed in real time.

[1401] Step 4:

[1402] The server analyzes the data of detected pedestrians and identifies elderly people and those with walking difficulties, using information such as the pedestrian's speed, movement patterns, and posture stability.

[1403] Step 5:

[1404] The server calculates the walking time required for identified elderly people or people with walking difficulties, based on the speed of the pedestrian and the length of the intersection.

[1405] Step 6:

[1406] The terminal sets a new green signal time in the signal control module based on the analysis result received from the server, adding the required extension time to the current green signal time and setting the new green signal time in the traffic light.

[1407] Step 7:

[1408] The server generates voice guidance at appropriate times based on the pedestrian's location information, such as "The green light will be extended by 10 seconds from here" via a speaker system.

[1409] Step 8:

[1410] The device adjusts lighting within the intersection and provides visual support, drawing pedestrians' attention to safely cross the intersection.

[1411] Step 9:

[1412] The server monitors pedestrians' movements to see if there are any abnormalities. If the server detects any abnormal movements such as a sudden stop or a fall, it will recognize this as an abnormal situation.

[1413] Step 10:

[1414] When an abnormal condition is detected, the device generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection. Specifically, an emergency stop signal or an audio warning is issued.

[1415] Step 11:

[1416] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and take appropriate action, thereby ensuring safety when an abnormal situation occurs.

[1417] Example 1

[1418] 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."

[1419] When elderly people or people with walking difficulties cross intersections, they often lack the time to cross safely. In such cases, the risk of an accident increases. In addition, improper control of traffic signals can have a significant impact on other pedestrians and vehicles. Furthermore, rapid response is required in the event of pedestrians suddenly stopping or falling, or other abnormal behavior. It is necessary to solve these issues and ensure that all traffic participants can use intersections safely.

[1420] 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.

[1421] In this invention, the server includes a sensor for capturing pedestrian video in real time, a processing unit for preprocessing the captured video to detect the speed and location of pedestrians, an artificial intelligence unit for detecting pedestrians based on the preprocessed video data and analyzing their location and speed, a determination unit for identifying elderly people or people with walking difficulties and calculating the required walking time, a control unit for extending the green light time based on the calculated walking time, a support unit for providing audio guidance and visual support, a monitoring unit for detecting abnormal pedestrian behavior and generating a warning signal, and a notification unit for notifying the generated warning signal. This allows for an increase in the time required to safely cross an intersection as needed, allowing elderly people and people with walking difficulties to use the intersection safely. Furthermore, by quickly responding to abnormal behavior, the risk of accidents can be reduced.

[1422] "Sensor means" refers to a high resolution camera or other sensing device for acquiring video data in real time.

[1423] "Processing means" refers to a data processing device for pre-processing the acquired video data and detecting the velocity and position.

[1424] "Artificial intelligence means" refers to machine learning algorithms and models that analyze pre-processed video data and identify the location and speed of pedestrians.

[1425] "Determination means" refers to a device or algorithm that determines whether an elderly person or a person with walking difficulty is present based on the analysis results and calculates the walking time required for that person.

[1426] The "control means" refers to a traffic light control device that appropriately extends the green light time of a traffic light at an intersection based on the calculated walking time.

[1427] "Support means" refers to devices that provide audio guidance and visual support to pedestrians crossing an intersection.

[1428] "Monitoring means" refers to devices or systems that monitor pedestrian movement and detect abnormal behavior such as sudden stops or falls.

[1429] "Notification means" refers to a device for notifying vehicles and other pedestrians around the intersection of the generated warning signal.

[1430] The present invention relates to a support system for elderly people and people with walking difficulties to safely cross intersections. This system is implemented by combining a sensor means, a processing means, an artificial intelligence means, a determination means, a control means, a support means, a monitoring means, and a notification means.

[1431] Program Generation and Processing Description

[1432] 1. Sensor means

[1433] The server acquires pedestrian video data in real time using high-resolution cameras installed at intersections. The cameras have a resolution of 1080p and capture video at 30 frames per second, enabling high-quality video acquisition.

[1434] 2. Processing Methods

[1435] The server preprocesses the acquired video data. Specifically, it uses the OpenCV library to remove noise from the video frames and correct the frame rate. For example, it uses a Gaussian filter to remove noise and stabilize the video frames.

[1436] 3. Artificial Intelligence Means

[1437] The server inputs the preprocessed video data into a machine learning algorithm (e.g., a CNN model using TensorFlow or PyTorch) to detect the location coordinates and movement speed of pedestrians. Specifically, it uses a pre-trained model such as ResNet to identify the location and speed by outputting the bounding box of the pedestrian.

[1438] 4. Judgment means

[1439] The server then uses the analysis results to determine whether a person is elderly or has difficulty walking. Criteria for this include walking speed of 0.5 m / s or less, and specific posture characteristics (e.g., leaning forward, using a cane). This improves the accuracy of detecting elderly people and people with difficulty walking.

[1440] 5. Control Measures

[1441] Based on the results of the judgment, the terminal accesses the intersection's signal control system and appropriately extends the green light time. For example, it sends the new green light extension time to a Siemens signal controller, which then controls the traffic lights.

[1442] 6. Support Measures

[1443] The server uses the Google Text-to-Speech API to generate an audio message that says, "The green light will be extended by 10 seconds," which is then played over the intersection's speakers. Additionally, as a visual aid, LED lights of a specific color flash to warn pedestrians.

[1444] The terminal controls Philips smart LED lights and adjusts the lighting within the intersection appropriately, providing visual support.

