system

Abstract

We provide the system. [Solution] A means of capturing an object using a camera as an image acquisition means and calculating the distance to that object, A means for determining the risk of collision based on calculated distance and movement information, and for generating a warning according to the situation, A means for saving video information before and after a specific event occurs, and transmitting that information to an external recording medium as needed, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] As the use of electric kick scooters becomes increasingly popular, it is necessary to reduce the risk of accidents and collisions. Also, in the event of an accident, the problem is that there is insufficient data as evidence. There is a need for a technology that can safely and efficiently solve the above problems.

Means for Solving the Problems

[0005] This invention provides a means for capturing an object using a camera as an image acquisition means and calculating the distance to that object. Furthermore, it has means for determining the risk of collision based on the calculated distance and motion information and generating a warning according to the situation. In particular, when a specific event occurs, the system provides means for saving video information before and after the event and transmitting it to an external recording medium as needed. This system makes it possible to prevent accidents by detecting the risk of collision in advance and issuing appropriate warnings. Furthermore, in the event of an accident, the record is reliably saved, enabling smooth post-accident response.

[0006] The "image acquisition method" is a function that uses a camera fixed to the electric kick scooter to capture images of the surroundings in real time.

[0007] "Object acquisition" refers to the act of identifying and determining the location of surrounding vehicles, pedestrians, obstacles, etc., from camera footage.

[0008] "Methods for calculating distance" refers to the process of quantifying the physical distance to an identified object based on video data acquired from a camera.

[0009] "A means of assessing risk and generating warnings according to the situation" refers to a process that evaluates the possibility of collision based on calculated distance and movement information, and then alerts the user to the danger with sound or vibration according to the result.

[0010] "Saving video information before and after an event occurs" means recording a series of video data on a recording medium, focusing on the moment a specific dangerous event or collision occurs, and the events before and after that point.

[0011] "Means of transmitting to an external storage medium" refers to a function that uploads saved video data to the cloud or another storage device, making it accessible when needed in the future. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

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

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

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system designed to enhance the safety of electric scooters, aiming to detect and prevent accident risks using a smartphone. The system functions by attaching a terminal consisting of a smartphone and its built-in camera to the electric scooter and monitoring the surrounding environment.

[0034] The device captures video in real time via its camera and uses object detection technology to identify vehicles, pedestrians, and other objects. For each identified object, the device calculates the distance and assesses the potential collision risk. The distance calculation is based on the acquired image data, specifically using depth estimation technology to quantify the distance to each object.

[0035] Furthermore, the device analyzes this distance information to estimate the object's approach speed. Combining the speed and distance data, it calculates the time until contact and determines the risk based on pre-set criteria. If a collision is deemed highly likely, it warns the user through voice alerts and vibrations. This warning allows the user to understand the situation in real time and take appropriate evasive action.

[0036] Furthermore, the device has a function to record video when specific events occur, depending on the situation. This means that video information before and after an accident is automatically saved and can be referenced later. The saved video data can also be transmitted to external storage media such as the cloud, and serves as evidence for use in insurance claims and legal proceedings after an accident.

[0037] As a concrete example, consider a scenario where a user is crossing a park on an electric scooter and spots a pedestrian ahead. The device recognizes the pedestrian using its camera and measures the distance as 15 meters. It then analyzes the subsequent frames to estimate the pedestrian's approach speed at 3 meters per second and calculates the time until collision as 5 seconds. If the device determines the risk is high based on safety standards, it immediately issues a warning and provides an alert to allow for appropriate action. This entire sequence of data is recorded and, if necessary, uploaded to the cloud later for use as evidence.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The device uses a camera fixed to the smartphone to acquire real-time video of the surroundings. The video data is captured as a series of image frames.

[0041] Step 2:

[0042] The device performs pre-processing on the captured image frames, adjusting brightness and contrast. This improves the video quality and makes it suitable for analysis.

[0043] Step 3:

[0044] For frames that have been preprocessed, the terminal performs AI-based object detection. Vehicles, pedestrians, obstacles, etc., are identified, and the location information of each object is obtained.

[0045] Step 4:

[0046] The device uses depth estimation technology to calculate the distance to identified objects. Distance data from the camera position to each object is output.

[0047] Step 5:

[0048] Based on distance data, the device analyzes changes in position between consecutive frames and estimates the approaching or moving-away velocity of an object.

[0049] Step 6:

[0050] Based on the distance and speed data obtained, the device assesses the risk of collision. It predicts the likelihood of a collision according to the established safety standards.

[0051] Step 7:

[0052] If a collision is detected as possible, the device will issue an alert via voice and vibration to immediately warn the user.

[0053] Step 8:

[0054] When a high risk is detected under specific conditions, the device records and saves video footage before and after the incident. This video data will be referenced later if necessary for review.

[0055] Step 9:

[0056] If recorded data is needed, the device sends it to an external storage medium such as cloud storage. This process ensures that the video is properly stored as evidence.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In recent years, small electric vehicles have become popular as a means of personal transportation, but this has also led to an increase in the risk of accidents. In particular, real-time environmental awareness and appropriate countermeasures are required to prevent collisions with surrounding objects. The objective of this invention is to effectively recognize the surrounding environment for a moving vehicle and warn the user of potential dangers early. Furthermore, it aims to record the circumstances before and after an accident as needed, enabling appropriate processing.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for detecting an object using an imaging device as an observation means and calculating the distance to the object; means for evaluating the risk of contact based on the calculated distance and speed information and generating a notification according to the conditions; and means for recording visual information before and after a specific situation occurs and transmitting that information to an external storage device as necessary. This enables accurate understanding of the surrounding environment of a moving vehicle and provides quick and effective warnings of potential dangers. It also allows for detailed recording of the circumstances at the time of an accident, which can be used for subsequent analysis and processing.

[0062] "Observation means" refers to a device or group of devices used to capture the surrounding situation, and primarily involves acquiring image information of the environment using imaging devices.

[0063] An "imaging device" is a device that converts light into electrical signals to generate images, and includes devices such as cameras and sensors.

[0064] "Target" refers to elements that require attention along a travel path, such as objects or people detected by observation methods.

[0065] "Means of calculating distance" refers to the techniques and algorithms used to measure the physical distance to an observed object.

[0066] "Distance information" refers to numerical data that indicates the physical distance to the calculated target.

[0067] "Speed ​​information" refers to data that indicates the speed at which an object moves over time.

[0068] "Means for assessing the risk of contact" refers to a process or technology for determining the likelihood of a collision based on distance and speed information.

[0069] A "means of generating notifications" refers to a system that provides warnings and information to users according to the assessed risk.

[0070] "Means for recording visual information" refers to technologies and systems for saving images acquired from an imaging device under specific circumstances.

[0071] "External storage devices" refer to equipment including cloud services and physical media for the stable storage of recorded information.

[0072] This invention is an information processing system for enhancing safety, which monitors the surrounding environment using a terminal attached to a means of transport. The following hardware and software are used to implement the invention.

[0073] The terminal is a portable information terminal equipped with an imaging device, which uses a high-sensitivity camera. Furthermore, this terminal uses software libraries such as TENSORFLOW® and OpenCV for image processing to identify objects in real time. It also uses a depth estimation algorithm to calculate the distance to the identified object.

[0074] As part of this system, the terminal collects distance and speed information and assesses the risk of collision. Based on the assessment, the server generates audio and vibration warnings to notify the user. If recording and saving visual information is necessary, the terminal automatically starts recording and sends the video data to an external storage device. This data can then serve as evidence that can be used later for accident analysis or legal proceedings.

[0075] As a concrete example, when a user crosses a park, the device identifies a pedestrian ahead. It calculates the distance to be 15 meters and estimates the speed to be 3 meters per second, calculating the time until collision to be 5 seconds. If it determines that there is a danger, the device immediately issues a warning to the user. This entire sequence of events is recorded and sent to the cloud later if necessary.

[0076] Examples of prompts to input into a generative AI model:

[0077] "I am designing a real-time hazard detection system to be installed on my electric mobility device. This system will use an imaging device to detect objects, calculate distance and speed, and issue a collision warning if necessary. Please propose an efficient notification method."

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The terminal first captures images of the environment in real time using an imaging device. The input data consists of a series of image frames acquired from the camera. This video data is then supplied directly to the next object detection step. Specifically, the terminal takes multiple shots per second to capture the dynamic environment.

[0081] Step 2:

[0082] The device analyzes the captured video data using an object detection algorithm. The input is the image frame obtained in step 1, and the output is the identification result of objects present in the screen. This identification is performed using libraries such as TensorFlow and OpenCV. Specifically, the device applies a deep learning model to each frame to identify vehicles and pedestrians.

[0083] Step 3:

[0084] The terminal calculates the distance to each object based on the object detection results. The input here is the object identification result, and the output is data including the distance for each object. Depth estimation techniques are used for distance calculation, applying stereo vision and monocular depth estimation. Specifically, the terminal calculates the distance using triangulation or other methods based on the location information of the identified objects.

[0085] Step 4:

[0086] The terminal estimates the movement speed based on the sequential position information of the object. The input is the object's distance data and position frame obtained in step 3, and the output is the estimated speed for each object. Specifically, the terminal calculates the change in position between frames and uses the change over time to determine the speed.

[0087] Step 5:

[0088] The terminal evaluates the risk of contact based on the distance and speed information obtained. The input information is the distance and speed data obtained in steps 3 and 4, and the output is the risk level evaluation result. Specifically, the terminal compares the data with pre-set safety standards to determine whether the risk is high or low.

[0089] Step 6:

[0090] The device will alert the user if it determines that the risk is high. The input will be the evaluation results from step 5, and the output will be an audio alert or vibration warning. Specifically, the device will call an API within the program to immediately draw the user's attention.

[0091] Step 7:

[0092] The terminal records video captured under specific conditions and saves it as needed. The input is video data obtained from the imaging device, and the output is the recorded video file. Specifically, the terminal saves video before and after an event is triggered to a dedicated folder and prepares it for uploading to an external storage device.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Autonomous vehicles are required to accurately recognize surrounding objects and prevent collision risks. However, current technology makes it difficult to accurately grasp distance and movement in real time and issue warnings quickly. Therefore, providing effective means to improve the safety of autonomous vehicles is a challenge.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for capturing an object and calculating the spatial distance to the object using image acquisition means mounted on a storage medium as an execution device; means for evaluating the possibility of collision based on the calculated distance and motion information and generating a warning according to the situation; means for saving visual information before and after a specific situation occurs and transmitting that information to an external recording medium as necessary; and means for transmitting audible and vibratory warnings to a presentation device. This enables autonomous vehicles to accurately judge their surroundings, proactively detect potential collision risks, and improve safety.

[0098] A "storage medium as an execution device" is hardware used to store data and execute software as needed.

[0099] "Image acquisition means" refers to a process or device for acquiring visual information using a camera or sensor.

[0100] "Means for calculating spatial distance" refers to techniques that quantify the distance to a recognized object based on acquired visual information.

[0101] "Assessing the likelihood of a collision" is the process of analyzing potential hazards from recognized objects and surrounding conditions, and making decisions to prevent accidents.

[0102] A "means for generating warnings" is a mechanism that issues signals or messages to alert the user or system based on evaluation results.

[0103] "Saving visual information" refers to the operation of recording video or image data at a specific moment when a particular event or situation occurs.

[0104] "Means of transmitting to an external recording medium" refers to a mechanism for transferring stored data to other storage devices or cloud services via the internet or other means.

[0105] "Means for transmitting warnings to a display device using sound and vibration" refers to methods of attracting the user's attention using sound and vibration.

[0106] To implement this invention, it is first necessary to develop a program to be mounted on a storage medium that serves as an execution device. This program runs on a mobile device such as a smartphone and acquires surrounding visual information in real time through a camera.

[0107] The server uses a smartphone camera as an image acquisition method and utilizes image processing libraries such as OpenCV to capture objects. At this time, it performs object recognition from the acquired images using machine learning models such as TensorFlow, and calculates the spatial distance based on the results using depth estimation technology.

[0108] By combining the calculated distance with motion information obtained from consecutive frames, the server assesses the likelihood of a collision. To assist the user in avoiding danger, warnings based on the risk predicted by the generative AI model are transmitted to the display device via voice and vibration. Furthermore, visual information in specific situations is transmitted via the network to an external storage medium such as the cloud, which can be referenced as evidence in the event of an accident.

[0109] A concrete example would be a self-driving vehicle in an urban area that detects a bicycle suddenly appearing in front of it. In this case, the server would immediately calculate the distance, evaluate the time until contact, and send a warning to the vehicle system. Another example of a prompt in a generative AI model would be "detect a specific object from the video, estimate its distance, and perform a real-time risk assessment."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The device uses its built-in camera to acquire video in real time.

[0113] The input is a video stream from the camera sensor, and the output is a sequence of image data. At this stage, the terminal uses the OpenCV library to divide the video into frames and convert them into a format that can be processed in real time.

[0114] Step 2:

[0115] The server receives image data sent from the terminal and performs object detection.

[0116] The input is the image data obtained in Step 1, and the output is the position information of objects within each frame. The server uses TensorFlow and a pre-trained generative AI model to identify objects within the frame and obtain their coordinates. This process reveals the type of object and its location.

[0117] Step 3:

[0118] The server uses depth estimation technology to calculate the distance to an object based on the object detection results.

