system

Abstract

We provide the system. [Solution] A means for acquiring road surface image information from an imaging device attached to a mobile body, Means for processing the aforementioned road surface image information to analyze the road surface condition, A means for detecting an anomaly and generating a warning based on the aforementioned analysis results, A means for notifying the user terminal of the aforementioned warning, 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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] Wheelchair users are exposed to risks associated with changes in road surface conditions in daily life. In particular, steps, slopes, and slippery road surfaces increase the risk of falling. With conventional methods, it is difficult to detect these risks in advance, which has been a factor hindering safe and comfortable movement. Therefore, there is a need to provide a system that monitors the road surface condition in real time, detects abnormalities in advance, and notifies the user.

Means for Solving the Problems

[0005] To solve the above problems, the present invention begins by attaching an imaging device to a moving object and acquiring image information of the road surface. Subsequently, means are used to process this image information and analyze the road surface condition. Furthermore, by providing means to detect anomalies based on the analysis results and generate warnings, the system enables users to take quick measures to avoid danger. In addition, means are provided to notify the user terminal of the generated warnings, realizing a system that provides information so that users can immediately judge the situation.

[0006] A "mobile device" refers to a device or machine that can move in a specific direction, primarily referring to wheelchairs and other means of transportation.

[0007] An "imaging device" refers to a device used to acquire image data, and includes devices such as cameras and sensors.

[0008] "Image information" refers to data acquired by an imaging device, representing information about a visual object.

[0009] "Road surface condition" is a general term that describes the state of roads and ground, and includes characteristics such as flatness, slope, and slipperiness.

[0010] "Means of analysis" refers to processing technologies and devices used to analyze acquired data and extract useful information.

[0011] An "abnormality" is an event or condition that deviates from the normal state and indicates a potential danger.

[0012] A "warning" refers to information or signals issued to draw attention to a specific event or situation.

[0013] A "user terminal" is a device used by a user to receive information, and includes smartphones, tablets, and other similar devices. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a tagged 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.

[0018] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0020] In the following embodiments, a tagged communication I / F (Interface) is an interface that includes a communication processor and an antenna. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system for ensuring safety by monitoring road surface conditions in real time when users are moving in a wheelchair. This system has the following functions: imaging device, image processing, road surface analysis, anomaly detection, and warning notification.

[0036] The device is mounted on the wheelchair and uses an imaging device to periodically photograph the road surface in front of it. This makes it possible to accurately understand the road surface conditions at all times.

[0037] The terminal preprocesses the captured images and efficiently transmits the information to the server. A secure communication protocol is used during this process.

[0038] The receiving server uses advanced image analysis algorithms to analyze road surface conditions in real time. The analysis employs a convolutional neural network (CNN), enabling highly accurate anomaly detection.

[0039] The analysis results will record any hazards on the road surface as anomalies. Examples include the size of bumps or slippery areas that may be prone to freezing.

[0040] If an anomaly is detected, the server generates a warning message and notifies the terminal. This notification includes details about the type and location of the anomaly, enabling the user to take prompt action.

[0041] The device provides users with easily understandable warnings. For example, visual or audio warnings can be configured, allowing for information tailored to the user's needs.

[0042] This system allows wheelchair users to pay attention to their direction of travel, reducing the risk of falls and accidents. Specifically, it can detect icy surfaces and take evasive action, enabling safer movement.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The device uses its camera to capture images of the road surface ahead at regular intervals. The acquired images are stored in temporary memory.

[0046] Step 2:

[0047] The device performs pre-processing on the captured image, including noise reduction and brightness adjustment. This process optimizes image quality and improves the accuracy of subsequent analysis.

[0048] Step 3:

[0049] The terminal compresses the pre-processed image data and sends it to the server. Data transmission is performed using a secure communication protocol.

[0050] Step 4:

[0051] The server performs analysis on the received image data using a convolutional neural network (CNN). This is used to evaluate factors such as road surface unevenness, slope, and slipperiness.

[0052] Step 5:

[0053] Based on the analysis results, the server determines whether there are any abnormalities in the road surface conditions. If an abnormality is detected, it generates warning information. This warning information includes the type of abnormality and its location.

[0054] Step 6:

[0055] The server sends the generated warning information to the terminal. The notification contains all the information necessary for subsequent user support.

[0056] Step 7:

[0057] The terminal displays warnings received from the server to the user. It uses on-screen warning messages and audio alerts to draw the user's attention.

[0058] Step 8:

[0059] The user checks the notification from their device and reconsiders their direction of travel. They should either change their course to avoid the anomaly or consider measures to continue moving cautiously.

[0060] (Example 1)

[0061] 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."

[0062] The aim is to solve the problem of increased risk of accidents and falls for wheelchair users who lack a way to accurately and in real time perceive road conditions while moving, especially in areas with unstable road surfaces or at times when visibility is poor.