[1445] 7. Monitoring measures

[1446] The server analyzes the video data collected in real time and detects abnormal behavior such as sudden stops or falls by pedestrians. For example, it runs an algorithm that monitors sudden posture changes or sudden stops in real time.

[1447] 8. Means of notification

[1448] If the server detects any abnormal behavior, it generates a warning signal. This can be generated in various forms, such as an emergency stop signal or an audio warning. It also generates an audio warning message, "Caution, a pedestrian has fallen," and notifies those around it via speakers or LED displays.

[1449] The device then notifies the generated warning signal to vehicles and other pedestrians around the intersection, enabling a rapid response in the event of an abnormality.

[1450] Specific examples

[1451] Example 1: Elderly people crossing an intersection

[1452] The user (elderly person) arrives at the intersection at 11:00 AM.

[1453] The server acquires video data in real time from a high-resolution camera and performs preprocessing using OpenCV.

[1454] The server inputs the video data into a pre-trained TensorFlow model to detect elderly people and determine their walking speed as 0.4 m / s.

[1455] The terminal accesses the traffic light control system and extends the green light time from 30 seconds to 35 seconds.

[1456] The server uses the Google Text-to-Speech API to announce, "The green light will be extended by 10 seconds," and plays it over the speaker. It also makes the smart LED light flash blue to warn the driver.

[1457] The user (elderly person) can cross the intersection safely.

[1458] Example prompt sentence:

[1459] Give a concrete example of an elderly person crossing an intersection. Explain in detail how the system works to assist the elderly person.

[1460] Example 2: Pedestrian falls

[1461] A user (pedestrian) tries to cross an intersection at 5pm.

[1462] The server detects sudden falls by pedestrians in real time and identifies abnormalities.

[1463] The device generates a warning signal and issues a warning via a speaker or LED display board saying, "Caution, a pedestrian has fallen."

[1464] Other users (pedestrians and drivers) receive a warning and take safety measures.

[1465] Example prompt sentence:

[1466] Explain how the system detects and alerts a pedestrian if they fall at an intersection.

[1467] In this way, the system of the present invention combines various means to provide a comprehensive solution for elderly people and people with mobility impairments to safely use intersections.

[1468] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1469] Step 1:

[1470] The server acquires video data in real time from a high-resolution camera installed at an intersection. It receives high-resolution video (1080p, 30 frames per second) as input and obtains video data for preprocessing as output. The camera can provide clear video both day and night. Specifically, the video stream from the camera is sent to the server using the RTSP protocol.

[1471] Step 2:

[1472] The server preprocesses the captured video data. It receives the captured video data as input, performs noise removal and frame rate correction, and outputs analyzable video data. Specifically, it uses the OpenCV library to apply a Gaussian filter to remove noise and smooth the frames, thereby improving the accuracy of pedestrian detection.

[1473] Step 3:

[1474] The server inputs the preprocessed video data into a machine learning algorithm. It receives the preprocessed video data as input and outputs data to identify the location coordinates and movement speed of pedestrians. Specifically, it uses a CNN model such as ResNet using TensorFlow or PyTorch to calculate the bounding box (location coordinates) and speed of pedestrians.

[1475] Step 4:

[1476] The server determines whether a person is elderly or has difficulty walking based on the analysis results. It receives the pedestrian's location coordinates and movement speed data as input, and outputs the data identifying the person as elderly or has difficulty walking as the result of the determination. Specifically, it determines whether a pedestrian with a walking speed of 0.5 m / s or less is elderly, and then executes the determination algorithm taking into account specific posture characteristics.

[1477] Step 5:

[1478] Based on the judgment result, the terminal sends signal information to the signal control system to extend the green light time. It receives the judgment result as input and outputs signal control data to set the new green light time. Specifically, it sends an instruction to the Siemens signal controller to extend the green light time from 30 seconds to 35 seconds.

[1479] Step 6:

[1480] The server starts the voice guidance system and generates a voice message. It receives the judgment result and the new green light time data as input, and generates and outputs the voice guidance "The green light will be extended by 10 seconds." Specifically, it uses the Google Text-to-Speech API to generate the voice message and plays it from the speaker.

[1481] Step 7:

[1482] The device adjusts the lighting as a visual aid, receiving data on the new green light duration as input and outputting lighting control data to flash LED lights of a specific color. Specifically, the Philips smart LED lights flash blue to alert pedestrians.

[1483] Step 8:

[1484] The server monitors pedestrian movements in real time and detects abnormal behavior. It receives real-time video data as input and outputs a warning signal if an abnormality is detected. Specifically, it runs algorithms to detect sudden stops and falls and identify abnormalities.

[1485] Step 9:

[1486] The terminal notifies the generated warning signal. It receives abnormality detection data as input and outputs notification data to issue an emergency stop signal or voice warning. Specifically, it uses a speaker or LED display board to send out a warning message such as "Caution, a pedestrian has fallen" to notify surrounding vehicles and other pedestrians.

[1487] Through this series of steps, the system can provide support for elderly people and people with mobility impairments to cross intersections safely and respond quickly to abnormal behavior.

[1488] (Application example 1)

[1489] 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."

[1490] The goal is to solve the problem of insufficient support to prevent unexpected situations and accidents when elderly people and people with walking difficulties cross intersections safely, and the problem of a lack of technology for autonomous vehicles to properly recognize these pedestrians and drive safely. Furthermore, there is a need to build an integrated system to ensure the safety of pedestrians and facilitate the operation of autonomous vehicles.

[1491] 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.