[0119] The input is the location data from step 2, and the output is the distance to the object quantified. The server uses a depth estimation algorithm to calculate the exact distance by matching known physical data with image parameters.

[0120] Step 4:

[0121] The server analyzes positional information obtained from consecutive frames to calculate the object's movement speed.

[0122] The input consists of position and time data calculated from previous frames, and the output is the object's velocity. The server divides the distance traveled by the time to determine the velocity. This information is used to predict the time until contact.

[0123] Step 5:

[0124] The server compares the predicted contact time with safety standards to assess the risk of collision.

[0125] The input is the speed and distance information from step 4, and the output is a risk assessment. The server compares this to the set criteria and immediately generates a warning signal if it determines that the risk is high.

[0126] Step 6:

[0127] The device communicates warnings to the user through voice and vibration.

[0128] The input is the warning signal generated in step 5, and the output is an alert for the user. The device plays a voice message or activates vibration to notify the user of the imminent danger.

[0129] Step 7:

[0130] The server sends video data before and after a specific event to the cloud.

[0131] The input is the video data acquired in Step 1, and the output is the recorded video saved to an external storage medium via the network. The server uses a storage service such as AWS® S3 to back up this data so that it can be used for later analysis or as evidence.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention aims to improve the safety of electric scooters by providing a new system that takes into account the user's emotional state. The system integrates a smartphone mounted on the electric scooter, a camera for monitoring the surrounding environment, and an emotion engine for recognizing the user's emotions.

[0134] The device first uses the smartphone's camera to acquire real-time images of the surroundings. This allows it to detect objects such as vehicles, people, and obstacles on the road and calculate the distance to them. Based on this information, the device assesses the potential risk of collision and issues alerts via voice or vibration as needed.

[0135] Furthermore, the device is equipped with an emotion engine that determines the user's emotional state in real time based on facial and voice characteristics. Based on this emotional state, the content and frequency of risk warnings are adjusted. For example, if the system detects that the user is stressed, it can increase the frequency of warnings or adjust the intensity of alerts.

[0136] Furthermore, this system has a function to record the user's stress level and emotional changes, and to generate a long-term safety profile. This profile can be used to optimize safety settings for each individual user.

[0137] As a concrete example, consider a scenario where a user is operating an electric scooter, and the camera detects a car ahead, calculating the distance to be 20 meters. The emotion engine analyzes the user's face and, if it determines that their concentration is waning, adjusts the device to issue a warning earlier than usual. As a result, the user can react to the situation more quickly, which is expected to reduce the risk of an accident. The recorded data is saved to the cloud as needed and used for post-incident review and analysis.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The device activates the smartphone's camera and acquires real-time video of the surroundings. The video is processed as a series of image frames.

[0141] Step 2:

[0142] The device applies an object detection algorithm to the acquired image frames to identify objects such as vehicles and pedestrians. The position and size of each object are identified.

[0143] Step 3:

[0144] The device calculates the distance based on the location information of the identified object. It uses depth estimation technology to measure the distance from the camera to the object and outputs it as numerical data.

[0145] Step 4:

[0146] The device analyzes the change in the object's position between consecutive frames and estimates its velocity. Based on this velocity information, it evaluates whether the object is approaching.

[0147] Step 5:

[0148] Based on the calculated distance and speed, the device assesses the risk of contact and determines the risk level based on pre-set safety standards.

[0149] Step 6:

[0150] Simultaneously, the device activates an emotion engine, analyzing the user's emotional state from data collected by the camera and microphone. Emotions are determined from factors such as facial expressions and tone of voice.

[0151] Step 7:

[0152] The device adjusts the intensity and frequency of alerts based on the user's emotional state. For example, if it determines that the user is stressed, it will issue warnings more frequently or with greater emphasis than usual.

[0153] Step 8:

[0154] When a warning is issued, the device automatically records and saves video footage of the dangerous area. If necessary, this data is uploaded to the cloud.

[0155] Step 9:

[0156] Subsequently, the device updates the user's individual safety profile based on the collected emotional data. This improves the accuracy of subsequent risk assessments.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] In modern personal transportation, there is a challenge in that the impact of users' emotions and mental states on safety is not adequately considered. In particular, impaired judgment due to emotional states increases the risk of collisions and accidents, so a system that monitors and adjusts this in real time is needed. Furthermore, providing warnings appropriate to the surrounding environment is also essential for improving safety.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes means for capturing an object using a video device as an image acquisition means and calculating the distance to the object; means for determining the risk of collision based on the calculated distance and motion information and generating a warning according to the situation; means for emotion recognition that analyzes the user's emotional state; means for adjusting the content and frequency of the warning based on that emotional state; and means for saving video information before and after a specific event occurs and transmitting that information to an external recording medium as necessary. This makes it possible to provide highly accurate risk assessment and customized warnings based on the user's emotional state and surrounding environmental information.

[0162] An "image acquisition means" is a device for collecting visual information of the environment in real time, and is a device that enables the detection of objects and the calculation of their distances.

[0163] "Means for calculating distance" refers to a function that mathematically measures the distance to an object based on acquired visual information, and is a process for providing accurate positional information.

[0164] "Means for determining the risk of collision" refers to a method of evaluating the likelihood of a physical collision occurring based on distance information and motion data, and establishing criteria for issuing warnings.

[0165] "Means of generating warnings" refers to systems or processes that provide users with visual or auditory alerts based on risk assessments.

[0166] "Emotion recognition means" refers to technology that analyzes the characteristics of a user's face and voice to determine their emotional state in real time, and is a method for evaluating the user's mental state.

[0167] "Means for adjusting warning content and frequency" refers to a process for improving security by optimizing the content and frequency of warning messages, taking into account the user's emotional information.

[0168] "Means of transmitting to an external recording medium" refers to the function of transferring data to the cloud or other storage systems in order to save the collected data and analysis results outside the device.

[0169] This invention is a system for improving the safety of electric mobility devices, which analyzes the user's emotional state and the surrounding environment in real time. The system is integrated into a terminal used by the user and includes several key components.

[0170] The device first uses a camera as an image device to collect visual information from its surroundings. During this process, it uses libraries such as OpenCV and TensorFlow to perform image processing, enabling real-time object detection and distance measurement. The distance data serves as fundamental information for evaluating the likelihood of collisions.

[0171] Next, the device uses emotion recognition software to analyze the user's face and voice to determine their emotional state. By applying the Emotion API or similar emotion classification models, it can assess stress levels and attention levels, and dynamically adjust the frequency and content of warnings.

[0172] Furthermore, the system records user behavior data and saves video information in response to specific events. This enables post-event analysis and user profile generation, leading to long-term security optimization. The recorded data is securely transmitted to external storage media using cloud storage.

[0173] As a concrete example, consider a scenario where a user is using an electric mobility device while properly operating a terminal, and the system detects a vehicle ahead and calculates its distance. If the emotional engine detects a decrease in the user's concentration, the terminal will intensify its warnings and prompt the user to react quickly. This is expected to reduce the risk of collisions and prevent accidents.

[0174] An example of a prompt for a generated AI model is: "Describe the details of a safety system that takes into account the user's emotional state in electric mobility devices. Specifically describe the roles of hardware and software, and clearly explain how they provide benefits to the user."

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The device activates the camera built into the smartphone and captures the surrounding image in real time. The input is visual information from the camera, and the output is video data. This video data is processed using OpenCV and TensorFlow to detect objects and calculate distances. Specifically, the system identifies vehicles and obstacles from the video data and performs analysis to calculate their positions and velocities.

[0178] Step 2:

[0179] Based on the location information of the detected object, the terminal calculates the distance. The input is the object detection result from step 1, and the output is the distance information to the object. Stereo vision and image parsing techniques are used to calculate the accurate distance and provide foundational data for evaluating the likelihood of a collision. Specifically, the distance is measured by triangulation using parallax.

[0180] Step 3:

[0181] The device combines distance and motion data to assess collision risk. Inputs are distance information to an object and its speed, while output is the risk assessment result. Based on this risk, the need for a warning is determined, and a warning is generated if necessary. Specifically, future movements are predicted using a statistical model based on accumulated data.

[0182] Step 4:

[0183] Next, the device activates its emotion engine and recognizes the user's emotional state from their face and voice. The input is the user's video and audio data, and the output is the evaluation result of their emotional state. Using the Emotion API and other tools, real-time emotion recognition is performed to understand the user's stress level and concentration level. This allows the system's operation to be adjusted according to the user's psychological state.

[0184] Step 5:

[0185] The device combines the risk assessment from Step 3 and the emotional state from Step 4 to optimize the content and frequency of warnings. The input is the risk assessment result and the emotional state assessment result, and the output is the adjusted warning. Specifically, if the user is experiencing stress, the system adjusts to issue more frequent warnings or stronger vibration warnings.

[0186] Step 6:

[0187] The server records all session data and stores the information necessary for analysis in the cloud. Inputs include all past operation logs and sensor data, while outputs are long-term user profiles. The stored data is used for later review and statistical analysis, and is utilized to improve security tailored to each user.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0190] In electric scooters and other personal mobility devices, risks threatening user safety involve not only the detection of hazardous objects in the surroundings and proper risk assessment, but also significant factors such as changes in the user's emotional state and concentration level. Conventional systems were unable to simultaneously consider these factors and perform risk assessments, resulting in insufficient safety.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0192] In this invention, the server includes means for capturing the surrounding environment using a visual device as an image acquisition means and calculating the distance to an object; means for evaluating the risk of collision based on the calculated distance and movement information and generating a warning according to the situation; and means for analyzing the user's emotional state using emotion analysis means and adjusting the risk assessment and warning content. This enables more appropriate and timely safety measures by simultaneously considering the user's surrounding environment and emotional state.

[0193] An "image acquisition means" is a device that uses a visual device to capture visual information of the surrounding environment and collect necessary data.

[0194] A "visual device" is a device, including cameras and sensors, that is used to visually perceive surrounding objects and the environment.

[0195] "Means for calculating distance" refers to a method of calculating the physical distance to an object based on visual information obtained from image acquisition means.

[0196] "Movement information" refers to data related to the motion of an object, such as its position, velocity, and direction.

[0197] A "means for assessing collision risk" refers to a method of determining the likelihood of a collision between an object and a user based on acquired distance and movement information.

[0198] "Means of generating warnings" refers to methods of creating visual or audible alerts to draw the user's attention.

[0199] "Emotional analysis methods" are techniques for determining a user's emotional state by analyzing their facial expressions and vocal characteristics.

[0200] An "external data storage device" is a data storage medium used to save visual information related to specific events as needed, so that it can be accessed later.

[0201] A system implementing this invention consists of a terminal equipped with a visual device and an emotion analysis device, and a server for integrating and processing the data from these devices.

[0202] The device uses a camera as its visual device to capture its surroundings and process the visual data in real time. This camera uses image analysis software such as OpenCV or TensorFlow to detect objects from the visual data and calculate the distance to those objects. This information is transmitted to the device, and the risk of collision is assessed.

[0203] Furthermore, the device includes a function to analyze facial expressions and voice characteristics as a means of sentiment analysis. Here, it utilizes Google Cloud's Sentiment Analysis API and other tools to determine the user's emotional state in real time. This sentiment information is used for risk assessment and adjustment of warning content, and if the risk is determined to be high, a visual or audible alert is generated.

[0204] The server receives this data and, when a specific event occurs, saves the visual information before and after the event to an external data storage device. This makes it possible to review the situation later and perform detailed analysis.

[0205] As a concrete example, consider a scenario where a user is wearing smart glasses while outdoors. If a moving car is detected ahead and the distance is deemed dangerous, the system checks the user's facial expression, and if the emotion engine determines that the user is stressed, it provides an enhanced alert. This allows the user to quickly perceive danger and take appropriate action.

[0206] An example of a prompt message would be, "Please tell me when to issue a warning alert if the user is in a stressful state."

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The device uses visual devices to capture its surroundings in real time. The camera acquires visual information as image data, and image recognition software (such as OpenCV or TensorFlow) identifies objects. The input is real-time video data, and the output is the type of object and its location.

[0210] Step 2:

[0211] The device calculates distance from the object's location information. Using the object's location extracted from image data, it calculates the distance to the object using triangulation and other calculation methods. The input is the object's location information, and the output is the distance to the object.

[0212] Step 3:

[0213] The terminal assesses the risk of collision based on distance and movement information. This involves a step-by-step risk assessment using information such as speed and the direction of movement of the object. The input is the calculated distance and movement information, and the output is the result of the risk assessment.

[0214] Step 4:

[0215] The device analyzes the user's emotional state using an emotion analysis device. It sends facial expressions captured by the camera and voice collected by the microphone to Google Cloud's emotion analysis API to obtain the user's emotional state in real time. The input is data on facial expressions and voice, and the output is the evaluation result of the emotional state.

[0216] Step 5:

[0217] The server generates alerts based on risk assessment and emotional state. The type and intensity of the alerts are customized according to the level of risk and the user's emotional state. The inputs are the risk assessment results and emotional state assessment, and the output is the generated warning alert.

[0218] Step 6:

[0219] When a specific event occurs, the server saves the visual information before and after the event to an external data storage device. This ensures that the data necessary for later analysis and verification is stored. The input is the trigger for the specific event, and the output is the saved visual information.