[0063] 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.

[0064] In this invention, the server includes means for preprocessing road surface image information and transmitting it to an analysis device via data communication means, means for processing the image information using a convolutional neural network and analyzing the road surface condition, and means for detecting anomalies and generating warning information based on the analysis results. This enables wheelchair users to grasp the road surface condition in real time and obtain timely information to avoid danger.

[0065] A "mobile device" is a mechanical device that has the ability to move from one location to another.

[0066] An "imaging mechanism" is a device that acquires an image of an object using optical means.

[0067] "Image information" refers to information represented in digital or analog form that shows specific visual data.

[0068] "Preprocessing" refers to the initial data processing procedures performed to analyze data in a more appropriate format.

[0069] "Data communication means" refers to a method or device for sending and receiving digital data.

[0070] An "analysis device" is a mechanical device that automatically analyzes received data and generates meaningful information.

[0071] A "convolutional neural network" is a type of artificial intelligence that has a multi-layered structure and exhibits high performance, particularly in image recognition.

[0072] Anomaly detection is the process of recognizing phenomena or patterns that deviate from the normal state.

[0073] A "warning message" is a message containing detailed information to draw attention to a specific issue.

[0074] A "user device" is an electronic device that an individual operates and uses to receive information.

[0075] This invention provides technology to ensure user safety while moving, through a series of systems and programs mounted on a wheelchair, which is a mobile device. The main hardware involved is an imaging mechanism attached to the wheelchair, a data transfer terminal, and a server.

[0076] The terminal uses an imaging mechanism equipped with a high-resolution camera to periodically acquire image information of the road surface. This image information is pre-processed within the terminal, such as noise reduction and contrast adjustment, before being transmitted to the server via a secure protocol.

[0077] The server utilizes an advanced convolutional neural network (CNN) to process the received image information. The CNN is implemented using existing frameworks such as TENSORFLOW®, and accurately detects anomalies such as road surface irregularities and slippery, icy areas. For detected anomalies, warning information is generated, including the type and location of the anomaly.

[0078] Users can receive the aforementioned warning information through the device's display or audio output. This output is provided as a visual or audio alert to help users move safely.

[0079] For example, if the terminal detects ice on the road surface, the server generates a warning such as "There is an icy area 30 meters ahead," and the terminal communicates this to the user via voice.

[0080] Examples of prompt statements that can be used as input to a generative AI model are as follows:

[0081] "Design a system that analyzes road conditions in real time and detects anomalies to ensure the safe movement of wheelchair users. This system will use imaging devices and CNNs to identify dangerous road conditions and notify the user."

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The device uses a high-resolution camera mounted on the wheelchair to periodically capture images of the road surface ahead. The camera captures images once per second, obtaining digital image data as input. Specifically, the camera automatically triggers the shutter, and the acquired image is saved to the device's memory.

[0085] Step 2:

[0086] The device preprocesses the captured image data. It applies noise reduction filters and contrast adjustments to the digital image data obtained as input, generating clear image data as output. Specifically, it uses the OpenCV library to adjust the brightness and contrast of the image.

[0087] Step 3:

[0088] The terminal needs to transfer pre-processed image data to the server. As input, it securely sends the pre-processed image data to the server using the HTTPS protocol, and as output, it obtains confirmation of receipt. Specifically, the image is compressed into JPEG format, encrypted, and then transmitted.

[0089] Step 4:

[0090] The server analyzes the received image data. It uses a convolutional neural network (CNN) to analyze the transmitted image data as input, and outputs the road surface condition analysis results. Specifically, the server utilizes the TensorFlow framework to execute the analysis model and detect anomalies.

[0091] Step 5:

[0092] The server detects anomalies based on the analysis results and generates warning information. Using the CNN analysis results as input, it generates a warning message that includes the type and location of the anomaly as output. Specifically, it generates a text message such as "There is a frozen area 30 meters ahead."

[0093] Step 6:

[0094] The server sends the generated warning message to the terminal. As input, it securely sends the generated warning information to the terminal using the HTTPS protocol, and as output, the terminal confirms receipt. Specifically, it converts the warning data into JSON format and sends it securely.

[0095] Step 7:

[0096] The terminal notifies the user of the received warning information. Based on the warning information received from the server as input, it provides warnings in the form of audio or visual output. Specifically, it displays "Caution: Slippery surface ahead" on the terminal's display and emits an audio warning from the speaker.

[0097] (Application Example 1)

[0098] 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."

[0099] Ensuring safety during the movement of automated guided vehicles (AGVs) within factories is a challenge. In particular, it is necessary to establish a system that can detect obstacles such as slippery surfaces and steps in real time and promptly notify warnings, thereby reducing the risk of accidents and enabling safe goods transport.

[0100] 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.