[1492] In this invention, the server includes a sensor means for detecting the speed and position of pedestrians, an artificial intelligence means for analyzing the detected speed and position data, and a control means for adjusting the green light time of a traffic light based on the analysis results. This enables a means for identifying elderly people or people with walking difficulty in an autonomous vehicle and adjusting the vehicle speed, a means for acquiring camera images of the vehicle in real time and detecting pedestrians using an AI module, and a voice output means for providing a voice alert to pedestrians.

[1493] "Sensor means" refers to a device installed to detect the speed and position of a pedestrian.

[1494] "Artificial intelligence means" refers to AI technology used to analyze detected speed and location data and determine the attributes and status of pedestrians.

[1495] The "control means" is a system that adjusts the green light time of traffic lights based on the analysis results of the artificial intelligence means, thereby ensuring the safety of pedestrians.

[1496] "Support means" refers to means for providing audio or visual support to pedestrians based on the analysis results.

[1497] The "warning means" is a device that detects an abnormal condition and issues an alert to surrounding vehicles and pedestrians.

[1498] "Means for acquiring in real time" refers to a method for capturing video in real time using a vehicle camera and processing it immediately.

[1499] The "AI module" is software that uses artificial intelligence technology to detect pedestrians in camera footage and analyze their attributes.

[1500] "Means for identifying pedestrians" refers to a method that uses an AI module to determine whether a pedestrian is elderly or has walking difficulties.

[1501] "Means for adjusting vehicle speed" refers to a system that automatically slows or stops vehicles near intersections to ensure the safety of pedestrians.

[1502] "Audio output means" means a speaker system or other audio output device for providing an audio alert to a pedestrian.

[1503] System configuration

[1504] This invention relates to a support system for elderly people and people with walking difficulties to cross intersections safely. The system consists of the following main components:

[1505] 1. Sensor means

[1506] The server captures real-time video of pedestrians using a high-resolution camera mounted on the vehicle, which is then pre-processed to remove noise and correct the frame rate.

[1507] 2. Artificial Intelligence Means

[1508] The server uses an AI module (such as TensorFlow) to detect pedestrians from preprocessed video data, analyze the position and speed of each pedestrian, and determine whether they are elderly or have difficulty walking based on the analysis results.

[1509] 3. Control Measures

[1510] The server will adjust the green light time at intersections if it identifies elderly people or people with walking difficulties, and the autonomous vehicle will enter intersections at an appropriate speed and stop if necessary.

[1511] 4. Support measures

[1512] The server uses a voice output method (such as gTTS) to provide a voice alert such as "Pedestrians present, stop vehicle," as well as a visual warning.

[1513] 5. Warning measures

[1514] The server monitors for abnormal conditions such as sudden stops or falls by pedestrians, and if detected, generates an alert that is sent to surrounding vehicles and pedestrians.

[1515] System Operation

[1516] The system operates by combining a high-resolution camera, an AI module, and an audio output device. The camera captures video data in real time and the server pre-processes the video data. The pre-processed data is input into the AI ​​module, which analyzes pedestrian attributes (such as whether they are elderly or have difficulty walking). Based on the analysis results, the control means adjusts the green light time for the traffic light, and the support means provides audio and visual support.

[1517] Specific examples

[1518] The following is a specific example of the system.

[1519] Example 1: When there is an elderly person near an intersection

[1520] The server captures images using a high-resolution camera and uses an AI module to determine whether the person is elderly.

[1521] The control means extends the green light time of the traffic light, and the support means issues an audio alert saying "Green light extended."

[1522] Example 2: When a pedestrian falls near an intersection

[1523] The server detects abnormal pedestrian behavior and the warning means generates an alert.

[1524] Users (other pedestrians and vehicle drivers) receive an alert and take appropriate action.

[1525] Prompt Sentence Examples

[1526] "Please create the following program. This is code that will acquire video footage from a vehicle-mounted camera in real time, detect pedestrians using an AI model, and safely adjust the speed. If the pedestrian is elderly or has difficulty walking, the code will have the function of stopping the vehicle and issuing an audio alert."

[1527] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1528] Step 1:

[1529] The server captures video in real time using a high-resolution camera mounted on the vehicle. The captured video is pre-processed to remove noise and correct the frame rate. The input of this process is the video data from the camera, and the output is the pre-processed video data.

[1530] Step 2:

[1531] The server inputs the preprocessed video data into an AI module, which uses a deep learning framework such as TensorFlow to detect pedestrians in the video. The input is the preprocessed video data, and the output is the pedestrian's location coordinates and movement speed data.

[1532] Step 3:

[1533] The server analyzes the output data from the AI ​​module to identify elderly people and people with walking difficulties. This identification includes analyzing the pedestrian's movement speed and posture. The input is the pedestrian's position coordinates and movement speed data, and the output is information identifying elderly people and people with walking difficulties.

[1534] Step 4:

[1535] The server adjusts the green light time based on the analysis results. This adjustment includes adding the time required for identified elderly people and people with mobility impairments to cross the intersection safely. The input is the identification information, and the output is the adjusted green light time.

[1536] Step 5:

[1537] The server uses the voice output means to provide voice guidance when pedestrians cross the intersection. It uses a text-to-speech synthesis tool such as gTTS to generate a voice alert saying "Pedestrians present, stop vehicles." The input is the identification result and traffic light information, and the output is the generated voice file.

[1538] Step 6:

[1539] The device plays the generated audio alert and also generates a visual warning, such as displaying a "Watch out for pedestrians" or "Vehicle stopped" message on the vehicle's dashboard. The inputs are the audio file and the visual warning message, and the outputs are the audio alert and the display message.