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention is a system designed to enhance the safety of electric scooters, aiming to detect and prevent accident risks using a smartphone. The system functions by attaching a terminal consisting of a smartphone and its built-in camera to the electric scooter and monitoring the surrounding environment.

[0237] The device captures video in real time via its camera and uses object detection technology to identify vehicles, pedestrians, and other objects. For each identified object, the device calculates the distance and assesses the potential collision risk. The distance calculation is based on the acquired image data, specifically using depth estimation technology to quantify the distance to each object.

[0238] Furthermore, the device analyzes this distance information to estimate the object's approach speed. Combining the speed and distance data, it calculates the time until contact and determines the risk based on pre-set criteria. If a collision is deemed highly likely, it warns the user through voice alerts and vibrations. This warning allows the user to understand the situation in real time and take appropriate evasive action.

[0239] Furthermore, the device has a function to record video when specific events occur, depending on the situation. This means that video information before and after an accident is automatically saved and can be referenced later. The saved video data can also be transmitted to external storage media such as the cloud, and serves as evidence for use in insurance claims and legal proceedings after an accident.

[0240] As a concrete example, consider a scenario where a user is crossing a park on an electric scooter and spots a pedestrian ahead. The device recognizes the pedestrian using its camera and measures the distance as 15 meters. It then analyzes the subsequent frames to estimate the pedestrian's approach speed at 3 meters per second and calculates the time until collision as 5 seconds. If the device determines the risk is high based on safety standards, it immediately issues a warning and provides an alert to allow for appropriate action. This entire sequence of data is recorded and, if necessary, uploaded to the cloud later for use as evidence.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The device uses a camera fixed to the smartphone to acquire real-time video of the surroundings. The video data is captured as a series of image frames.

[0244] Step 2:

[0245] The device performs pre-processing on the captured image frames, adjusting brightness and contrast. This improves the video quality and makes it suitable for analysis.

[0246] Step 3:

[0247] For frames that have been preprocessed, the terminal performs AI-based object detection. Vehicles, pedestrians, obstacles, etc., are identified, and the location information of each object is obtained.

[0248] Step 4:

[0249] The device uses depth estimation technology to calculate the distance to identified objects. Distance data from the camera position to each object is output.

[0250] Step 5:

[0251] Based on distance data, the device analyzes changes in position between consecutive frames and estimates the approaching or moving-away velocity of an object.

[0252] Step 6:

[0253] Based on the distance and speed data obtained, the device assesses the risk of collision. It predicts the likelihood of a collision according to the established safety standards.

[0254] Step 7:

[0255] If a collision is detected as possible, the device will issue an alert via voice and vibration to immediately warn the user.

[0256] Step 8:

[0257] When a high risk is detected under specific conditions, the device records and saves video footage before and after the incident. This video data will be referenced later if necessary for review.

[0258] Step 9:

[0259] If recorded data is needed, the device sends it to an external storage medium such as cloud storage. This process ensures that the video is properly stored as evidence.

[0260] (Example 1)

[0261] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0262] In recent years, small electric vehicles have become popular as a means of personal transportation, but this has also led to an increase in the risk of accidents. In particular, real-time environmental awareness and appropriate countermeasures are required to prevent collisions with surrounding objects. The objective of this invention is to effectively recognize the surrounding environment for a moving vehicle and warn the user of potential dangers early. Furthermore, it aims to record the circumstances before and after an accident as needed, enabling appropriate processing.

[0263] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0264] In this invention, the server includes means for detecting an object using an imaging device as an observation means and calculating the distance to the object; means for evaluating the risk of contact based on the calculated distance and speed information and generating a notification according to the conditions; and means for recording visual information before and after a specific situation occurs and transmitting that information to an external storage device as necessary. This enables accurate understanding of the surrounding environment of a moving vehicle and provides quick and effective warnings of potential dangers. It also allows for detailed recording of the circumstances at the time of an accident, which can be used for subsequent analysis and processing.

[0265] "Observation means" refers to a device or group of devices used to capture the surrounding situation, and primarily involves acquiring image information of the environment using imaging devices.

[0266] An "imaging device" is a device that converts light into electrical signals to generate images, and includes devices such as cameras and sensors.

[0267] "Target" refers to elements that require attention along a travel path, such as objects or people detected by observation methods.

[0268] "Means of calculating distance" refers to the techniques and algorithms used to measure the physical distance to an observed object.

[0269] "Distance information" refers to numerical data that indicates the physical distance to the calculated target.

[0270] "Speed ​​information" refers to data that indicates the speed at which an object moves over time.

[0271] "Means for assessing the risk of contact" refers to a process or technology for determining the likelihood of a collision based on distance and speed information.

[0272] A "means of generating notifications" refers to a system that provides warnings and information to users according to the assessed risk.

[0273] "Means for recording visual information" refers to technologies and systems for saving images acquired from an imaging device under specific circumstances.

[0274] "External storage devices" refer to equipment including cloud services and physical media for the stable storage of recorded information.

[0275] This invention is an information processing system for enhancing safety, which monitors the surrounding environment using a terminal attached to a means of transport. The following hardware and software are used to implement the invention.

[0276] The device is a portable information terminal equipped with an imaging device, which uses a high-sensitivity camera. Furthermore, this device uses software libraries such as TensorFlow and OpenCV for image processing to identify objects in real time. It also uses a depth estimation algorithm to calculate the distance to the identified object.

[0277] As part of this system, the terminal collects distance and speed information and assesses the risk of collision. Based on the assessment, the server generates audio and vibration warnings to notify the user. If recording and saving visual information is necessary, the terminal automatically starts recording and sends the video data to an external storage device. This data can then serve as evidence that can be used later for accident analysis or legal proceedings.

[0278] As a concrete example, when a user crosses a park, the device identifies a pedestrian ahead. It calculates the distance to be 15 meters and estimates the speed to be 3 meters per second, calculating the time until collision to be 5 seconds. If it determines that there is a danger, the device immediately issues a warning to the user. This entire sequence of events is recorded and sent to the cloud later if necessary.

[0279] Examples of prompts to input into a generative AI model:

[0280] "I am designing a real-time hazard detection system to be installed on my electric mobility device. This system will use an imaging device to detect objects, calculate distance and speed, and issue a collision warning if necessary. Please propose an efficient notification method."

[0281] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0282] Step 1:

[0283] First, the terminal uses an imaging device to capture the video of the environment in real time. The input data is a series of consecutive image frames obtained from the camera. This video data is directly supplied to the next object detection step. As a specific operation, the terminal takes pictures multiple times per second to try to understand the dynamic environment.

[0284] Step 2:

[0285] The terminal analyzes the captured video data using an object detection algorithm. Using the image frames obtained in Step 1 as input, it obtains the identification results of the objects present on the screen as output. This identification is carried out by leveraging libraries such as TensorFlow and OpenCV. As a specific operation, for each frame, the terminal applies a deep learning model to identify vehicles and pedestrians.

[0286] Step 3:

[0287] The terminal calculates the distance to each object from the object detection results. Here, the input is the object identification result, and the output is data including the distance for each object. Depth estimation technology is used for distance calculation, applying stereo vision or monocular depth estimation. As a specific operation, based on the position information of the identified objects, the terminal calculates the distance using methods such as triangulation.

[0288] Step 4:

[0289] The terminal estimates the moving speed based on the consecutive position information of the objects. The input is the object distance data and the object position frames obtained in Step 3, and the output is the estimated speed for each object. As a specific operation, the terminal calculates the position change between frames and uses the time change to obtain the speed.

[0290] Step 5:

[0291] The terminal evaluates the risk of contact based on the distance and speed information obtained. The input information is the distance and speed data obtained in steps 3 and 4, and the output is the risk level evaluation result. Specifically, the terminal compares the data with pre-set safety standards to determine whether the risk is high or low.

[0292] Step 6:

[0293] The device will alert the user if it determines that the risk is high. The input will be the evaluation results from step 5, and the output will be an audio alert or vibration warning. Specifically, the device will call an API within the program to immediately draw the user's attention.

[0294] Step 7:

[0295] The terminal records video captured under specific conditions and saves it as needed. The input is video data obtained from the imaging device, and the output is the recorded video file. Specifically, the terminal saves video before and after an event is triggered to a dedicated folder and prepares it for uploading to an external storage device.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] Autonomous vehicles are required to accurately recognize surrounding objects and prevent collision risks. However, current technology makes it difficult to accurately grasp distance and movement in real time and issue warnings quickly. Therefore, providing effective means to improve the safety of autonomous vehicles is a challenge.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for capturing an object and calculating the spatial distance to the object using image acquisition means mounted on a storage medium as an execution device, means for evaluating the possibility of a collision based on the calculated distance and movement information and generating a warning according to the situation, means for storing the visual information before and after a specific situation occurs and transmitting the information to an external recording medium as necessary, and means for transmitting warnings by voice and vibration to a presentation device. As a result, it becomes possible for an autonomous vehicle to accurately judge the surrounding environment, detect potential collision risks in advance, and improve safety.

[0301] The "storage medium as an execution device" is hardware for storing data and executing software as necessary.

[0302] The "image acquisition means" is a process or device for acquiring visual information using a camera or sensor.

[0303] The "means for calculating the spatial distance" is a technique for quantifying the distance to a recognized object based on the acquired visual information.

[0304] "Evaluating the possibility of a collision" is a process of analyzing potential risks from recognized objects and surrounding situations and making a judgment to prevent accidents.

[0305] The "means for generating a warning" is a mechanism for emitting signals or messages to alert the user or system based on the evaluation result.

[0306] "Storing the visual information" is an operation of recording the video or image data at that moment when a specific event or situation occurs.

[0307] The "means for transmitting to an external recording medium" is a mechanism for transferring the stored data to other storage devices or cloud services via the Internet or the like.

[0308] "Means for transmitting warnings to a display device using sound and vibration" refers to methods of attracting the user's attention using sound and vibration.

[0309] To implement this invention, it is first necessary to develop a program to be mounted on a storage medium that serves as an execution device. This program runs on a mobile device such as a smartphone and acquires surrounding visual information in real time through a camera.

[0310] The server uses a smartphone camera as an image acquisition method and utilizes image processing libraries such as OpenCV to capture objects. At this time, it performs object recognition from the acquired images using machine learning models such as TensorFlow, and calculates the spatial distance based on the results using depth estimation technology.

[0311] By combining the calculated distance with motion information obtained from consecutive frames, the server assesses the likelihood of a collision. To assist the user in avoiding danger, warnings based on the risk predicted by the generative AI model are transmitted to the display device via voice and vibration. Furthermore, visual information in specific situations is transmitted via the network to an external storage medium such as the cloud, which can be referenced as evidence in the event of an accident.

[0312] A concrete example would be a self-driving vehicle in an urban area that detects a bicycle suddenly appearing in front of it. In this case, the server would immediately calculate the distance, evaluate the time until contact, and send a warning to the vehicle system. Another example of a prompt in a generative AI model would be "detect a specific object from the video, estimate its distance, and perform a real-time risk assessment."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The device uses its built-in camera to acquire video in real time.

[0316] The input is a video stream from the camera sensor, and the output is a sequence of image data. At this stage, the terminal uses the OpenCV library to divide the video into frames and convert them into a format that can be processed in real time.

[0317] Step 2:

[0318] The server receives image data sent from the terminal and performs object detection.

[0319] The input is the image data obtained in Step 1, and the output is the position information of objects within each frame. The server uses TensorFlow and a pre-trained generative AI model to identify objects within the frame and obtain their coordinates. This process reveals the type of object and its location.

[0320] Step 3:

[0321] The server uses depth estimation technology to calculate the distance to an object based on the object detection results.

[0322] The input is the location data from step 2, and the output is the distance to the object quantified. The server uses a depth estimation algorithm to calculate the exact distance by matching known physical data with image parameters.

[0323] Step 4:

[0324] The server analyzes positional information obtained from consecutive frames to calculate the object's movement speed.

[0325] The input consists of position and time data calculated from previous frames, and the output is the object's velocity. The server divides the distance traveled by the time to determine the velocity. This information is used to predict the time until contact.

[0326] Step 5:

[0327] The server compares the predicted contact time with safety standards to assess the risk of collision.

[0328] The input is the speed and distance information from step 4, and the output is a risk assessment. The server compares this to the set criteria and immediately generates a warning signal if it determines that the risk is high.

[0329] Step 6:

[0330] The device communicates warnings to the user through voice and vibration.

[0331] The input is the warning signal generated in step 5, and the output is an alert for the user. The device plays a voice message or activates vibration to notify the user of the imminent danger.

[0332] Step 7:

[0333] The server sends video data before and after a specific event to the cloud.

[0334] The input is the video data acquired in Step 1, and the output is the recorded video saved to an external storage medium via the network. The server uses a storage service such as AWS S3 to back up this data so that it can be used for later analysis or as evidence.

[0335] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0336] This invention aims to improve the safety of electric scooters by providing a new system that takes into account the user's emotional state. The system integrates a smartphone mounted on the electric scooter, a camera for monitoring the surrounding environment, and an emotion engine for recognizing the user's emotions.

[0337] The device first uses the smartphone's camera to acquire real-time images of the surroundings. This allows it to detect objects such as vehicles, people, and obstacles on the road and calculate the distance to them. Based on this information, the device assesses the potential risk of collision and issues alerts via voice or vibration as needed.