[0101] In this invention, the server includes means for acquiring image information of the ground surface from an imaging device attached to a moving object, means for processing the image information of the ground surface to analyze the ground surface conditions and evaluate the safety in the direction of travel of the moving object, and means for detecting abnormalities and generating warnings based on the analysis results. This makes it possible to achieve safe movement in real time and prevent accidents in factories.

[0102] "Mobile equipment" refers to mechanical devices that are movable for transporting goods, and in particular includes automated guided vehicles (AGVs) used in factories.

[0103] An "imaging device" is a device such as a high-resolution camera attached to a moving object, used to acquire image information of the Earth's surface.

[0104] "Ground surface image information" refers to image data acquired by an imaging device, representing the state of the ground surface.

[0105] The "analysis method" is a means for processing acquired image information of the ground surface and evaluating its condition, and it utilizes a convolutional neural network (CNN).

[0106] An "abnormality" refers to an obstacle on the ground surface that could hinder the movement of a moving object, and specifically includes slippery areas and uneven surfaces.

[0107] A "warning" is a message sent to the user's device when an anomaly is detected, and it includes the type of anomaly and location information.

[0108] The system for realizing this invention consists of an imaging device attached to a mobile body, a server connected to it, and a user terminal. The server acquires image information of the ground surface using the imaging device, which consists of a high-resolution camera. The acquired image information is securely transmitted to the server via a wireless communication protocol. Specifically, communication technologies such as MQTT can be used.

[0109] The server analyzes the received image information using a convolutional neural network (CNN). The CNN evaluates the condition of the ground surface and implements advanced image processing to enhance safety. If an anomaly is detected as a result of the analysis, the server generates a warning message and notifies the user terminal. This message includes the type and location of the anomaly, allowing the user to take prompt action.

[0110] The user's terminal provides the notified warning in an intuitively understandable format. For example, it can be displayed as a voice assistant or a visual warning on the display, allowing the user to take immediate action. As a concrete example, it can detect a floor that has become slippery due to rain and automatically limit the speed of the moving object, allowing for continued safe movement.

[0111] An example of a prompt for a generated AI model might be, "Design a system for the safe movement of automated guided vehicles within a factory and provide an AI model that enables high-precision analysis." This prompt would then design the AI ​​model to support real-time anomaly detection and warning generation.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The terminal periodically acquires image information of the ground surface using an imaging device mounted on the mobile device. The imaging interval can be adjusted according to the speed of the mobile device and environmental conditions. The input is the captured raw image data, and the output is an image file in digital format.

[0115] Step 2:

[0116] The terminal preprocesses the acquired image data. It compresses the data, reduces noise, and converts it into a format suitable for communication. This processing allows the image data to be efficiently transmitted to the server. The input is the image data acquired in step 1, and the output is the processed image data.

[0117] Step 3:

[0118] The terminal sends the pre-processed image data to the server. A secure communication protocol such as MQTT is used for this transmission. The input is the image data processed in step 2, and the output is the image data that has arrived at the server.

[0119] Step 4:

[0120] The server analyzes the received image data using a Convolutional Neural Network (CNN). CNN is a deep learning technique for accurately detecting anomalies on the ground surface (such as slippery areas or uneven surfaces). The input is the image data received by the server, and the output is the anomaly information resulting from the analysis.

[0121] Step 5:

[0122] The server generates a warning message based on the analysis results. This message, which includes the type and location of the anomaly, is designed to allow the receiving user to take prompt action. The input is the anomaly information obtained in step 4, and the output is the warning message.

[0123] Step 6:

[0124] The terminal receives warning messages from the server and notifies the user. This notification is made via audio or visual means, allowing the user to immediately recognize and take action. The input is the warning message sent from the server, and the output is the presentation of warning information to the user.

[0125] Step 7:

[0126] Based on the notified warning messages, the user adjusts the direction and speed of the moving object as needed. This action ensures real-time safety. The input is the warning information received from the terminal, and the output is the user's actions to achieve safe movement.

[0127] 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.

[0128] This invention relates to a system that uses a device attached to a moving object to understand road surface conditions and provide appropriate warnings according to the user's emotional state. This system comprises an imaging device, an image processing device, an emotion recognition engine, and a warning generation device.

[0129] The terminal first acquires an image of the road surface ahead using an imaging device while moving. This image is processed in real time, noise is removed, and then it is sent to the server.

[0130] The server uses a convolutional neural network (CNN) to analyze image data and evaluate road surface conditions. It acquires information such as steps, slipperiness, and slope, and detects anomalies.

[0131] Next, the server uses an emotion engine to recognize the user's emotional state from camera images and audio data. This process identifies the user's emotions using facial expression analysis and voice tone analysis.

[0132] Based on the analyzed road surface conditions and emotional state, the server generates appropriate warning messages. These warnings are tailored to the user's emotional state, using mild language or, in some cases, urgent language.

[0133] The final warning message is sent to the user via the device. The user can review the warning and use it to determine if it is safe to proceed.