[1540] Step 7:

[1541] The server monitors pedestrians' abnormal behavior in real time and detects sudden stops or falls. If an abnormality is detected, an alert is generated through a warning means and notified to surrounding vehicles and pedestrians. The input is real-time pedestrian data, and the output is the generated alert information.

[1542] Step 8:

[1543] Users (other pedestrians or vehicle drivers) receive the alert and take appropriate action. For example, a driver may bring the vehicle to a complete stop and pay attention to the pedestrian. The input is the alert information, and the output is the appropriate user action.

[1544] 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.

[1545] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[1546] System configuration

[1547] 1. Sensor means

[1548] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[1549] The device pre-processes the video data and runs algorithms to detect the speed and location of pedestrians.

[1550] 2. Artificial Intelligence Means

[1551] The server runs an AI module to analyze the acquired video data, which analyzes the speed and posture of pedestrians and determines whether they are elderly or have difficulty walking.

[1552] Based on the analyzed data, the device calculates the time required for pedestrians to cross the intersection safely.

[1553] 3. Emotion Engine

[1554] The server runs an emotion engine to analyze the pedestrian's facial expressions and body movements.

[1555] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[1556] 4. Control Measures

[1557] The server operates the traffic light control module based on the analysis results of the AI ​​and the recognition results of the emotion engine, specifically extending the green light time as necessary.

[1558] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[1559] 5. Support measures

[1560] The server provides audio guidance and visual support for walking assistance, for example, issuing a voice message such as "The green light will be extended by 10 seconds from here."

[1561] The device adjusts the lighting within the intersection to visually alert pedestrians.

[1562] If the emotion engine determines that the user is feeling anxious or tense based on its analysis results, it will provide more calming voice guidance or changes.

[1563] 6. Warning measures

[1564] The server monitors pedestrians' movements and emotional states for any abnormalities and generates a warning signal if it detects any abnormalities.

[1565] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[1566] Program processing and specific examples

[1567] Photographing pedestrians by sensor means and preprocessing

[1568] The server captures video from cameras installed at intersections in real time and preprocesses the video to remove noise and correct the frame rate.

[1569] The server converts the pre-processed video into an input format for the AI ​​module.

[1570] Analysis of pedestrian speed and position using artificial intelligence means.

[1571] The server uses an AI module to detect pedestrians in the video and calculates the location coordinates and movement speed of each pedestrian in real time.

[1572] The server stores the analysis results and determines whether the person is elderly or has difficulty walking.

[1573] Emotion analysis using an emotion engine

[1574] The server analyzes the pedestrian's facial expressions and body movements from the video data and uses an emotion engine to recognize the pedestrian's emotional state.

[1575] Based on the analysis results, the server identifies pedestrians who are anxious or tense and sends that information to support and warning means.

[1576] Identifying elderly people and people with walking difficulties and extending the green light time at traffic lights

[1577] The server uses specific criteria from the analysis results of the AI ​​and emotion engine to identify elderly people and people with walking difficulties, and calculates the walking time required for each person.

[1578] The terminal adds the calculated additional time to the current green light time to set a new green light time.

[1579] Support means audio guidance and lighting support

[1580] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. Specifically, a voice message such as "The green light will be extended by 10 seconds from here" is provided via a speaker system.

[1581] The terminal adjusts lighting within the intersection, provides visual support, and provides calming audio guidance and lighting if pedestrians become nervous.

[1582] Detect anomalies and issue alerts using warning methods

[1583] The server monitors the pedestrian's movement and emotional state for any abnormalities, detecting sudden stops, falls, and abnormal emotional states (e.g., extreme anxiety or fear).

[1584] When an abnormality is detected, the device generates a warning signal and notifies vehicles and other pedestrians around the intersection, such as an emergency stop signal or an audio warning.

[1585] Specific examples

[1586] Example 1:

[1587] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[1588] The server receives the camera footage and analyzes it using AI and an emotion engine.

[1589] The device identifies elderly people and extends the green light time.

[1590] The server provides voice guidance regarding "extended green light."

[1591] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[1592] Seniors can cross the intersection safely.

[1593] Example 2:

[1594] At 5pm, a person fell while trying to pass through an intersection.

[1595] The server detects an anomaly and generates an alert.

[1596] The device sends an alert to those around the intersection and issues an emergency stop signal.

[1597] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[1598] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[1599] In this way, the system is highly integrated and provides a range of functions to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[1600] The processing flow will be explained below.

[1601] Step 1:

[1602] The server acquires real-time video data from high-resolution cameras installed at intersections, which are captured by sensor means and sent to a pre-processing module.

[1603] Step 2:

[1604] The server pre-processes the received video data, specifically noise reduction, frame rate correction, and image resolution adjustment, and then transfers the pre-processed data to the AI ​​module.

[1605] Step 3:

[1606] The server inputs the pre-processed video data into the AI ​​module to detect the speed and location of pedestrians, which then calculates the pedestrian's location coordinates and movement speed in real time and returns this data to the server.

[1607] Step 4:

[1608] The server uses the analysis results of the AI ​​module to determine whether a pedestrian is elderly or has mobility issues, based on the pedestrian's speed, movement pattern, and posture stability.

[1609] Step 5:

[1610] The server captures the pedestrian's facial expressions and body movements and inputs them into the emotion engine, which analyzes the pedestrian's emotional state (anxiety, tension, etc.) and returns the results to the server.

[1611] Step 6:

[1612] The server uses the results of AI and emotion engine analysis to calculate the walking time required for elderly people and those with mobility issues, taking into account the pedestrian's speed and the length of the intersection.

[1613] Step 7:

[1614] The terminal sets a new green signal time in the signal control module based on the analysis results received from the server, adds the required extension time to the current green signal time, and applies the new green signal time to the traffic light.