[0338] Furthermore, the device is equipped with an emotion engine that determines the user's emotional state in real time based on facial and voice characteristics. Based on this emotional state, the content and frequency of risk warnings are adjusted. For example, if the system detects that the user is stressed, it can increase the frequency of warnings or adjust the intensity of alerts.

[0339] Furthermore, this system has a function to record the user's stress level and emotional changes, and to generate a long-term safety profile. This profile can be used to optimize safety settings for each individual user.

[0340] As a concrete example, consider a scenario where a user is operating an electric scooter, and the camera detects a car ahead, calculating the distance to be 20 meters. The emotion engine analyzes the user's face and, if it determines that their concentration is waning, adjusts the device to issue a warning earlier than usual. As a result, the user can react to the situation more quickly, which is expected to reduce the risk of an accident. The recorded data is saved to the cloud as needed and used for post-incident review and analysis.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] The device activates the smartphone's camera and acquires real-time video of the surroundings. The video is processed as a series of image frames.

[0344] Step 2:

[0345] The device applies an object detection algorithm to the acquired image frames to identify objects such as vehicles and pedestrians. The position and size of each object are identified.

[0346] Step 3:

[0347] The device calculates the distance based on the location information of the identified object. It uses depth estimation technology to measure the distance from the camera to the object and outputs it as numerical data.

[0348] Step 4:

[0349] The device analyzes the change in the object's position between consecutive frames and estimates its velocity. Based on this velocity information, it evaluates whether the object is approaching.

[0350] Step 5:

[0351] Based on the calculated distance and speed, the device assesses the risk of contact and determines the risk level based on pre-set safety standards.

[0352] Step 6:

[0353] Simultaneously, the device activates an emotion engine, analyzing the user's emotional state from data collected by the camera and microphone. Emotions are determined from factors such as facial expressions and tone of voice.

[0354] Step 7:

[0355] The device adjusts the intensity and frequency of alerts based on the user's emotional state. For example, if it determines that the user is stressed, it will issue warnings more frequently or with greater emphasis than usual.

[0356] Step 8:

[0357] When a warning is issued, the device automatically records and saves video footage of the dangerous area. If necessary, this data is uploaded to the cloud.

[0358] Step 9:

[0359] Subsequently, the device updates the user's individual safety profile based on the collected emotional data. This improves the accuracy of subsequent risk assessments.

[0360] (Example 2)

[0361] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0362] In modern personal transportation, there is a challenge in that the impact of users' emotions and mental states on safety is not adequately considered. In particular, impaired judgment due to emotional states increases the risk of collisions and accidents, so a system that monitors and adjusts this in real time is needed. Furthermore, providing warnings appropriate to the surrounding environment is also essential for improving safety.

[0363] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0364] In this invention, the server includes means for capturing an object using a video device as an image acquisition means and calculating the distance to the object; means for determining the risk of collision based on the calculated distance and motion information and generating a warning according to the situation; means for emotion recognition that analyzes the user's emotional state; means for adjusting the content and frequency of the warning based on that emotional state; and means for saving video information before and after a specific event occurs and transmitting that information to an external recording medium as necessary. This makes it possible to provide highly accurate risk assessment and customized warnings based on the user's emotional state and surrounding environmental information.

[0365] An "image acquisition means" is a device for collecting visual information of the environment in real time, and is a device that enables the detection of objects and the calculation of their distances.

[0366] "Means for calculating distance" refers to a function that mathematically measures the distance to an object based on acquired visual information, and is a process for providing accurate positional information.

[0367] "Means for determining the risk of collision" refers to a method of evaluating the likelihood of a physical collision occurring based on distance information and motion data, and establishing criteria for issuing warnings.

[0368] "Means of generating warnings" refers to systems or processes that provide users with visual or auditory alerts based on risk assessments.

[0369] "Emotion recognition means" refers to technology that analyzes the characteristics of a user's face and voice to determine their emotional state in real time, and is a method for evaluating the user's mental state.

[0370] "Means for adjusting warning content and frequency" refers to a process for improving security by optimizing the content and frequency of warning messages, taking into account the user's emotional information.

[0371] "Means of transmitting to an external recording medium" refers to the function of transferring data to the cloud or other storage systems in order to save the collected data and analysis results outside the device.

[0372] This invention is a system for improving the safety of electric mobility devices, which analyzes the user's emotional state and the surrounding environment in real time. The system is integrated into a terminal used by the user and includes several key components.

[0373] The device first uses a camera as an image device to collect visual information from its surroundings. During this process, it uses libraries such as OpenCV and TensorFlow to perform image processing, enabling real-time object detection and distance measurement. The distance data serves as fundamental information for evaluating the likelihood of collisions.

[0374] Next, the device uses emotion recognition software to analyze the user's face and voice to determine their emotional state. By applying the Emotion API or similar emotion classification models, it can assess stress levels and attention levels, and dynamically adjust the frequency and content of warnings.

[0375] Furthermore, the system records user behavior data and saves video information in response to specific events. This enables post-event analysis and user profile generation, leading to long-term security optimization. The recorded data is securely transmitted to external storage media using cloud storage.

[0376] As a concrete example, consider a scenario where a user is using an electric mobility device while properly operating a terminal, and the system detects a vehicle ahead and calculates its distance. If the emotional engine detects a decrease in the user's concentration, the terminal will intensify its warnings and prompt the user to react quickly. This is expected to reduce the risk of collisions and prevent accidents.

[0377] An example of a prompt for a generated AI model is: "Describe the details of a safety system that takes into account the user's emotional state in electric mobility devices. Specifically describe the roles of hardware and software, and clearly explain how they provide benefits to the user."

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] The device activates the camera built into the smartphone and captures the surrounding image in real time. The input is visual information from the camera, and the output is video data. This video data is processed using OpenCV and TensorFlow to detect objects and calculate distances. Specifically, the system identifies vehicles and obstacles from the video data and performs analysis to calculate their positions and velocities.

[0381] Step 2:

[0382] Based on the location information of the detected object, the terminal calculates the distance. The input is the object detection result from step 1, and the output is the distance information to the object. Stereo vision and image parsing techniques are used to calculate the accurate distance and provide foundational data for evaluating the likelihood of a collision. Specifically, the distance is measured by triangulation using parallax.

[0383] Step 3:

[0384] The device combines distance and motion data to assess collision risk. Inputs are distance information to an object and its speed, while output is the risk assessment result. Based on this risk, the need for a warning is determined, and a warning is generated if necessary. Specifically, future movements are predicted using a statistical model based on accumulated data.

[0385] Step 4:

[0386] Next, the device activates its emotion engine and recognizes the user's emotional state from their face and voice. The input is the user's video and audio data, and the output is the evaluation result of their emotional state. Using the Emotion API and other tools, real-time emotion recognition is performed to understand the user's stress level and concentration level. This allows the system's operation to be adjusted according to the user's psychological state.

[0387] Step 5:

[0388] The device combines the risk assessment from Step 3 and the emotional state from Step 4 to optimize the content and frequency of warnings. The input is the risk assessment result and the emotional state assessment result, and the output is the adjusted warning. Specifically, if the user is experiencing stress, the system adjusts to issue more frequent warnings or stronger vibration warnings.

[0389] Step 6:

[0390] The server records all session data and stores the information necessary for analysis in the cloud. Inputs include all past operation logs and sensor data, while outputs are long-term user profiles. The stored data is used for later review and statistical analysis, and is utilized to improve security tailored to each user.

[0391] (Application Example 2)

[0392] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0393] In electric scooters and other personal mobility devices, risks threatening user safety involve not only the detection of hazardous objects in the surroundings and proper risk assessment, but also significant factors such as changes in the user's emotional state and concentration level. Conventional systems were unable to simultaneously consider these factors and perform risk assessments, resulting in insufficient safety.

[0394] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0395] In this invention, the server includes means for capturing the surrounding environment using a visual device as an image acquisition means and calculating the distance to an object; means for evaluating the risk of collision based on the calculated distance and movement information and generating a warning according to the situation; and means for analyzing the user's emotional state using emotion analysis means and adjusting the risk assessment and warning content. This enables more appropriate and timely safety measures by simultaneously considering the user's surrounding environment and emotional state.

[0396] An "image acquisition means" is a device that uses a visual device to capture visual information of the surrounding environment and collect necessary data.

[0397] A "visual device" is a device, including cameras and sensors, that is used to visually perceive surrounding objects and the environment.

[0398] "Means for calculating distance" refers to a method of calculating the physical distance to an object based on visual information obtained from image acquisition means.

[0399] "Movement information" refers to data related to the motion of an object, such as its position, velocity, and direction.

[0400] A "means for assessing collision risk" refers to a method of determining the likelihood of a collision between an object and a user based on acquired distance and movement information.

[0401] "Means of generating warnings" refers to methods of creating visual or audible alerts to draw the user's attention.

[0402] "Emotional analysis methods" are techniques for determining a user's emotional state by analyzing their facial expressions and vocal characteristics.

[0403] An "external data storage device" is a data storage medium used to save visual information related to specific events as needed, so that it can be accessed later.

[0404] A system implementing this invention consists of a terminal equipped with a visual device and an emotion analysis device, and a server for integrating and processing the data from these devices.

[0405] The device uses a camera as its visual device to capture its surroundings and process the visual data in real time. This camera uses image analysis software such as OpenCV or TensorFlow to detect objects from the visual data and calculate the distance to those objects. This information is transmitted to the device, and the risk of collision is assessed.

[0406] Furthermore, the device includes a function to analyze facial expressions and voice characteristics as a means of sentiment analysis. Here, it utilizes Google Cloud's sentiment analysis API and other tools to determine the user's emotional state in real time. This sentiment information is used for risk assessment and adjustment of warning content, and if the risk is determined to be high, a visual or audible alert is generated.

[0407] The server receives this data and, when a specific event occurs, saves the visual information before and after the event to an external data storage device. This makes it possible to review the situation later and perform detailed analysis.

[0408] As a concrete example, consider a scenario where a user is wearing smart glasses while outdoors. If a moving car is detected ahead and the distance is deemed dangerous, the system checks the user's facial expression, and if the emotion engine determines that the user is stressed, it provides an enhanced alert. This allows the user to quickly perceive danger and take appropriate action.

[0409] An example of a prompt message would be, "Please tell me when to issue a warning alert if the user is in a stressful state."

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The device uses visual devices to capture its surroundings in real time. The camera acquires visual information as image data, and image recognition software (such as OpenCV or TensorFlow) identifies objects. The input is real-time video data, and the output is the type of object and its location.

[0413] Step 2:

[0414] The device calculates distance from the object's location information. Using the object's location extracted from image data, it calculates the distance to the object using triangulation and other calculation methods. The input is the object's location information, and the output is the distance to the object.

[0415] Step 3:

[0416] The terminal assesses the risk of collision based on distance and movement information. This involves a step-by-step risk assessment using information such as speed and the direction of movement of the object. The input is the calculated distance and movement information, and the output is the result of the risk assessment.

[0417] Step 4:

[0418] The device analyzes the user's emotional state using an emotion analysis device. It sends facial expressions captured by the camera and voice collected by the microphone to Google Cloud's emotion analysis API to obtain the user's emotional state in real time. The input is data on facial expressions and voice, and the output is the evaluation result of the emotional state.

[0419] Step 5:

[0420] The server generates alerts based on risk assessment and emotional state. The type and intensity of the alerts are customized according to the level of risk and the user's emotional state. The inputs are the risk assessment results and emotional state assessment, and the output is the generated warning alert.

[0421] Step 6:

[0422] When a specific event occurs, the server saves the visual information before and after the event to an external data storage device. This ensures that the data necessary for later analysis and verification is stored. The input is the trigger for the specific event, and the output is the saved visual information.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0424] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0429] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0431] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0433] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0434] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0435] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0438] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0439] This invention is a system designed to enhance the safety of electric scooters, aiming to detect and prevent accident risks using a smartphone. The system functions by attaching a terminal consisting of a smartphone and its built-in camera to the electric scooter and monitoring the surrounding environment.

[0440] The device captures video in real time via its camera and uses object detection technology to identify vehicles, pedestrians, and other objects. For each identified object, the device calculates the distance and assesses the potential collision risk. The distance calculation is based on the acquired image data, specifically using depth estimation technology to quantify the distance to each object.

[0441] Furthermore, the device analyzes this distance information to estimate the object's approach speed. Combining the speed and distance data, it calculates the time until contact and determines the risk based on pre-set criteria. If a collision is deemed highly likely, it warns the user through voice alerts and vibrations. This warning allows the user to understand the situation in real time and take appropriate evasive action.

[0442] Furthermore, the device has a function to record video when specific events occur, depending on the situation. This means that video information before and after an accident is automatically saved and can be referenced later. The saved video data can also be transmitted to external storage media such as the cloud, and serves as evidence for use in insurance claims and legal proceedings after an accident.

[0443] As a concrete example, consider a scenario where a user is crossing a park on an electric scooter and spots a pedestrian ahead. The device recognizes the pedestrian using its camera and measures the distance as 15 meters. It then analyzes the subsequent frames to estimate the pedestrian's approach speed at 3 meters per second and calculates the time until collision as 5 seconds. If the device determines the risk is high based on safety standards, it immediately issues a warning and provides an alert to allow for appropriate action. This entire sequence of data is recorded and, if necessary, uploaded to the cloud later for use as evidence.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The device uses a camera fixed to the smartphone to acquire real-time video of the surroundings. The video data is captured as a series of image frames.