[0134] For example, if a user is feeling tense and there is a slippery surface ahead, the emotion engine will recognize this and gently notify them with a message like, "Pay attention to the road surface ahead." Conversely, if the user is relaxed, it will use normal warning sounds and visual indicators to draw attention. This allows users to receive information tailored to their emotional state, enabling them to travel safely and comfortably.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The device uses an imaging device attached to the wheelchair to capture images of the road surface ahead at regular intervals. This image data is temporarily stored on the device.

[0138] Step 2:

[0139] The terminal applies noise reduction processing to the saved images and adjusts them to a quality suitable for analysis. The adjusted image data is then compressed and sent to the server.

[0140] Step 3:

[0141] The server decompresses the received compressed image data and performs analysis using a convolutional neural network (CNN). This analysis detects road surface irregularities such as steps, slopes, and the possibility of freezing.

[0142] Step 4:

[0143] The server detects anomalies from the analysis results and generates a warning based on them. The generated warning information includes the type of anomaly and its location.

[0144] Step 5:

[0145] Data regarding the user's facial expressions and voice tone is transmitted to the server via the camera and microphone on the device worn by the user.

[0146] Step 6:

[0147] The server processes the received user data using an emotion engine to analyze the user's emotional state. The analysis results are used to adjust warning messages.

[0148] Step 7:

[0149] The server optimizes the content and presentation of warning messages based on the user's emotional state. For example, it might change to a calmer warning sound or use gentler language in text messages.

[0150] Step 8:

[0151] The device will notify the user of a final warning message. It will prompt the user to take appropriate action through on-screen displays and audio output.

[0152] Step 9:

[0153] Users check warnings received from their devices and adjust their direction of travel and actions accordingly. This decision-making process ensures safe and comfortable travel.

[0154] (Example 2)

[0155] 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".

[0156] There is a need to provide a system that can generate warnings that take into account not only abnormal road conditions but also the user's emotional state when a moving object is in motion. This will reduce the tension and confusion caused by the uniform warnings of conventional warning systems, thereby improving safety and comfort.

[0157] 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.

[0158] In this invention, the server includes means for processing road surface image information to analyze road surface conditions, means for recognizing the user's emotional state and combining it with the analysis results, and means for detecting anomalies based on the analysis results and emotional state and generating warnings that take the user's emotions into consideration. This makes it possible for the user to receive safe and accurate warnings that are appropriate to their emotional state.

[0159] An "imaging device" is a device attached to a moving object to acquire image information of the surroundings.

[0160] "Road surface condition" refers to information indicating the surface conditions of the road, including characteristics such as unevenness, slope, and slipperiness.

[0161] "Emotion recognition" is a technology that analyzes a user's emotional state and identifies it through facial expressions and tone of voice.

[0162] A "convolutional neural network" is a method of artificial intelligence that automatically learns the spatial layers and features of input data to perform classification and interpretation.

[0163] A "warning message" is a notification that conveys information about anomalies or safety issues detected by the system to the user.

[0164] A "user terminal" is a device used by a user to receive warning messages, and typically refers to a mobile device or computer.

[0165] "Abnormal" refers to conditions that are different from the norm in terms of road surface conditions or user circumstances, and that require special attention.

[0166] This invention is a system that uses a digital device attached to a mobile body. The system has the following functions:

[0167] The terminal uses a digital imaging device to acquire real-time image information of the road surface in front of the moving object. The acquired images are processed to be clear through a noise reduction filter and then sent to a server for analysis.

[0168] The server analyzes the received image information using convolutional neural network (CNN) technology to evaluate the road surface conditions. During the analysis, meaningful data such as road surface irregularities, slipperiness, and slope are extracted, and anomalies are detected as needed.

[0169] Simultaneously, the server utilizes emotion recognition technology to analyze facial expression and voice data transmitted by the user. This allows it to identify the user's emotional state and evaluate the impact of those emotions on their attention and sense of security.

[0170] The server then integrates the road surface condition analysis results with the user's emotional state to generate a warning message. This message is sensitive to the user's emotions and is adjusted to be either mild or urgent. For example, a warning such as "Pay attention to the road surface ahead" will be delivered in a particularly calm tone if the user is feeling stressed.

[0171] Finally, the generated warning message is notified to the user through the device. The notification is made via a visual display or an auditory assistance device, allowing the user to confirm the safety of their path based on the warning content.

[0172] As a concrete example, a user-provided prompt might be something like, "Generate an appropriate warning message based on the road conditions during travel and the user's emotional state." This allows the AI ​​model to generate individual warning messages in response to the request.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The terminal uses an imaging device to acquire image information of the road surface in front of a moving object. The input is an image acquired in real time, which is then passed through a noise reduction filter. During the noise reduction process, unnecessary data is reduced, and a clear image is generated. The output is image data in a state suitable for analysis.