[1615] Step 8:

[1616] The server provides audio guidance and visual support based on the pedestrian's location and emotional state. For example, if the emotion engine detects anxiety, it will play a voice message such as "Please cross safely."

[1617] Step 9:

[1618] The device adjusts the lighting within the intersection and provides visual support, changing the brightness and flashing patterns of the lights to better attract pedestrians' attention.

[1619] Step 10:

[1620] The server monitors the pedestrian's movements and emotional state for abnormalities, and if it detects an abnormal state such as a sudden stop, a fall, or extreme anxiety or fear, it activates a warning mechanism.

[1621] Step 11:

[1622] When an abnormal condition is detected, the device immediately generates a warning signal, which is then sent to vehicles and other pedestrians around the intersection, triggering an emergency stop signal and / or an audio warning.

[1623] Step 12:

[1624] Users (vehicle drivers and other pedestrians) receive warning signals and audio alerts and can take appropriate action, allowing them to respond quickly and stay safe even when an abnormal situation occurs.

[1625] Example 2

[1626] 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."

[1627] Conventional intersection safety systems mainly adjust the green light time of traffic lights and only provide basic audio guidance and visual support for pedestrians. As a result, they sometimes lack sufficient support for elderly people and people with walking difficulties to cross intersections safely. Furthermore, they lack the functionality to consider the pedestrian's mental state, which means they are unable to provide appropriate support to pedestrians who feel anxious or tense. Therefore, there is a need for a system that can solve these problems and provide comprehensive support and safety measures for elderly people and people with walking difficulties.

[1628] 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.

[1629] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, means for preprocessing detected video data, artificial intelligence means for analyzing the preprocessed video data, means for determining whether the pedestrian is elderly or has difficulty walking based on the analyzed data, means including an emotion engine for analyzing facial expressions and body movements and recognizing the pedestrian's emotional state, control means for adjusting the green light time of a traffic light based on the analysis results and the emotional data, support means for providing audio or visual support to the pedestrian based on the analysis results and the emotional data, and warning means for monitoring whether there are any abnormalities in the pedestrian's movements or emotional state and issuing a warning if an abnormality is detected. This makes it possible to comprehensively monitor the physical and mental state of pedestrians and provide comprehensive safety measures and support for the elderly and people with difficulty walking.

[1630] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[1631] "Preprocessing" refers to the process of converting acquired video data into a format that is easier to analyze by removing noise, adjusting resolution, correcting frame rate, etc.

[1632] "Artificial intelligence means" refers to algorithms or modules that analyze pre-processed video data and extract information on the speed, position, and posture of pedestrians.

[1633] The "emotion engine" is an engine that analyzes the emotional state of pedestrians from their facial expressions and body movements.

[1634] The "control means" is a mechanism for adjusting the green light time of a traffic light based on the analysis results and emotion data.

[1635] "Support means" refers to a device that provides audio guidance and visual support to pedestrians based on analysis results and emotional data.

[1636] The "warning means" is a device that monitors whether there are any abnormalities in the movements or emotional state of pedestrians, and issues a warning if an abnormality is detected.

[1637] "Elderly" generally refers to pedestrians aged 60 or over.

[1638] A "person with walking difficulties" is a person who has difficulty walking normally due to physical or health reasons.

[1639] "Green light time" is the time a signal's green light is on, ensuring pedestrians can cross an intersection.

[1640] An "abnormal state" is a state in which a pedestrian deviates from normal walking behavior, such as a sudden stop or fall, or extreme anxiety or fear.

[1641] The present invention relates to a system that provides comprehensive safety measures and support by combining an emotion engine with a support system that enables elderly people and people with walking difficulties to cross intersections safely. This system is implemented by combining a sensor means, an artificial intelligence means, a control means, a support means, a warning means, and an emotion engine.

[1642] Sensor Means

[1643] The server uses high-resolution cameras installed at intersections to capture images of pedestrians in real time.

[1644] The device preprocesses the video data, removing noise, adjusting the resolution, and correcting the frame rate.

[1645] Artificial Intelligence Tools

[1646] The server runs an AI module that analyzes the pre-processed video data, analyzing pedestrian speed and posture, and calculating each pedestrian's location coordinates and movement speed in real time.

[1647] Based on the analyzed data, the device determines whether the pedestrian is elderly or has difficulty walking, and calculates the walking time required for that pedestrian.

[1648] Emotion Engine

[1649] The server runs an emotion engine that analyzes pedestrians' facial expressions and body movements.

[1650] The server uses the emotion data recognized by the emotion engine to notify the support means if the pedestrian is feeling anxious or nervous.

[1651] Control means

[1652] The server operates the traffic light control module based on the AI ​​analysis results and the emotion engine's recognition results, extending the green light time as necessary.

[1653] The terminal sends a control signal directly to the traffic light to appropriately extend the green light time.

[1654] Support Measures

[1655] The server provides audio guidance and visual support for walking assistance, for example, providing a voice message such as "The green light will be extended by 10 seconds from here."

[1656] The device adjusts the lighting at the intersection and visually alerts pedestrians, and if it detects that the user is feeling anxious or nervous, it provides voice guidance and changes the lighting to calm them down.

[1657] warning means

[1658] The server monitors the pedestrian's movements and emotional state for abnormalities, and generates a warning signal if it detects an abnormality, such as a sudden stop or a fall.

[1659] The device then notifies vehicles and other pedestrians around the intersection of the generated warning signal, for example by issuing an emergency stop signal or an audio warning.