[0447] Step 2:

[0448] The device performs pre-processing on the captured image frames, adjusting brightness and contrast. This improves the video quality and makes it suitable for analysis.

[0449] Step 3:

[0450] For frames that have been preprocessed, the terminal performs AI-based object detection. Vehicles, pedestrians, obstacles, etc., are identified, and the location information of each object is obtained.

[0451] Step 4:

[0452] The device uses depth estimation technology to calculate the distance to identified objects. Distance data from the camera position to each object is output.

[0453] Step 5:

[0454] Based on distance data, the device analyzes changes in position between consecutive frames and estimates the approaching or moving-away velocity of an object.

[0455] Step 6:

[0456] Based on the distance and speed data obtained, the device assesses the risk of collision. It predicts the likelihood of a collision according to the established safety standards.

[0457] Step 7:

[0458] If a collision is detected as possible, the device will issue an alert via voice and vibration to immediately warn the user.

[0459] Step 8:

[0460] When a high risk is detected under specific conditions, the device records and saves video footage before and after the incident. This video data will be referenced later if necessary for review.

[0461] Step 9:

[0462] If recorded data is needed, the device sends it to an external storage medium such as cloud storage. This process ensures that the video is properly stored as evidence.

[0463] (Example 1)

[0464] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0465] In recent years, small electric vehicles have become popular as a means of personal transportation, but this has also led to an increase in the risk of accidents. In particular, real-time environmental awareness and appropriate countermeasures are required to prevent collisions with surrounding objects. The objective of this invention is to effectively recognize the surrounding environment for a moving vehicle and warn the user of potential dangers early. Furthermore, it aims to record the circumstances before and after an accident as needed, enabling appropriate processing.

[0466] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0467] In this invention, the server includes means for detecting an object using an imaging device as an observation means and calculating the distance to the object; means for evaluating the risk of contact based on the calculated distance and speed information and generating a notification according to the conditions; and means for recording visual information before and after a specific situation occurs and transmitting that information to an external storage device as necessary. This enables accurate understanding of the surrounding environment of a moving vehicle and provides quick and effective warnings of potential dangers. It also allows for detailed recording of the circumstances at the time of an accident, which can be used for subsequent analysis and processing.

[0468] "Observation means" refers to a device or group of devices used to capture the surrounding situation, and primarily involves acquiring image information of the environment using imaging devices.

[0469] An "imaging device" is a device that converts light into electrical signals to generate images, and includes devices such as cameras and sensors.

[0470] "Target" refers to elements that require attention along a travel path, such as objects or people detected by observation methods.

[0471] "Means of calculating distance" refers to the techniques and algorithms used to measure the physical distance to an observed object.

[0472] "Distance information" refers to numerical data that indicates the physical distance to the calculated target.

[0473] "Speed ​​information" refers to data that indicates the speed at which an object moves over time.

[0474] "Means for assessing the risk of contact" refers to a process or technology for determining the likelihood of a collision based on distance and speed information.

[0475] A "means of generating notifications" refers to a system that provides warnings and information to users according to the assessed risk.

[0476] "Means for recording visual information" refers to technologies and systems for saving images acquired from an imaging device under specific circumstances.

[0477] "External storage devices" refer to equipment including cloud services and physical media for the stable storage of recorded information.

[0478] This invention is an information processing system for enhancing safety, which monitors the surrounding environment using a terminal attached to a means of transport. The following hardware and software are used to implement the invention.

[0479] The device is a portable information terminal equipped with an imaging device, which uses a high-sensitivity camera. Furthermore, this device uses software libraries such as TensorFlow and OpenCV for image processing to identify objects in real time. It also uses a depth estimation algorithm to calculate the distance to the identified object.

[0480] As part of this system, the terminal collects distance and speed information and assesses the risk of collision. Based on the assessment, the server generates audio and vibration warnings to notify the user. If recording and saving visual information is necessary, the terminal automatically starts recording and sends the video data to an external storage device. This data can then serve as evidence that can be used later for accident analysis or legal proceedings.

[0481] As a concrete example, when a user crosses a park, the device identifies a pedestrian ahead. It calculates the distance to be 15 meters and estimates the speed to be 3 meters per second, calculating the time until collision to be 5 seconds. If it determines that there is a danger, the device immediately issues a warning to the user. This entire sequence of events is recorded and sent to the cloud later if necessary.

[0482] Examples of prompts to input into a generative AI model:

[0483] "I am designing a real-time hazard detection system to be installed on my electric mobility device. This system will use an imaging device to detect objects, calculate distance and speed, and issue a collision warning if necessary. Please propose an efficient notification method."

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] The terminal first captures images of the environment in real time using an imaging device. The input data consists of a series of image frames acquired from the camera. This video data is then supplied directly to the next object detection step. Specifically, the terminal takes multiple shots per second to capture the dynamic environment.

[0487] Step 2:

[0488] The device analyzes the captured video data using an object detection algorithm. The input is the image frame obtained in step 1, and the output is the identification result of objects present in the screen. This identification is performed using libraries such as TensorFlow and OpenCV. Specifically, the device applies a deep learning model to each frame to identify vehicles and pedestrians.

[0489] Step 3:

[0490] The terminal calculates the distance to each object based on the object detection results. The input here is the object identification result, and the output is data including the distance for each object. Depth estimation techniques are used for distance calculation, applying stereo vision and monocular depth estimation. Specifically, the terminal calculates the distance using triangulation or other methods based on the location information of the identified objects.

[0491] Step 4:

[0492] The terminal estimates the movement speed based on the sequential position information of the object. The input is the object's distance data and position frame obtained in step 3, and the output is the estimated speed for each object. Specifically, the terminal calculates the change in position between frames and uses the change over time to determine the speed.

[0493] Step 5:

[0494] The terminal evaluates the risk of contact based on the distance and speed information obtained. The input information is the distance and speed data obtained in steps 3 and 4, and the output is the risk level evaluation result. Specifically, the terminal compares the data with pre-set safety standards to determine whether the risk is high or low.

[0495] Step 6:

[0496] The device will alert the user if it determines that the risk is high. The input will be the evaluation results from step 5, and the output will be an audio alert or vibration warning. Specifically, the device will call an API within the program to immediately draw the user's attention.

[0497] Step 7:

[0498] The terminal records video captured under specific conditions and saves it as needed. The input is video data obtained from the imaging device, and the output is the recorded video file. Specifically, the terminal saves video before and after an event is triggered to a dedicated folder and prepares it for uploading to an external storage device.

[0499] (Application Example 1)

[0500] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0501] Autonomous vehicles are required to accurately recognize surrounding objects and prevent collision risks. However, current technology makes it difficult to accurately grasp distance and movement in real time and issue warnings quickly. Therefore, providing effective means to improve the safety of autonomous vehicles is a challenge.

[0502] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0503] In this invention, the server includes means for capturing an object and calculating the spatial distance to the object using image acquisition means mounted on a storage medium as an execution device; means for evaluating the possibility of collision based on the calculated distance and motion information and generating a warning according to the situation; means for saving visual information before and after a specific situation occurs and transmitting that information to an external recording medium as necessary; and means for transmitting audible and vibratory warnings to a presentation device. This enables autonomous vehicles to accurately judge their surroundings, proactively detect potential collision risks, and improve safety.

[0504] A "storage medium as an execution device" is hardware used to store data and execute software as needed.

[0505] "Image acquisition means" refers to a process or device for acquiring visual information using a camera or sensor.

[0506] "Means for calculating spatial distance" refers to techniques that quantify the distance to a recognized object based on acquired visual information.

[0507] "Assessing the likelihood of a collision" is the process of analyzing potential hazards from recognized objects and surrounding conditions, and making decisions to prevent accidents.

[0508] A "means for generating warnings" is a mechanism that issues signals or messages to alert the user or system based on evaluation results.

[0509] "Saving visual information" refers to the operation of recording video or image data at a specific moment when a particular event or situation occurs.

[0510] "Means of transmitting to an external recording medium" refers to a mechanism for transferring stored data to other storage devices or cloud services via the internet or other means.

[0511] "Means for transmitting warnings to a display device using sound and vibration" refers to methods of attracting the user's attention using sound and vibration.

[0512] To implement this invention, it is first necessary to develop a program to be mounted on a storage medium that serves as an execution device. This program runs on a mobile device such as a smartphone and acquires surrounding visual information in real time through a camera.

[0513] The server uses a smartphone camera as an image acquisition method and utilizes image processing libraries such as OpenCV to capture objects. At this time, it performs object recognition from the acquired images using machine learning models such as TensorFlow, and calculates the spatial distance based on the results using depth estimation technology.

[0514] By combining the calculated distance with motion information obtained from consecutive frames, the server assesses the likelihood of a collision. To assist the user in avoiding danger, warnings based on the risk predicted by the generative AI model are transmitted to the display device via voice and vibration. Furthermore, visual information in specific situations is transmitted via the network to an external storage medium such as the cloud, which can be referenced as evidence in the event of an accident.

[0515] A concrete example would be a self-driving vehicle in an urban area that detects a bicycle suddenly appearing in front of it. In this case, the server would immediately calculate the distance, evaluate the time until contact, and send a warning to the vehicle system. Another example of a prompt in a generative AI model would be "detect a specific object from the video, estimate its distance, and perform a real-time risk assessment."

[0516] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0517] Step 1:

[0518] The device uses its built-in camera to acquire video in real time.

[0519] The input is a video stream from the camera sensor, and the output is a sequence of image data. At this stage, the terminal uses the OpenCV library to divide the video into frames and convert them into a format that can be processed in real time.

[0520] Step 2:

[0521] The server receives image data sent from the terminal and performs object detection.

[0522] The input is the image data obtained in Step 1, and the output is the position information of objects within each frame. The server uses TensorFlow and a pre-trained generative AI model to identify objects within the frame and obtain their coordinates. This process reveals the type of object and its location.

[0523] Step 3:

[0524] The server uses depth estimation technology to calculate the distance to an object based on the object detection results.

[0525] The input is the location data from step 2, and the output is the distance to the object quantified. The server uses a depth estimation algorithm to calculate the exact distance by matching known physical data with image parameters.

[0526] Step 4:

[0527] The server analyzes positional information obtained from consecutive frames to calculate the object's movement speed.

[0528] The input consists of position and time data calculated from previous frames, and the output is the object's velocity. The server divides the distance traveled by the time to determine the velocity. This information is used to predict the time until contact.

[0529] Step 5:

[0530] The server compares the predicted contact time with safety standards to assess the risk of collision.

[0531] The input is the speed and distance information from step 4, and the output is a risk assessment. The server compares this to the set criteria and immediately generates a warning signal if it determines that the risk is high.

[0532] Step 6:

[0533] The device communicates warnings to the user through voice and vibration.

[0534] The input is the warning signal generated in step 5, and the output is an alert for the user. The device plays a voice message or activates vibration to notify the user of the imminent danger.

[0535] Step 7:

[0536] The server sends video data before and after a specific event to the cloud.

[0537] The input is the video data acquired in Step 1, and the output is the recorded video saved to an external storage medium via the network. The server uses a storage service such as AWS S3 to back up this data so that it can be used for later analysis or as evidence.

[0538] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0539] This invention aims to improve the safety of electric scooters by providing a new system that takes into account the user's emotional state. The system integrates a smartphone mounted on the electric scooter, a camera for monitoring the surrounding environment, and an emotion engine for recognizing the user's emotions.

[0540] The device first uses the smartphone's camera to acquire real-time images of the surroundings. This allows it to detect objects such as vehicles, people, and obstacles on the road and calculate the distance to them. Based on this information, the device assesses the potential risk of collision and issues alerts via voice or vibration as needed.

[0541] Furthermore, the device is equipped with an emotion engine that determines the user's emotional state in real time based on facial and voice characteristics. Based on this emotional state, the content and frequency of risk warnings are adjusted. For example, if the system detects that the user is stressed, it can increase the frequency of warnings or adjust the intensity of alerts.

[0542] Furthermore, this system has a function to record the user's stress level and emotional changes, and to generate a long-term safety profile. This profile can be used to optimize safety settings for each individual user.

[0543] As a concrete example, consider a scenario where a user is operating an electric scooter, and the camera detects a car ahead, calculating the distance to be 20 meters. The emotion engine analyzes the user's face and, if it determines that their concentration is waning, adjusts the device to issue a warning earlier than usual. As a result, the user can react to the situation more quickly, which is expected to reduce the risk of an accident. The recorded data is saved to the cloud as needed and used for post-incident review and analysis.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The device activates the smartphone's camera and acquires real-time video of the surroundings. The video is processed as a series of image frames.

[0547] Step 2:

[0548] The device applies an object detection algorithm to the acquired image frames to identify objects such as vehicles and pedestrians. The position and size of each object are identified.

[0549] Step 3:

[0550] The device calculates the distance based on the location information of the identified object. It uses depth estimation technology to measure the distance from the camera to the object and outputs it as numerical data.