[0176] Step 2:

[0177] The terminal sends the denoised image data to the server. The server analyzes the received image data using a convolutional neural network (CNN). The input to the analysis is the processed image data, and the output is information about the road surface conditions, such as features like steps, slipperiness, and slope. This analysis process utilizes GPU acceleration to achieve rapid processing.

[0178] Step 3:

[0179] The server processes camera images and audio data transmitted by the user. This data serves as input, and emotion recognition technology analyzes the user's facial expressions and voice. The output is the user's emotional state, including emotional characteristics such as reassurance, tension, and relaxation. This process utilizes facial expression analysis models and voice tone analysis models.

[0180] Step 4:

[0181] The server generates a warning message based on the analysis results of the road surface conditions and the user's emotional state. The input consists of both analysis results, and the AI ​​generation model determines the warning content based on this data. The output is an emotionally sensitive warning message, with the urgency level adjusted as needed. The AI ​​generation model creates the warning message using the prompt "Generate an appropriate warning message based on the road surface conditions and the user's emotional state during travel."

[0182] Step 5:

[0183] The terminal receives warning messages sent from the server and notifies the user. The input is the warning message, and the output is presented to the user in visual or auditory form. The terminal provides warnings to the user in an intuitively understandable way through screen displays or earphones, supporting the user in checking the safety of their path.

[0184] (Application Example 2)

[0185] 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".

[0186] The present invention aims to solve the problem of ensuring safety based on road surface conditions while providing appropriate warnings that correspond to the user's emotional state during the operation of a moving object. Conventional technologies were capable of detecting road surface conditions and generating warnings, but they did not take into account the user's emotional state, and the appropriateness of the warning content was sometimes lacking.

[0187] 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.

[0188] In this invention, the server includes means for acquiring road surface image information from an imaging device attached to a mobile vehicle, means for processing the road surface image information to analyze the road surface condition, and means for recognizing the user's emotional state and adjusting warnings based on that emotional state. This enables the provision of optimal warnings according to the user's emotional state, allowing for safe and comfortable travel.

[0189] A "mobile object" is a device that can physically change its position, such as a vehicle or a drone.

[0190] An "imaging device" is a device that detects light and generates image data, and is usually a camera.

[0191] "Image information" refers to visual data acquired by an imaging device, and is fundamental data for performing specific processing and analysis.

[0192] "Road surface condition" refers to the physical characteristics and state of the ground surface that a moving object comes into contact with or is affected by.

[0193] "Analysis means" refers to a device or method for analyzing acquired data according to specific criteria and extracting useful information.

[0194] An "anomaly" refers to a phenomenon or pattern that deviates from the normal state or expected standards.

[0195] A "warning" is a message or signal that notifies the user in advance of a potential danger or abnormal situation.

[0196] "Emotional state" refers to a user's mental or emotional condition, which is usually perceived through facial expressions and voice.

[0197] "Adjustment" refers to changing specific parameters or settings according to specific conditions or requirements.

[0198] A "terminal" is an electronic device used for inputting, receiving, and processing information.

[0199] In this invention, various devices and a server equipped on a mobile vehicle are used to detect road surface conditions and generate warnings based on the user's emotional state.

[0200] The server acquires real-time image information of the road surface from an imaging device attached to a mobile vehicle. A high-resolution camera can be used as this imaging device. The acquired image information is preprocessed appropriately to remove noise. Subsequently, the road surface condition is analyzed using a convolutional neural network (CNN). This analysis can extract information such as steps, slipperiness, and slope, and detect anomalies. Frameworks such as TensorFlow and PyTorch can be used to implement the CNN.

[0201] The server also incorporates an emotion recognition engine to recognize the user's emotional state. This engine captures the user's facial expressions with a camera and acquires their voice with a microphone, then evaluates their emotional state. Emotion recognition utilizes facial expression analysis and voice tone analysis. Therefore, facial recognition software and the Google® Cloud Speech-to-Text API can be used.

[0202] Based on the analyzed road surface condition information and emotional state information, the server generates a warning message and sends it to the user's terminal. This warning message is adjusted to be either mild or urgent depending on the user's emotional state. By utilizing a generation AI model, it is possible to provide more natural and user-friendly messages.

[0203] For example, if the user is tense and the road ahead is slippery, the server will notify them in a calm tone with the message "Please pay attention ahead." On the other hand, if the user is relaxed, the server will use a visual display along with a normal warning sound to draw their attention.

[0204] An example of a prompt to input into the generation AI model is: "Generate the most appropriate warning message based on current road conditions and passenger sentiment."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server acquires real-time image information of the road surface from an imaging device mounted on a mobile vehicle. The input is image data captured by the imaging device, and the output is pre-processed road surface image information. In this processing, a noise reduction algorithm is applied to clear the image data and improve the accuracy of the analysis.