[1660] Specific examples

[1661] Example 1

[1662] At 11:00 a.m., there is an elderly person walking slowly at an intersection.

[1663] The server receives the camera footage and analyzes it using AI and an emotion engine.

[1664] The device identifies elderly people and extends the green light time.

[1665] The server provides voice guidance regarding "extended green light."

[1666] If the server's emotion engine detects that an elderly person is feeling anxious, it provides voice guidance to calm them down.

[1667] The user can cross the intersection safely.

[1668] Example 2

[1669] At 5pm, a person falls while trying to pass through an intersection.

[1670] The server detects the anomaly and generates an alert.

[1671] The device sends an alert to those around the intersection and issues an emergency stop signal.

[1672] The server's emotion engine detects that the fallen pedestrian is feeling fear and notifies those around them of this information.

[1673] Users (other pedestrians and drivers) receive an alert and take appropriate action.

[1674] As can be seen, the system is highly integrated and provides a range of features to ensure the safety of elderly people and those with mobility impairments, as well as additional support based on emotional state.

[1675] Prompt Sentence Examples

[1676] "Calculate the extra walking time required for an elderly person to cross safely at an intersection."

[1677] "Create appropriate audio guidance for when pedestrians are nervous."

[1678] In this way, each element of the system works together to improve pedestrian safety and provide comprehensive support that enables pedestrians to cross intersections with confidence.

[1679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1680] Step 1:

[1681] The server receives real-time video from high-resolution cameras installed at intersections. The input is the camera's video data, which includes pedestrian movements and the surrounding environment. The server preprocesses this data. Preprocessing includes noise removal, resolution adjustment, and frame rate correction, and the resulting video data is suitable for analysis.

[1682] Step 2:

[1683] The terminal converts the preprocessed video data received from the server into an input data format using a preprocessing algorithm. The input is the preprocessed video data, and the data format conversion is performed to make it compatible with the pedestrian detection algorithm. The converted data is then received.

[1684] Step 3:

[1685] The server inputs the converted video data into the AI ​​module to detect and analyze pedestrians. The converted video data is input, and the AI ​​module calculates the speed and location of pedestrians in real time. As a result, the location coordinates and movement speed data of each pedestrian are output.

[1686] Step 4:

[1687] The server analyzes the location and speed data obtained from the AI ​​module and determines whether each pedestrian is elderly or has difficulty walking. The input is location coordinates and movement speed data, and the output is the determination result of whether the pedestrian is elderly or has difficulty walking.

[1688] Step 5:

[1689] The server runs an emotion engine and analyzes the facial expressions and body movements of pedestrians from the received video data. The inputs are the judgment results obtained in the previous step and the video data, and the emotion engine identifies pedestrians who are feeling anxious or nervous. The analysis results are output as data on the pedestrian's emotional state.

[1690] Step 6:

[1691] The server operates the traffic light control module based on the analysis results of the AI ​​module and the recognition results of the emotion engine. The input is the judgment result and emotional state data of elderly people and people with walking difficulties, and the output is an instruction to extend the green light time. This instruction extends the green light time as necessary.

[1692] Step 7:

[1693] The terminal receives a control signal from the server and sends it to the traffic light. The input is the control signal from the server, and the output is an update of the traffic light setting and a new green light time is set.

[1694] Step 8:

[1695] The server generates voice guidance at appropriate times based on the pedestrian's location information and emotional state. The input is the pedestrian's location information and emotional state data, and the output is a voice guidance message. Specifically, the server generates a voice message such as "The green light will be extended by 10 seconds from here."

[1696] Step 9:

[1697] The device adjusts the lighting in the intersection to visually alert pedestrians. The input is instructions from the server, and the output is updated lighting settings. For nervous pedestrians, lighting effects are added to calm them down.

[1698] Step 10:

[1699] The server monitors pedestrians' movements and emotional states for abnormalities, detecting sudden stops, falls, and other anomalies. The input is real-time monitored pedestrian data, and if an anomaly is detected, a warning signal is generated. The output is an anomaly detection alert, which is sent to the warning means.

[1700] Step 11:

[1701] The terminal receives the generated warning signal and notifies vehicles and other pedestrians around the intersection. The input is the warning signal from the server, and the output is the turning on of warning lights in the intersection and the sound of a warning.

[1702] (Application example 2)

[1703] 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."

[1704] The problem that this invention aims to solve is to support elderly people and people with mobility difficulties to move safely and efficiently within a physical store, and to provide appropriate support based on their emotional state, such as anxiety or tension. Another objective is to ensure safety by detecting abnormal conditions and responding quickly. This aims to provide an environment where elderly people and people with mobility difficulties can enjoy shopping with peace of mind.

[1705] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1706] In this invention, the server includes sensor means for detecting the speed and position of pedestrians, artificial intelligence means for analyzing the detected speed and position data, control means for adjusting the green light time of traffic lights based on the analysis results, support means for providing audio or visual support to pedestrians based on the analysis results, emotion analysis means for analyzing facial expressions and body movements to recognize emotional states, support means for providing audio guidance to pedestrians to encourage stability based on their emotional states, and warning means for detecting abnormal conditions and issuing alerts to surrounding vehicles and pedestrians. This makes it possible to support the safe movement of pedestrians and provide appropriate navigation and support while reducing tension and anxiety.

[1707] "Sensor means" refers to a device for detecting the speed and position of a pedestrian.

[1708] "Artificial intelligence means" refers to techniques that utilize machine learning and algorithms to analyze detected speed and location data.

[1709] "Control means" refers to a device or system for adjusting the green light time of a traffic light based on the analysis results.

[1710] "Support means" refers to devices or technologies that provide audio or visual support to pedestrians based on the analysis results.