[0551] Step 4:

[0552] The device analyzes the change in the object's position between consecutive frames and estimates its velocity. Based on this velocity information, it evaluates whether the object is approaching.

[0553] Step 5:

[0554] Based on the calculated distance and speed, the device assesses the risk of contact and determines the risk level based on pre-set safety standards.

[0555] Step 6:

[0556] Simultaneously, the device activates an emotion engine, analyzing the user's emotional state from data collected by the camera and microphone. Emotions are determined from factors such as facial expressions and tone of voice.

[0557] Step 7:

[0558] The device adjusts the intensity and frequency of alerts based on the user's emotional state. For example, if it determines that the user is stressed, it will issue warnings more frequently or with greater emphasis than usual.

[0559] Step 8:

[0560] When a warning is issued, the device automatically records and saves video footage of the dangerous area. If necessary, this data is uploaded to the cloud.

[0561] Step 9:

[0562] Subsequently, the device updates the user's individual safety profile based on the collected emotional data. This improves the accuracy of subsequent risk assessments.

[0563] (Example 2)

[0564] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0565] In modern personal transportation, there is a challenge in that the impact of users' emotions and mental states on safety is not adequately considered. In particular, impaired judgment due to emotional states increases the risk of collisions and accidents, so a system that monitors and adjusts this in real time is needed. Furthermore, providing warnings appropriate to the surrounding environment is also essential for improving safety.

[0566] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0567] In this invention, the server includes means for capturing an object using a video device as an image acquisition means and calculating the distance to the object; means for determining the risk of collision based on the calculated distance and motion information and generating a warning according to the situation; means for emotion recognition that analyzes the user's emotional state; means for adjusting the content and frequency of the warning based on that emotional state; and means for saving video information before and after a specific event occurs and transmitting that information to an external recording medium as necessary. This makes it possible to provide highly accurate risk assessment and customized warnings based on the user's emotional state and surrounding environmental information.

[0568] An "image acquisition means" is a device for collecting visual information of the environment in real time, and is a device that enables the detection of objects and the calculation of their distances.

[0569] "Means for calculating distance" refers to a function that mathematically measures the distance to an object based on acquired visual information, and is a process for providing accurate positional information.

[0570] "Means for determining the risk of collision" refers to a method of evaluating the likelihood of a physical collision occurring based on distance information and motion data, and establishing criteria for issuing warnings.

[0571] "Means of generating warnings" refers to systems or processes that provide users with visual or auditory alerts based on risk assessments.

[0572] "Emotion recognition means" refers to technology that analyzes the characteristics of a user's face and voice to determine their emotional state in real time, and is a method for evaluating the user's mental state.

[0573] "Means for adjusting warning content and frequency" refers to a process for improving security by optimizing the content and frequency of warning messages, taking into account the user's emotional information.

[0574] "Means of transmitting to an external recording medium" refers to the function of transferring data to the cloud or other storage systems in order to save the collected data and analysis results outside the device.

[0575] This invention is a system for improving the safety of electric mobility devices, which analyzes the user's emotional state and the surrounding environment in real time. The system is integrated into a terminal used by the user and includes several key components.

[0576] The device first uses a camera as an image device to collect visual information from its surroundings. During this process, it uses libraries such as OpenCV and TensorFlow to perform image processing, enabling real-time object detection and distance measurement. The distance data serves as fundamental information for evaluating the likelihood of collisions.

[0577] Next, the device uses emotion recognition software to analyze the user's face and voice to determine their emotional state. By applying the Emotion API or similar emotion classification models, it can assess stress levels and attention levels, and dynamically adjust the frequency and content of warnings.

[0578] Furthermore, the system records user behavior data and saves video information in response to specific events. This enables post-event analysis and user profile generation, leading to long-term security optimization. The recorded data is securely transmitted to external storage media using cloud storage.

[0579] As a concrete example, consider a scenario where a user is using an electric mobility device while properly operating a terminal, and the system detects a vehicle ahead and calculates its distance. If the emotional engine detects a decrease in the user's concentration, the terminal will intensify its warnings and prompt the user to react quickly. This is expected to reduce the risk of collisions and prevent accidents.

[0580] An example of a prompt for a generated AI model is: "Describe the details of a safety system that takes into account the user's emotional state in electric mobility devices. Specifically describe the roles of hardware and software, and clearly explain how they provide benefits to the user."

[0581] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0582] Step 1:

[0583] The device activates the camera built into the smartphone and captures the surrounding image in real time. The input is visual information from the camera, and the output is video data. This video data is processed using OpenCV and TensorFlow to detect objects and calculate distances. Specifically, the system identifies vehicles and obstacles from the video data and performs analysis to calculate their positions and velocities.

[0584] Step 2:

[0585] Based on the location information of the detected object, the terminal calculates the distance. The input is the object detection result from step 1, and the output is the distance information to the object. Stereo vision and image parsing techniques are used to calculate the accurate distance and provide foundational data for evaluating the likelihood of a collision. Specifically, the distance is measured by triangulation using parallax.

[0586] Step 3:

[0587] The device combines distance and motion data to assess collision risk. Inputs are distance information to an object and its speed, while output is the risk assessment result. Based on this risk, the need for a warning is determined, and a warning is generated if necessary. Specifically, future movements are predicted using a statistical model based on accumulated data.

[0588] Step 4:

[0589] Next, the device activates its emotion engine and recognizes the user's emotional state from their face and voice. The input is the user's video and audio data, and the output is the evaluation result of their emotional state. Using the Emotion API and other tools, real-time emotion recognition is performed to understand the user's stress level and concentration level. This allows the system's operation to be adjusted according to the user's psychological state.

[0590] Step 5:

[0591] The device combines the risk assessment from Step 3 and the emotional state from Step 4 to optimize the content and frequency of warnings. The input is the risk assessment result and the emotional state assessment result, and the output is the adjusted warning. Specifically, if the user is experiencing stress, the system adjusts to issue more frequent warnings or stronger vibration warnings.

[0592] Step 6:

[0593] The server records all session data and stores the information necessary for analysis in the cloud. Inputs include all past operation logs and sensor data, while outputs are long-term user profiles. The stored data is used for later review and statistical analysis, and is utilized to improve security tailored to each user.

[0594] (Application Example 2)

[0595] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0596] In electric scooters and other personal mobility devices, risks threatening user safety involve not only the detection of hazardous objects in the surroundings and proper risk assessment, but also significant factors such as changes in the user's emotional state and concentration level. Conventional systems were unable to simultaneously consider these factors and perform risk assessments, resulting in insufficient safety.

[0597] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0598] In this invention, the server includes means for capturing the surrounding environment using a visual device as an image acquisition means and calculating the distance to an object; means for evaluating the risk of collision based on the calculated distance and movement information and generating a warning according to the situation; and means for analyzing the user's emotional state using emotion analysis means and adjusting the risk assessment and warning content. This enables more appropriate and timely safety measures by simultaneously considering the user's surrounding environment and emotional state.

[0599] An "image acquisition means" is a device that uses a visual device to capture visual information of the surrounding environment and collect necessary data.

[0600] A "visual device" is a device, including cameras and sensors, that is used to visually perceive surrounding objects and the environment.

[0601] "Means for calculating distance" refers to a method of calculating the physical distance to an object based on visual information obtained from image acquisition means.

[0602] "Movement information" refers to data related to the motion of an object, such as its position, velocity, and direction.

[0603] A "means for assessing collision risk" refers to a method of determining the likelihood of a collision between an object and a user based on acquired distance and movement information.

[0604] "Means of generating warnings" refers to methods of creating visual or audible alerts to draw the user's attention.

[0605] "Emotional analysis methods" are techniques for determining a user's emotional state by analyzing their facial expressions and vocal characteristics.

[0606] An "external data storage device" is a data storage medium used to save visual information related to specific events as needed, so that it can be accessed later.

[0607] A system implementing this invention consists of a terminal equipped with a visual device and an emotion analysis device, and a server for integrating and processing the data from these devices.

[0608] The device uses a camera as its visual device to capture its surroundings and process the visual data in real time. This camera uses image analysis software such as OpenCV or TensorFlow to detect objects from the visual data and calculate the distance to those objects. This information is transmitted to the device, and the risk of collision is assessed.

[0609] Furthermore, the device includes a function to analyze facial expressions and voice characteristics as a means of sentiment analysis. Here, it utilizes Google Cloud's sentiment analysis API and other tools to determine the user's emotional state in real time. This sentiment information is used for risk assessment and adjustment of warning content, and if the risk is determined to be high, a visual or audible alert is generated.

[0610] The server receives this data and, when a specific event occurs, saves the visual information before and after the event to an external data storage device. This makes it possible to review the situation later and perform detailed analysis.

[0611] As a concrete example, consider a scenario where a user is wearing smart glasses while outdoors. If a moving car is detected ahead and the distance is deemed dangerous, the system checks the user's facial expression, and if the emotion engine determines that the user is stressed, it provides an enhanced alert. This allows the user to quickly perceive danger and take appropriate action.

[0612] An example of a prompt message would be, "Please tell me when to issue a warning alert if the user is in a stressful state."

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The device uses visual devices to capture its surroundings in real time. The camera acquires visual information as image data, and image recognition software (such as OpenCV or TensorFlow) identifies objects. The input is real-time video data, and the output is the type of object and its location.

[0616] Step 2:

[0617] The device calculates distance from the object's location information. Using the object's location extracted from image data, it calculates the distance to the object using triangulation and other calculation methods. The input is the object's location information, and the output is the distance to the object.

[0618] Step 3:

[0619] The terminal assesses the risk of collision based on distance and movement information. This involves a step-by-step risk assessment using information such as speed and the direction of movement of the object. The input is the calculated distance and movement information, and the output is the result of the risk assessment.

[0620] Step 4:

[0621] The device analyzes the user's emotional state using an emotion analysis device. It sends facial expressions captured by the camera and voice collected by the microphone to Google Cloud's emotion analysis API to obtain the user's emotional state in real time. The input is data on facial expressions and voice, and the output is the evaluation result of the emotional state.

[0622] Step 5:

[0623] The server generates alerts based on risk assessment and emotional state. The type and intensity of the alerts are customized according to the level of risk and the user's emotional state. The inputs are the risk assessment results and emotional state assessment, and the output is the generated warning alert.

[0624] Step 6:

[0625] When a specific event occurs, the server saves the visual information before and after the event to an external data storage device. This ensures that the data necessary for later analysis and verification is stored. The input is the trigger for the specific event, and the output is the saved visual information.

[0626] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0627] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0632] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0633] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0634] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0636] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0637] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0638] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0639] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0641] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0642] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] This invention is a system designed to enhance the safety of electric scooters, aiming to detect and prevent accident risks using a smartphone. The system functions by attaching a terminal consisting of a smartphone and its built-in camera to the electric scooter and monitoring the surrounding environment.

[0644] The device captures video in real time via its camera and uses object detection technology to identify vehicles, pedestrians, and other objects. For each identified object, the device calculates the distance and assesses the potential collision risk. The distance calculation is based on the acquired image data, specifically using depth estimation technology to quantify the distance to each object.

[0645] Furthermore, the device analyzes this distance information to estimate the object's approach speed. Combining the speed and distance data, it calculates the time until contact and determines the risk based on pre-set criteria. If a collision is deemed highly likely, it warns the user through voice alerts and vibrations. This warning allows the user to understand the situation in real time and take appropriate evasive action.

[0646] Furthermore, the device has a function to record video when specific events occur, depending on the situation. This means that video information before and after an accident is automatically saved and can be referenced later. The saved video data can also be transmitted to external storage media such as the cloud, and serves as evidence for use in insurance claims and legal proceedings after an accident.

[0647] As a concrete example, consider a scenario where a user is crossing a park on an electric scooter and spots a pedestrian ahead. The device recognizes the pedestrian using its camera and measures the distance as 15 meters. It then analyzes the subsequent frames to estimate the pedestrian's approach speed at 3 meters per second and calculates the time until collision as 5 seconds. If the device determines the risk is high based on safety standards, it immediately issues a warning and provides an alert to allow for appropriate action. This entire sequence of data is recorded and, if necessary, uploaded to the cloud later for use as evidence.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The device uses a camera fixed to the smartphone to acquire real-time video of the surroundings. The video data is captured as a series of image frames.

[0651] Step 2:

[0652] The device performs pre-processing on the captured image frames, adjusting brightness and contrast. This improves the video quality and makes it suitable for analysis.

[0653] Step 3:

[0654] For frames that have been preprocessed, the terminal performs AI-based object detection. Vehicles, pedestrians, obstacles, etc., are identified, and the location information of each object is obtained.

[0655] Step 4:

[0656] The device uses depth estimation technology to calculate the distance to identified objects. Distance data from the camera position to each object is output.

[0657] Step 5:

[0658] Based on distance data, the device analyzes changes in position between consecutive frames and estimates the approaching or moving-away velocity of an object.

[0659] Step 6:

[0660] Based on the distance and speed data obtained, the device assesses the risk of collision. It predicts the likelihood of a collision according to the established safety standards.

[0661] Step 7:

[0662] If a collision is detected as possible, the device will issue an alert via voice and vibration to immediately warn the user.

[0663] Step 8:

[0664] When a high risk is detected under specific conditions, the device records and saves video footage before and after the incident. This video data will be referenced later if necessary for review.