[0208] Step 2:

[0209] The server analyzes the road surface conditions using a convolutional neural network (CNN) on preprocessed image data. The input is denoised road surface image data, and the output is condition information such as road surface height, slipperiness, and slope. The CNN detects specific patterns and evaluates the possibility of anomalies.

[0210] Step 3:

[0211] The server acquires the user's facial expressions and voice from cameras and microphones installed inside the mobile device, and recognizes their emotional state using an emotion recognition engine. The input is the user's facial image and voice data, and the output is the user's emotional state (e.g., tense, anxious, relaxed). The emotional state is extracted by performing facial expression analysis and voice tone analysis.

[0212] Step 4:

[0213] The server generates warning messages based on analyzed road surface conditions and emotional states. The inputs are road surface condition information and emotional state information, and the output is a user-optimized warning message. In this step, a generation AI model is used to input prompts and generate a message with adjusted content.

[0214] Step 5:

[0215] The server notifies the user terminal of the generated warning message. The input is the generated warning message, and the output is the message displayed on the user terminal. The terminal presents this message to the user as an audio or visual instruction to support safe movement.

[0216] 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.

[0217] 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 those described above. 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 shown 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] This invention is a system for ensuring safety by monitoring road surface conditions in real time when users are moving in a wheelchair. This system has the following functions: imaging device, image processing, road surface analysis, anomaly detection, and warning notification.

[0233] The device is mounted on the wheelchair and uses an imaging device to periodically photograph the road surface in front of it. This makes it possible to accurately understand the road surface conditions at all times.

[0234] The terminal preprocesses the captured images and efficiently transmits the information to the server. A secure communication protocol is used during this process.

[0235] The receiving server uses advanced image analysis algorithms to analyze road surface conditions in real time. The analysis employs a convolutional neural network (CNN), enabling highly accurate anomaly detection.

[0236] The analysis results will record any hazards on the road surface as anomalies. Examples include the size of bumps or slippery areas that may be prone to freezing.

[0237] If an anomaly is detected, the server generates a warning message and notifies the terminal. This notification includes details about the type and location of the anomaly, enabling the user to take prompt action.

[0238] The device provides users with easily understandable warnings. For example, visual or audio warnings can be configured, allowing for information tailored to the user's needs.

[0239] This system allows wheelchair users to pay attention to their direction of travel, reducing the risk of falls and accidents. Specifically, it can detect icy surfaces and take evasive action, enabling safer movement.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The device uses its camera to capture images of the road surface ahead at regular intervals. The acquired images are stored in temporary memory.

[0243] Step 2:

[0244] The device performs pre-processing on the captured image, including noise reduction and brightness adjustment. This process optimizes image quality and improves the accuracy of subsequent analysis.

[0245] Step 3:

[0246] The terminal compresses the pre-processed image data and sends it to the server. Data transmission is performed using a secure communication protocol.

[0247] Step 4:

[0248] The server performs analysis on the received image data using a convolutional neural network (CNN). This is used to evaluate factors such as road surface unevenness, slope, and slipperiness.

[0249] Step 5:

[0250] Based on the analysis results, the server determines whether there are any abnormalities in the road surface conditions. If an abnormality is detected, it generates warning information. This warning information includes the type of abnormality and its location.

[0251] Step 6:

[0252] The server sends the generated warning information to the terminal. The notification contains all the information necessary for subsequent user support.

[0253] Step 7:

[0254] The terminal displays warnings received from the server to the user. It uses on-screen warning messages and audio alerts to draw the user's attention.

[0255] Step 8:

[0256] The user checks the notification from their device and reconsiders their direction of travel. They should either change their course to avoid the anomaly or consider measures to continue moving cautiously.

[0257] (Example 1)

[0258] 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."

[0259] The aim is to solve the problem of increased risk of accidents and falls for wheelchair users who lack a way to accurately and in real time perceive road conditions while moving, especially in areas with unstable road surfaces or at times when visibility is poor.

[0260] 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.

[0261] In this invention, the server includes means for preprocessing road surface image information and transmitting it to an analysis device via data communication means, means for processing the image information using a convolutional neural network and analyzing the road surface condition, and means for detecting anomalies and generating warning information based on the analysis results. This enables wheelchair users to grasp the road surface condition in real time and obtain timely information to avoid danger.

[0262] A "mobile device" is a mechanical device that has the ability to move from one location to another.

[0263] An "imaging mechanism" is a device that acquires an image of an object using optical means.

[0264] "Image information" refers to information represented in digital or analog form that shows specific visual data.

[0265] "Preprocessing" refers to the initial data processing procedures performed to analyze data in a more appropriate format.

[0266] "Data communication means" refers to a method or device for sending and receiving digital data.

[0267] An "analysis device" is a mechanical device that automatically analyzes received data and generates meaningful information.