[1711] "Warning means" refers to devices and technologies that detect abnormal conditions and issue alerts to surrounding vehicles and pedestrians.

[1712] "Emotion analysis means" refers to devices or technologies that analyze facial expressions and body movements to recognize emotional states.

[1713] "Assistance tools" are devices and technologies that provide audio guidance to pedestrians to encourage stability based on their emotional state.

[1714] To realize this invention, the system operates as an application using smart glasses. The smart glasses use the following hardware and software to assist elderly people and people with mobility impairments to move safely and comfortably within a physical store.

[1715] Hardware

[1716] Smart glasses: Equipped with a camera, microphone, speaker, and GPS module.

[1717] Server: A high-performance computer for data processing and analysis.

[1718] In-store beacon: A device for obtaining accurate location information.

[1719] software

[1720] AI module: Machine learning algorithms for analyzing pedestrian speed and location data, using frameworks such as TensorFlow and PyTorch.

[1721] Emotion Engine: A program that analyzes facial expressions and body movements to recognize emotional states. It uses Emotion API and OpenCV.

[1722] Control module: This module adjusts the green light time and provides voice guidance. It uses Node.js and Python.

[1723] Alert system: A program for detecting abnormal conditions and generating alerts.

[1724] Processing flow

[1725] 1. Real-time image acquisition and preprocessing

[1726] A camera built into the smart glasses captures images of the inside of the store in real time.

[1727] The captured video is sent to a server where noise removal and frame rate correction are performed.

[1728] 2. Analysis of pedestrian speed and position

[1729] The server uses an AI module to detect pedestrians in the video data and calculate their location coordinates and speed.

[1730] Based on the analysis results, it is determined whether the pedestrian is elderly or has difficulty walking.

[1731] 3. Facial Expression and Body Movement Analysis

[1732] The server uses an emotion engine to analyze facial expressions and body movements to recognize emotional states.

[1733] Based on the recognized emotional state, the smart glasses provide audio guidance.

[1734] 4. Navigation aids and warning systems

[1735] Provide appropriate audio and visual navigation as a means of support.

[1736] If an abnormal condition is detected, the warning system will generate an alert and notify store staff.

[1737] Specific examples

[1738] Example 1

[1739] An elderly person wearing smart glasses visits a supermarket at 2 p.m.

[1740] The smart glasses receive the camera footage, which is then analyzed by the server using an AI module and emotion engine.

[1741] As a result of the analysis, elderly people are identified and appropriate route guidance is initiated.

[1742] Voice guidance such as "The cash register is 10 meters away" is provided through the smart glasses.

[1743] If it detects that the senior is feeling anxious, it will provide additional voice prompts to calm them down.

[1744] Example 2

[1745] At 5 p.m., an elderly person fell while walking inside the store.

[1746] When the smart glasses detect an abnormality, the server generates an alert and sends a notification to the store staff.

[1747] Furthermore, the emotion engine detects when the user is feeling fear due to falling, and appropriate measures are taken quickly.

[1748] Prompt Sentence Examples

[1749] "Develop an application for smart glasses that helps seniors navigate safely and stress-free within a store. The application should include the following features:

[1750] Images captured by the built-in camera are preprocessed in real time to detect the speed and location of pedestrians.

[1751] An artificial intelligence module is used to identify elderly people and those with walking difficulties.

[1752] The emotion engine analyzes facial expressions and body movements to recognize emotional states.

[1753] Providing navigation routes and audio and visual support.

[1754] When an abnormality is detected, a warning signal is generated and staff are notified.

[1755] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1756] Step 1:

[1757] The server receives real-time video footage from inside the store captured by the camera built into the smart glasses. The input is camera video data, and the output is pre-processed video data. Specifically, the server performs processing to remove noise from the video and correct the frame rate.

[1758] Step 2:

[1759] The server inputs the preprocessed video data into the AI ​​module. The input is noise-removed and frame-rate-corrected video data, and the output is the position coordinates and speed data of detected pedestrians. Specifically, the server detects pedestrians in the video and calculates the position and speed of each pedestrian.

[1760] Step 3:

[1761] The server identifies elderly people and people with walking difficulties based on the analysis results of the AI ​​module. The input is the position coordinates and speed data of pedestrians, and the output is identification information of elderly people and people with walking difficulties. Specifically, the server analyzes speed and posture to identify elderly people and people with walking difficulties.

[1762] Step 4:

[1763] The server uses emotion analysis means to analyze facial expressions and body movements. The input is video data of pedestrians, and the output is the identification result of their emotional state. Specifically, the server analyzes facial expressions and body movements to recognize the emotional state.

[1764] Step 5:

[1765] The server generates appropriate voice guidance for the pedestrian based on the emotional state. The inputs are the emotional state identification result and the pedestrian's location information, and the output is voice guidance data. Specifically, the server generates a voice message corresponding to the emotional state and sends it to the smart glasses.

[1766] Step 6:

[1767] The server detects abnormal conditions and activates the warning system. The inputs are the pedestrian's position coordinates and speed data, and the emotional state identification results, and the output is a warning signal. Specifically, the server detects abnormal conditions such as sudden stops, falls, extreme anxiety, or fear, and generates a warning signal to notify store staff.

[1768] 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.

[1769] 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.

[1770] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1771] 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.

[1772] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1773] 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.

[1774] 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).

[1775] 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.

[1776] 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."

[1777] 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.

[1778] 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).

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] The following is further disclosed regarding the above embodiment.