[0665] Step 9:

[0666] If recorded data is needed, the device sends it to an external storage medium such as cloud storage. This process ensures that the video is properly stored as evidence.

[0667] (Example 1)

[0668] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] In recent years, small electric vehicles have become popular as a means of personal transportation, but this has also led to an increase in the risk of accidents. In particular, real-time environmental awareness and appropriate countermeasures are required to prevent collisions with surrounding objects. The objective of this invention is to effectively recognize the surrounding environment for a moving vehicle and warn the user of potential dangers early. Furthermore, it aims to record the circumstances before and after an accident as needed, enabling appropriate processing.

[0670] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0671] In this invention, the server includes means for detecting an object using an imaging device as an observation means and calculating the distance to the object; means for evaluating the risk of contact based on the calculated distance and speed information and generating a notification according to the conditions; and means for recording visual information before and after a specific situation occurs and transmitting that information to an external storage device as necessary. This enables accurate understanding of the surrounding environment of a moving vehicle and provides quick and effective warnings of potential dangers. It also allows for detailed recording of the circumstances at the time of an accident, which can be used for subsequent analysis and processing.

[0672] "Observation means" refers to a device or group of devices used to capture the surrounding situation, and primarily involves acquiring image information of the environment using imaging devices.

[0673] An "imaging device" is a device that converts light into electrical signals to generate images, and includes devices such as cameras and sensors.

[0674] "Target" refers to elements that require attention along a travel path, such as objects or people detected by observation methods.

[0675] "Means of calculating distance" refers to the techniques and algorithms used to measure the physical distance to an observed object.

[0676] "Distance information" refers to numerical data that indicates the physical distance to the calculated target.

[0677] "Speed ​​information" refers to data that indicates the speed at which an object moves over time.

[0678] "Means for assessing the risk of contact" refers to a process or technology for determining the likelihood of a collision based on distance and speed information.

[0679] A "means of generating notifications" refers to a system that provides warnings and information to users according to the assessed risk.

[0680] "Means for recording visual information" refers to technologies and systems for saving images acquired from an imaging device under specific circumstances.

[0681] "External storage devices" refer to equipment including cloud services and physical media for the stable storage of recorded information.

[0682] This invention is an information processing system for enhancing safety, which monitors the surrounding environment using a terminal attached to a means of transport. The following hardware and software are used to implement the invention.

[0683] The device is a portable information terminal equipped with an imaging device, which uses a high-sensitivity camera. Furthermore, this device uses software libraries such as TensorFlow and OpenCV for image processing to identify objects in real time. It also uses a depth estimation algorithm to calculate the distance to the identified object.

[0684] As part of this system, the terminal collects distance and speed information and assesses the risk of collision. Based on the assessment, the server generates audio and vibration warnings to notify the user. If recording and saving visual information is necessary, the terminal automatically starts recording and sends the video data to an external storage device. This data can then serve as evidence that can be used later for accident analysis or legal proceedings.

[0685] As a concrete example, when a user crosses a park, the device identifies a pedestrian ahead. It calculates the distance to be 15 meters and estimates the speed to be 3 meters per second, calculating the time until collision to be 5 seconds. If it determines that there is a danger, the device immediately issues a warning to the user. This entire sequence of events is recorded and sent to the cloud later if necessary.

[0686] Examples of prompts to input into a generative AI model:

[0687] "I am designing a real-time hazard detection system to be installed on my electric mobility device. This system will use an imaging device to detect objects, calculate distance and speed, and issue a collision warning if necessary. Please propose an efficient notification method."

[0688] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0689] Step 1:

[0690] The terminal first captures images of the environment in real time using an imaging device. The input data consists of a series of image frames acquired from the camera. This video data is then supplied directly to the next object detection step. Specifically, the terminal takes multiple shots per second to capture the dynamic environment.

[0691] Step 2:

[0692] The device analyzes the captured video data using an object detection algorithm. The input is the image frame obtained in step 1, and the output is the identification result of objects present in the screen. This identification is performed using libraries such as TensorFlow and OpenCV. Specifically, the device applies a deep learning model to each frame to identify vehicles and pedestrians.

[0693] Step 3:

[0694] The terminal calculates the distance to each object based on the object detection results. The input here is the object identification result, and the output is data including the distance for each object. Depth estimation techniques are used for distance calculation, applying stereo vision and monocular depth estimation. Specifically, the terminal calculates the distance using triangulation or other methods based on the location information of the identified objects.

[0695] Step 4:

[0696] The terminal estimates the movement speed based on the sequential position information of the object. The input is the object's distance data and position frame obtained in step 3, and the output is the estimated speed for each object. Specifically, the terminal calculates the change in position between frames and uses the change over time to determine the speed.

[0697] Step 5:

[0698] The terminal evaluates the risk of contact based on the distance and speed information obtained. The input information is the distance and speed data obtained in steps 3 and 4, and the output is the risk level evaluation result. Specifically, the terminal compares the data with pre-set safety standards to determine whether the risk is high or low.

[0699] Step 6:

[0700] The device will alert the user if it determines that the risk is high. The input will be the evaluation results from step 5, and the output will be an audio alert or vibration warning. Specifically, the device will call an API within the program to immediately draw the user's attention.

[0701] Step 7:

[0702] The terminal records video captured under specific conditions and saves it as needed. The input is video data obtained from the imaging device, and the output is the recorded video file. Specifically, the terminal saves video before and after an event is triggered to a dedicated folder and prepares it for uploading to an external storage device.

[0703] (Application Example 1)

[0704] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0705] Autonomous vehicles are required to accurately recognize surrounding objects and prevent collision risks. However, current technology makes it difficult to accurately grasp distance and movement in real time and issue warnings quickly. Therefore, providing effective means to improve the safety of autonomous vehicles is a challenge.

[0706] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0707] In this invention, the server includes means for capturing an object and calculating the spatial distance to the object using image acquisition means mounted on a storage medium as an execution device; means for evaluating the possibility of collision based on the calculated distance and motion information and generating a warning according to the situation; means for saving visual information before and after a specific situation occurs and transmitting that information to an external recording medium as necessary; and means for transmitting audible and vibratory warnings to a presentation device. This enables autonomous vehicles to accurately judge their surroundings, proactively detect potential collision risks, and improve safety.

[0708] A "storage medium as an execution device" is hardware used to store data and execute software as needed.

[0709] "Image acquisition means" refers to a process or device for acquiring visual information using a camera or sensor.

[0710] "Means for calculating spatial distance" refers to techniques that quantify the distance to a recognized object based on acquired visual information.

[0711] "Assessing the likelihood of a collision" is the process of analyzing potential hazards from recognized objects and surrounding conditions, and making decisions to prevent accidents.

[0712] A "means for generating warnings" is a mechanism that issues signals or messages to alert the user or system based on evaluation results.

[0713] "Saving visual information" refers to the operation of recording video or image data at a specific moment when a particular event or situation occurs.

[0714] "Means of transmitting to an external recording medium" refers to a mechanism for transferring stored data to other storage devices or cloud services via the internet or other means.

[0715] "Means for transmitting warnings to a display device using sound and vibration" refers to methods of attracting the user's attention using sound and vibration.

[0716] To implement this invention, it is first necessary to develop a program to be mounted on a storage medium that serves as an execution device. This program runs on a mobile device such as a smartphone and acquires surrounding visual information in real time through a camera.

[0717] The server uses a smartphone camera as an image acquisition method and utilizes image processing libraries such as OpenCV to capture objects. At this time, it performs object recognition from the acquired images using machine learning models such as TensorFlow, and calculates the spatial distance based on the results using depth estimation technology.

[0718] By combining the calculated distance with motion information obtained from consecutive frames, the server assesses the likelihood of a collision. To assist the user in avoiding danger, warnings based on the risk predicted by the generative AI model are transmitted to the display device via voice and vibration. Furthermore, visual information in specific situations is transmitted via the network to an external storage medium such as the cloud, which can be referenced as evidence in the event of an accident.

[0719] A concrete example would be a self-driving vehicle in an urban area that detects a bicycle suddenly appearing in front of it. In this case, the server would immediately calculate the distance, evaluate the time until contact, and send a warning to the vehicle system. Another example of a prompt in a generative AI model would be "detect a specific object from the video, estimate its distance, and perform a real-time risk assessment."

[0720] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0721] Step 1:

[0722] The device uses its built-in camera to acquire video in real time.

[0723] The input is a video stream from the camera sensor, and the output is a sequence of image data. At this stage, the terminal uses the OpenCV library to divide the video into frames and convert them into a format that can be processed in real time.

[0724] Step 2:

[0725] The server receives image data sent from the terminal and performs object detection.

[0726] The input is the image data obtained in Step 1, and the output is the position information of objects within each frame. The server uses TensorFlow and a pre-trained generative AI model to identify objects within the frame and obtain their coordinates. This process reveals the type of object and its location.

[0727] Step 3:

[0728] The server uses depth estimation technology to calculate the distance to an object based on the object detection results.

[0729] The input is the location data from step 2, and the output is the distance to the object quantified. The server uses a depth estimation algorithm to calculate the exact distance by matching known physical data with image parameters.

[0730] Step 4:

[0731] The server analyzes positional information obtained from consecutive frames to calculate the object's movement speed.

[0732] The input consists of position and time data calculated from previous frames, and the output is the object's velocity. The server divides the distance traveled by the time to determine the velocity. This information is used to predict the time until contact.

[0733] Step 5:

[0734] The server compares the predicted contact time with safety standards to assess the risk of collision.

[0735] The input is the speed and distance information from step 4, and the output is a risk assessment. The server compares this to the set criteria and immediately generates a warning signal if it determines that the risk is high.

[0736] Step 6:

[0737] The device communicates warnings to the user through voice and vibration.

[0738] The input is the warning signal generated in step 5, and the output is an alert for the user. The device plays a voice message or activates vibration to notify the user of the imminent danger.

[0739] Step 7:

[0740] The server sends video data before and after a specific event to the cloud.

[0741] The input is the video data acquired in Step 1, and the output is the recorded video saved to an external storage medium via the network. The server uses a storage service such as AWS S3 to back up this data so that it can be used for later analysis or as evidence.

[0742] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0743] This invention aims to improve the safety of electric scooters by providing a new system that takes into account the user's emotional state. The system integrates a smartphone mounted on the electric scooter, a camera for monitoring the surrounding environment, and an emotion engine for recognizing the user's emotions.

[0744] The device first uses the smartphone's camera to acquire real-time images of the surroundings. This allows it to detect objects such as vehicles, people, and obstacles on the road and calculate the distance to them. Based on this information, the device assesses the potential risk of collision and issues alerts via voice or vibration as needed.

[0745] Furthermore, the device is equipped with an emotion engine that determines the user's emotional state in real time based on facial and voice characteristics. Based on this emotional state, the content and frequency of risk warnings are adjusted. For example, if the system detects that the user is stressed, it can increase the frequency of warnings or adjust the intensity of alerts.

[0746] Furthermore, this system has a function to record the user's stress level and emotional changes, and to generate a long-term safety profile. This profile can be used to optimize safety settings for each individual user.

[0747] As a concrete example, consider a scenario where a user is operating an electric scooter, and the camera detects a car ahead, calculating the distance to be 20 meters. The emotion engine analyzes the user's face and, if it determines that their concentration is waning, adjusts the device to issue a warning earlier than usual. As a result, the user can react to the situation more quickly, which is expected to reduce the risk of an accident. The recorded data is saved to the cloud as needed and used for post-incident review and analysis.

[0748] The following describes the processing flow.

[0749] Step 1:

[0750] The device activates the smartphone's camera and acquires real-time video of the surroundings. The video is processed as a series of image frames.

[0751] Step 2:

[0752] The device applies an object detection algorithm to the acquired image frames to identify objects such as vehicles and pedestrians. The position and size of each object are identified.

[0753] Step 3:

[0754] The device calculates the distance based on the location information of the identified object. It uses depth estimation technology to measure the distance from the camera to the object and outputs it as numerical data.

[0755] Step 4:

[0756] The device analyzes the change in the object's position between consecutive frames and estimates its velocity. Based on this velocity information, it evaluates whether the object is approaching.

[0757] Step 5:

[0758] Based on the calculated distance and speed, the device assesses the risk of contact and determines the risk level based on pre-set safety standards.

[0759] Step 6:

[0760] Simultaneously, the device activates an emotion engine, analyzing the user's emotional state from data collected by the camera and microphone. Emotions are determined from factors such as facial expressions and tone of voice.

[0761] Step 7:

[0762] The device adjusts the intensity and frequency of alerts based on the user's emotional state. For example, if it determines that the user is stressed, it will issue warnings more frequently or with greater emphasis than usual.

[0763] Step 8:

[0764] When a warning is issued, the device automatically records and saves video footage of the dangerous area. If necessary, this data is uploaded to the cloud.

[0765] Step 9:

[0766] Subsequently, the device updates the user's individual safety profile based on the collected emotional data. This improves the accuracy of subsequent risk assessments.

[0767] (Example 2)

[0768] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0769] In modern personal transportation, there is a challenge in that the impact of users' emotions and mental states on safety is not adequately considered. In particular, impaired judgment due to emotional states increases the risk of collisions and accidents, so a system that monitors and adjusts this in real time is needed. Furthermore, providing warnings appropriate to the surrounding environment is also essential for improving safety.