[0268] A "convolutional neural network" is a type of artificial intelligence that has a multi-layered structure and exhibits high performance, particularly in image recognition.

[0269] Anomaly detection is the process of recognizing phenomena or patterns that deviate from the normal state.

[0270] A "warning message" is a message containing detailed information to draw attention to a specific issue.

[0271] A "user device" is an electronic device that an individual operates and uses to receive information.

[0272] This invention provides technology to ensure user safety while moving, through a series of systems and programs mounted on a wheelchair, which is a mobile device. The main hardware involved is an imaging mechanism attached to the wheelchair, a data transfer terminal, and a server.

[0273] The terminal uses an imaging mechanism equipped with a high-resolution camera to periodically acquire image information of the road surface. This image information is pre-processed within the terminal, such as noise reduction and contrast adjustment, before being transmitted to the server via a secure protocol.

[0274] The server utilizes an advanced convolutional neural network (CNN) to process the received image information. The CNN is implemented using existing frameworks such as TensorFlow and accurately detects anomalies such as uneven road surfaces and slippery, icy areas. For detected anomalies, warning information is generated, including the type and location of the anomaly.

[0275] Users can receive the aforementioned warning information through the device's display or audio output. This output is provided as a visual or audio alert to help users move safely.

[0276] As a specific example, when the terminal detects the freezing of the road surface, the server generates a warning such as "There is a frozen area 30 meters ahead", and the terminal conveys it to the user by voice.

[0277] Examples of prompt sentences that can be considered as inputs to the generation AI model are as follows:

[0278] "Please design a system that analyzes the road surface condition in real time and detects abnormalities so that wheelchair users can move safely. In this system, an imaging device and a CNN are used to identify dangerous road surface conditions and notify the user."

[0279] The flow of the specific process in Example 1 will be described using FIG. 11.

[0280] Step 1:

[0281] The terminal uses a high-resolution camera mounted on the wheelchair to periodically capture images of the road surface ahead. At this time, the camera captures images at a frequency of once per second and obtains digital image data as input. As a specific operation, the camera automatically takes a shutter and saves the acquired image in the memory of the terminal.

[0282] Step 2:

[0283] The terminal preprocesses the captured image data. For the digital image data obtained as input, noise removal filters and contrast adjustment are performed to generate clear image data as output. Specifically, the OpenCV library is used to adjust the brightness and contrast of the image.

[0284] Step 3:

[0285] The terminal needs to transfer the pre - processed image data to the server. As input, the pre - processed image data is securely sent to the server using the HTTPS protocol, and as output, an acknowledgment of receipt is obtained. As a specific operation, the image is compressed into the JPEG format, encrypted, and then the data is transmitted.

[0286] Step 4:

[0287] The server analyzes the received image data. As input, the transferred image data is analyzed using a convolutional neural network (CNN), and as output, the analysis result of the road surface condition is obtained. Specifically, within the server, the TensorFlow framework is utilized to execute the analysis model to detect abnormalities.

[0288] Step 5:

[0289] The server detects abnormalities based on the analysis results and generates warning information. As input, the analysis results of the CNN are used, and as output, a warning message containing the type and location information of the abnormality is generated. As a specific operation, a text message such as "There is a frozen area 30 meters ahead" is generated.

[0290] Step 6:

[0291] The server sends the generated warning message to the terminal. As input, the generated warning information is securely sent to the terminal using the HTTPS protocol, and as output, the terminal performs an acknowledgment of receipt. As a specific operation, the warning data is converted into the JSON format and securely transmitted.

[0292] Step 7:

[0293] The terminal notifies the user of the received warning information. As input, based on the warning information received from the server, as output, a warning is provided in the form of audio or visual. As a specific operation, a message "Attention: There is a slippery road surface" is displayed on the terminal's display, and a warning sound is emitted from the speaker.

[0294] (Application Example 1)

[0295] 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."

[0296] Ensuring safety during the movement of automated guided vehicles (AGVs) within factories is a challenge. In particular, it is necessary to establish a system that can detect obstacles such as slippery surfaces and steps in real time and promptly notify warnings, thereby reducing the risk of accidents and enabling safe goods transport.

[0297] 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.

[0298] In this invention, the server includes means for acquiring image information of the ground surface from an imaging device attached to a moving object, means for processing the image information of the ground surface to analyze the ground surface conditions and evaluate the safety in the direction of travel of the moving object, and means for detecting abnormalities and generating warnings based on the analysis results. This makes it possible to achieve safe movement in real time and prevent accidents in factories.

[0299] "Mobile equipment" refers to mechanical devices that are movable for transporting goods, and in particular includes automated guided vehicles (AGVs) used in factories.

[0300] An "imaging device" is a device such as a high-resolution camera attached to a moving object, used to acquire image information of the Earth's surface.

[0301] "Ground surface image information" refers to image data acquired by an imaging device, representing the state of the ground surface.