[1790] (Claim 1)

[1791] sensor means for detecting the speed and position of a pedestrian;

[1792] artificial intelligence means for analyzing the detected speed and position data;

[1793] a control means for adjusting the green light time of the traffic light based on the analysis result;

[1794] a support means for providing audio or visual support to pedestrians based on the analysis results;

[1795] The system includes a warning means for detecting abnormal conditions and alerting surrounding vehicles and pedestrians.

[1796] (Claim 2)

[1797] 10. The system of claim 1, wherein the abnormal condition is detected as a sudden stop or a fall of a pedestrian.

[1798] (Claim 3)

[1799] 10. The system of claim 1, further comprising artificial intelligence means for analyzing the speed and posture of a pedestrian to determine whether the pedestrian is elderly or has walking difficulties.

[1800] "Example 1"

[1801] (Claim 1)

[1802] a sensor means for acquiring images of pedestrians in real time;

[1803] processing means for pre-processing the collected images to detect velocity and position;

[1804] an artificial intelligence means for detecting pedestrians based on the pre-processed video data and analyzing their positions and speeds;

[1805] A determination means for determining whether the person is elderly or has difficulty walking and for calculating the required walking time;

[1806] a control means for extending the green light time of a traffic light based on the calculated walking time;

[1807] support means for providing audio guidance and visual support;

[1808] monitoring means for detecting abnormal pedestrian behavior and generating a warning signal;

[1809] The system includes a notification means for notifying the generated warning signal.

[1810] (Claim 2)

[1811] 10. The system of claim 1, wherein the system provides an alert in response to a sudden stop or fall of a pedestrian.

[1812] (Claim 3)

[1813] 10. The system of claim 1, further comprising artificial intelligence means for analyzing walking speed and posture to determine whether the person is elderly or has difficulty walking.

[1814] "Application Example 1"

[1815] (Claim 1)

[1816] sensor means for detecting the speed and position of a pedestrian;

[1817] artificial intelligence means for analyzing the detected speed and position data;

[1818] a control means for adjusting the green light time of the traffic light based on the analysis result;

[1819] a support means for providing audio or visual support to pedestrians based on the analysis results;

[1820] warning means for detecting abnormal conditions and alerting surrounding vehicles and pedestrians;

[1821] A means for acquiring vehicle camera images in real time and detecting pedestrians using an AI module;

[1822] A means for identifying elderly people or people with walking disabilities in an automated driving system and adjusting the speed of the vehicle;

[1823] audio output means for providing an audio alert to a pedestrian;

[1824] A system including:

[1825] (Claim 2)

[1826] 10. The system of claim 1, wherein the abnormal condition is detected as a sudden stop or a fall of a pedestrian.

[1827] (Claim 3)

[1828] 10. The system of claim 1, further comprising artificial intelligence means for analyzing the speed and posture of a pedestrian to determine whether the pedestrian is elderly or has walking difficulties.

[1829] "Example 2: Combining Emotion Engines"

[1830] (Claim 1)

[1831] sensor means for detecting the speed and position of a pedestrian;

[1832] means for pre-processing the detected video data;

[1833] artificial intelligence means for analyzing the pre-processed video data;

[1834] A means for determining whether a pedestrian is elderly or has difficulty walking based on the analyzed data;

[1835] means including an emotion engine for analyzing facial expressions and body movements to recognize an emotional state;

[1836] a control means for adjusting the green light time of a traffic light based on the analysis result and the emotion data;

[1837] a support means for providing audio or visual support to pedestrians based on the analysis results and emotion data;

[1838] The system includes a warning means for monitoring pedestrians' movements and emotional states for abnormalities and issuing a warning if an abnormality is detected.

[1839] (Claim 2)

[1840] 10. The system of claim 1, wherein the abnormal condition is detected as a sudden stop or a fall of a pedestrian.

[1841] (Claim 3)

[1842] 10. The system of claim 1, further comprising artificial intelligence means for analyzing the speed and posture of a pedestrian to determine whether the pedestrian is elderly or has walking difficulties.

[1843] "Application example 2 when combining emotion engines"

[1844] (Claim 1)

[1845] sensor means for detecting the speed and position of a pedestrian;

[1846] artificial intelligence means for analyzing the detected speed and position data;

[1847] a control means for adjusting the green light time of the traffic light based on the analysis result;

[1848] a support means for providing audio or visual support to pedestrians based on the analysis results;

[1849] warning means for detecting abnormal conditions and alerting surrounding vehicles and pedestrians;

[1850] emotion analysis means for analyzing facial expressions and body movements to recognize emotional states;

[1851] A system including an assistance means for providing audio guidance to pedestrians to encourage stability based on their emotional state.

[1852] (Claim 2)

[1853] 10. The system of claim 1, wherein the abnormal condition is detected as a sudden stop or a fall of a pedestrian.

[1854] (Claim 3)

[1855] 10. The system of claim 1, further comprising artificial intelligence means for analyzing the speed and posture of a pedestrian to determine whether the pedestrian is elderly or has walking difficulties. [Explanation of symbols]

[1856] 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. sensor means for detecting the speed and position of a pedestrian; artificial intelligence means for analyzing the detected speed and position data; a control means for adjusting the green light time of the traffic light based on the analysis result; a support means for providing audio or visual support to pedestrians based on the analysis results; The system includes a warning means for detecting abnormal conditions and alerting surrounding vehicles and pedestrians.

2. 2. The system of claim 1, wherein the abnormal condition is detected as a sudden stop or a fall of a pedestrian.

3. 2. The system of claim 1, further comprising artificial intelligence means for analyzing the speed and posture of a pedestrian to determine whether the pedestrian is elderly or has walking difficulties.

Images