[0770] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0771] In this invention, the server includes means for capturing an object using a video device as an image acquisition means and calculating the distance to the object; means for determining the risk of collision based on the calculated distance and motion information and generating a warning according to the situation; means for emotion recognition that analyzes the user's emotional state; means for adjusting the content and frequency of the warning based on that emotional state; and means for saving video information before and after a specific event occurs and transmitting that information to an external recording medium as necessary. This makes it possible to provide highly accurate risk assessment and customized warnings based on the user's emotional state and surrounding environmental information.

[0772] An "image acquisition means" is a device for collecting visual information of the environment in real time, and is a device that enables the detection of objects and the calculation of their distances.

[0773] "Means for calculating distance" refers to a function that mathematically measures the distance to an object based on acquired visual information, and is a process for providing accurate positional information.

[0774] "Means for determining the risk of collision" refers to a method of evaluating the likelihood of a physical collision occurring based on distance information and motion data, and establishing criteria for issuing warnings.

[0775] "Means of generating warnings" refers to systems or processes that provide users with visual or auditory alerts based on risk assessments.

[0776] "Emotion recognition means" refers to technology that analyzes the characteristics of a user's face and voice to determine their emotional state in real time, and is a method for evaluating the user's mental state.

[0777] "Means for adjusting warning content and frequency" refers to a process for improving security by optimizing the content and frequency of warning messages, taking into account the user's emotional information.

[0778] "Means of transmitting to an external recording medium" refers to the function of transferring data to the cloud or other storage systems in order to save the collected data and analysis results outside the device.

[0779] This invention is a system for improving the safety of electric mobility devices, which analyzes the user's emotional state and the surrounding environment in real time. The system is integrated into a terminal used by the user and includes several key components.

[0780] The device first uses a camera as an image device to collect visual information from its surroundings. During this process, it uses libraries such as OpenCV and TensorFlow to perform image processing, enabling real-time object detection and distance measurement. The distance data serves as fundamental information for evaluating the likelihood of collisions.

[0781] Next, the device uses emotion recognition software to analyze the user's face and voice to determine their emotional state. By applying the Emotion API or similar emotion classification models, it can assess stress levels and attention levels, and dynamically adjust the frequency and content of warnings.

[0782] Furthermore, the system records user behavior data and saves video information in response to specific events. This enables post-event analysis and user profile generation, leading to long-term security optimization. The recorded data is securely transmitted to external storage media using cloud storage.

[0783] As a concrete example, consider a scenario where a user is using an electric mobility device while properly operating a terminal, and the system detects a vehicle ahead and calculates its distance. If the emotional engine detects a decrease in the user's concentration, the terminal will intensify its warnings and prompt the user to react quickly. This is expected to reduce the risk of collisions and prevent accidents.

[0784] An example of a prompt for a generated AI model is: "Describe the details of a safety system that takes into account the user's emotional state in electric mobility devices. Specifically describe the roles of hardware and software, and clearly explain how they provide benefits to the user."

[0785] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0786] Step 1:

[0787] The device activates the camera built into the smartphone and captures the surrounding image in real time. The input is visual information from the camera, and the output is video data. This video data is processed using OpenCV and TensorFlow to detect objects and calculate distances. Specifically, the system identifies vehicles and obstacles from the video data and performs analysis to calculate their positions and velocities.

[0788] Step 2:

[0789] Based on the location information of the detected object, the terminal calculates the distance. The input is the object detection result from step 1, and the output is the distance information to the object. Stereo vision and image parsing techniques are used to calculate the accurate distance and provide foundational data for evaluating the likelihood of a collision. Specifically, the distance is measured by triangulation using parallax.

[0790] Step 3:

[0791] The device combines distance and motion data to assess collision risk. Inputs are distance information to an object and its speed, while output is the risk assessment result. Based on this risk, the need for a warning is determined, and a warning is generated if necessary. Specifically, future movements are predicted using a statistical model based on accumulated data.

[0792] Step 4:

[0793] Next, the device activates its emotion engine and recognizes the user's emotional state from their face and voice. The input is the user's video and audio data, and the output is the evaluation result of their emotional state. Using the Emotion API and other tools, real-time emotion recognition is performed to understand the user's stress level and concentration level. This allows the system's operation to be adjusted according to the user's psychological state.

[0794] Step 5:

[0795] The device combines the risk assessment from Step 3 and the emotional state from Step 4 to optimize the content and frequency of warnings. The input is the risk assessment result and the emotional state assessment result, and the output is the adjusted warning. Specifically, if the user is experiencing stress, the system adjusts to issue more frequent warnings or stronger vibration warnings.

[0796] Step 6:

[0797] The server records all session data and stores the information necessary for analysis in the cloud. Inputs include all past operation logs and sensor data, while outputs are long-term user profiles. The stored data is used for later review and statistical analysis, and is utilized to improve security tailored to each user.

[0798] (Application Example 2)

[0799] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0800] In electric scooters and other personal mobility devices, risks threatening user safety involve not only the detection of hazardous objects in the surroundings and proper risk assessment, but also significant factors such as changes in the user's emotional state and concentration level. Conventional systems were unable to simultaneously consider these factors and perform risk assessments, resulting in insufficient safety.

[0801] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0802] In this invention, the server includes means for capturing the surrounding environment using a visual device as an image acquisition means and calculating the distance to an object; means for evaluating the risk of collision based on the calculated distance and movement information and generating a warning according to the situation; and means for analyzing the user's emotional state using emotion analysis means and adjusting the risk assessment and warning content. This enables more appropriate and timely safety measures by simultaneously considering the user's surrounding environment and emotional state.

[0803] An "image acquisition means" is a device that uses a visual device to capture visual information of the surrounding environment and collect necessary data.

[0804] A "visual device" is a device, including cameras and sensors, that is used to visually perceive surrounding objects and the environment.

[0805] "Means for calculating distance" refers to a method of calculating the physical distance to an object based on visual information obtained from image acquisition means.

[0806] "Movement information" refers to data related to the motion of an object, such as its position, velocity, and direction.

[0807] A "means for assessing collision risk" refers to a method of determining the likelihood of a collision between an object and a user based on acquired distance and movement information.

[0808] "Means of generating warnings" refers to methods of creating visual or audible alerts to draw the user's attention.

[0809] "Emotional analysis methods" are techniques for determining a user's emotional state by analyzing their facial expressions and vocal characteristics.

[0810] An "external data storage device" is a data storage medium used to save visual information related to specific events as needed, so that it can be accessed later.

[0811] A system implementing this invention consists of a terminal equipped with a visual device and an emotion analysis device, and a server for integrating and processing the data from these devices.

[0812] The device uses a camera as its visual device to capture its surroundings and process the visual data in real time. This camera uses image analysis software such as OpenCV or TensorFlow to detect objects from the visual data and calculate the distance to those objects. This information is transmitted to the device, and the risk of collision is assessed.

[0813] Furthermore, the device includes a function to analyze facial expressions and voice characteristics as a means of sentiment analysis. Here, it utilizes Google Cloud's sentiment analysis API and other tools to determine the user's emotional state in real time. This sentiment information is used for risk assessment and adjustment of warning content, and if the risk is determined to be high, a visual or audible alert is generated.

[0814] The server receives this data and, when a specific event occurs, saves the visual information before and after the event to an external data storage device. This makes it possible to review the situation later and perform detailed analysis.

[0815] As a concrete example, consider a scenario where a user is wearing smart glasses while outdoors. If a moving car is detected ahead and the distance is deemed dangerous, the system checks the user's facial expression, and if the emotion engine determines that the user is stressed, it provides an enhanced alert. This allows the user to quickly perceive danger and take appropriate action.

[0816] An example of a prompt message would be, "Please tell me when to issue a warning alert if the user is in a stressful state."

[0817] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0818] Step 1:

[0819] The device uses visual devices to capture its surroundings in real time. The camera acquires visual information as image data, and image recognition software (such as OpenCV or TensorFlow) identifies objects. The input is real-time video data, and the output is the type of object and its location.

[0820] Step 2:

[0821] The device calculates distance from the object's location information. Using the object's location extracted from image data, it calculates the distance to the object using triangulation and other calculation methods. The input is the object's location information, and the output is the distance to the object.

[0822] Step 3:

[0823] The terminal assesses the risk of collision based on distance and movement information. This involves a step-by-step risk assessment using information such as speed and the direction of movement of the object. The input is the calculated distance and movement information, and the output is the result of the risk assessment.

[0824] Step 4:

[0825] The device analyzes the user's emotional state using an emotion analysis device. It sends facial expressions captured by the camera and voice collected by the microphone to Google Cloud's emotion analysis API to obtain the user's emotional state in real time. The input is data on facial expressions and voice, and the output is the evaluation result of the emotional state.

[0826] Step 5:

[0827] The server generates alerts based on risk assessment and emotional state. The type and intensity of the alerts are customized according to the level of risk and the user's emotional state. The inputs are the risk assessment results and emotional state assessment, and the output is the generated warning alert.

[0828] Step 6:

[0829] When a specific event occurs, the server saves the visual information before and after the event to an external data storage device. This ensures that the data necessary for later analysis and verification is stored. The input is the trigger for the specific event, and the output is the saved visual information.

[0830] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0831] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0832] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0833] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0834] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0835] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0836] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0837] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0838] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0839] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0840] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0841] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0842] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0843] 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.

[0844] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0845] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0846] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0847] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0848] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0849] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0850] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0851] The following is further disclosed regarding the embodiments described above.

[0852] (Claim 1)

[0853] A means of capturing an object using a camera as an image acquisition means and calculating the distance to that object,

[0854] A means for determining the risk of collision based on calculated distance and movement information, and for generating a warning according to the situation,

[0855] A means for saving video information before and after a specific event occurs, and transmitting that information to an external recording medium as needed,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, further comprising means for analyzing the movement pattern of a captured object, making predictions using the analysis results, and adjusting the warning content.

[0859] (Claim 3)

[0860] The system according to claim 1, further comprising means for performing a risk assessment based on pre-set safety standards.

[0861] "Example 1"

[0862] (Claim 1)

[0863] A means for detecting an object using an imaging device as an observation means and calculating the distance to the object,

[0864] A means for evaluating the risk of collision based on calculated distance and speed information, and for generating notifications according to the conditions,

[0865] A means for recording visual information before and after a specific situation occurs, and transmitting that information to an external storage device as needed,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, further comprising means for analyzing the motion pattern of a detected object, making predictions using the analysis results, and adjusting the notification content.

[0869] (Claim 3)

[0870] The system according to claim 1, further comprising means for performing a risk assessment based on pre-set safety standards.

[0871] "Application Example 1"

[0872] (Claim 1)

[0873] A means for capturing an object using an image acquisition means mounted on a storage medium as an execution device, and for calculating the spatial distance to that object,

[0874] A means for evaluating the possibility of collision based on calculated distance and movement information, and for generating a warning according to the situation,

[0875] A means for saving visual information before and after a specific situation occurs, and transmitting that information to an external recording medium as needed,

[0876] Means for transmitting warnings to a display device via sound and vibration,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, further comprising means for predicting future behavior based on the movement pattern of an analyzed object and adjusting the warning content.

[0880] (Claim 3)

[0881] The system according to claim 1, further comprising means for evaluating the degree of risk based on pre-set safety standards, and means for transmitting visual information to an external storage device via a network under specific conditions.

[0882] "Example 2 of combining an emotion engine"

[0883] (Claim 1)

[0884] A means for capturing an object using a video device as an image acquisition means and calculating the distance to that object,

[0885] A means for determining the risk of collision based on calculated distance and movement information, and for generating a warning according to the situation,

[0886] An emotion recognition means for analyzing the user's emotional state, and a means for adjusting the content and frequency of warnings based on that emotional state,

[0887] A means for saving video information before and after a specific event occurs, and transmitting that information to an external recording medium as needed,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, further comprising means for analyzing the movement pattern of a captured object, making predictions using the analysis results, and adjusting the warning content.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for performing a risk assessment based on pre-set safety standards.

[0893] "Application example 2 when combining with an emotional engine"

[0894] (Claim 1)

[0895] A means for capturing the surrounding environment using a visual device as an image acquisition means and calculating the distance to an object,

[0896] A means for evaluating the risk of collision based on calculated distance and movement information, and for generating warnings according to the situation,

[0897] A means of analyzing the user's emotional state using emotion analysis tools, and adjusting risk assessment and warning content,

[0898] A means for saving visual information before and after a specific event occurs, and transmitting that information to an external data storage device as needed,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, further comprising means for analyzing the motion pattern of a captured object, using the results of the analysis to predict future situations, and adjusting the warning content.

[0902] (Claim 3)

[0903] The system according to claim 1, further comprising means for monitoring the emotional state of a user using emotion analysis means and performing a risk assessment based on pre-set safety standards. [Explanation of Symbols]

[0904] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of capturing an object using a camera as an image acquisition means and calculating the distance to that object, A means for determining the risk of collision based on calculated distance and movement information, and for generating a warning according to the situation, A means for saving video information before and after a specific event occurs, and transmitting that information to an external recording medium as needed, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing the movement pattern of a captured object, making predictions using the analysis results, and adjusting the warning content.

3. The system according to claim 1, further comprising means for performing a risk assessment based on pre-set safety standards.

Images