[0302] The "analysis method" is a means for processing acquired image information of the ground surface and evaluating its condition, and it utilizes a convolutional neural network (CNN).

[0303] "Abnormality" refers to surface obstacles that may impede the progress of a moving object, specifically including slippery areas and steps.

[0304] "Warning" is a message notified to the user terminal when an abnormality is detected, including the type of abnormality and location information.

[0305] The system for realizing this invention is composed of an imaging device attached to a moving object, a server connected thereto, and a user terminal. The server uses an imaging device consisting of a high-resolution camera to acquire image information of the ground surface. The acquired image information is securely transmitted to the server via a wireless communication protocol. Specifically, communication technologies such as MQTT can be used.

[0306] In the server, the received image information is analyzed by a convolutional neural network (CNN). The CNN evaluates the state of the ground surface and realizes advanced image processing to enhance safety. As a result of the analysis, if an abnormality is detected, the server generates a warning message and notifies the user terminal. Since this message contains the type of abnormality and location information, the user can quickly take countermeasures.

[0307] The user terminal provides the notified warning in a form that can be intuitively understood. For example, by being displayed as a voice assistant or a visual warning on the display, the user can take immediate countermeasures. As a specific example, by detecting a floor that has become slippery due to rain and automatically limiting the speed of the moving object, safe movement can be continued.

[0308] Examples of prompt sentences for the generated AI model include "Design a system for an unmanned transport vehicle to move safely within a factory and provide an AI model that enables high-precision analysis." With this prompt, the AI model is designed to support real-time anomaly detection and warning generation.

[0309] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0310] Step 1:

[0311] The terminal periodically acquires image information of the ground surface using an imaging device mounted on the mobile device. The imaging interval can be adjusted according to the speed of the mobile device and environmental conditions. The input is the captured raw image data, and the output is an image file in digital format.

[0312] Step 2:

[0313] The terminal preprocesses the acquired image data. It compresses the data, reduces noise, and converts it into a format suitable for communication. This processing allows the image data to be efficiently transmitted to the server. The input is the image data acquired in step 1, and the output is the processed image data.

[0314] Step 3:

[0315] The terminal sends the pre-processed image data to the server. A secure communication protocol such as MQTT is used for this transmission. The input is the image data processed in step 2, and the output is the image data that has arrived at the server.

[0316] Step 4:

[0317] The server analyzes the received image data using a Convolutional Neural Network (CNN). CNN is a deep learning technique for accurately detecting anomalies on the ground surface (such as slippery areas or uneven surfaces). The input is the image data received by the server, and the output is the anomaly information resulting from the analysis.

[0318] Step 5:

[0319] The server generates a warning message based on the analysis results. This message, which includes the type and location of the anomaly, is designed to allow the receiving user to take prompt action. The input is the anomaly information obtained in step 4, and the output is the warning message.

[0320] Step 6:

[0321] The terminal receives warning messages from the server and notifies the user. This notification is made via audio or visual means, allowing the user to immediately recognize and take action. The input is the warning message sent from the server, and the output is the presentation of warning information to the user.

[0322] Step 7:

[0323] Based on the notified warning messages, the user adjusts the direction and speed of the moving object as needed. This action ensures real-time safety. The input is the warning information received from the terminal, and the output is the user's actions to achieve safe movement.

[0324] 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.

[0325] This invention relates to a system that uses a device attached to a moving object to understand road surface conditions and provide appropriate warnings according to the user's emotional state. This system comprises an imaging device, an image processing device, an emotion recognition engine, and a warning generation device.

[0326] The terminal first acquires an image of the road surface ahead using an imaging device while moving. This image is processed in real time, noise is removed, and then it is sent to the server.

[0327] The server uses a convolutional neural network (CNN) to analyze image data and evaluate road surface conditions. It acquires information such as steps, slipperiness, and slope, and detects anomalies.

[0328] Next, the server uses an emotion engine to recognize the user's emotional state from camera images and audio data. This process identifies the user's emotions using facial expression analysis and voice tone analysis.

[0329] Based on the analyzed road surface conditions and emotional state, the server generates appropriate warning messages. These warnings are tailored to the user's emotional state, using mild language or, in some cases, urgent language.

[0330] The final warning message is sent to the user via the device. The user can review the warning and use it to determine if it is safe to proceed.

[0331] For example, if a user is feeling tense and there is a slippery surface ahead, the emotion engine will recognize this and gently notify them with a message like, "Pay attention to the road surface ahead." Conversely, if the user is relaxed, it will use normal warning sounds and visual indicators to draw attention. This allows users to receive information tailored to their emotional state, enabling them to travel safely and comfortably.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The device uses an imaging device attached to the wheelchair to capture images of the road surface ahead at regular intervals. This image data is temporarily stored on the device.

[0335] Step 2:

[0336] The terminal applies noise reduction processing to the saved images and adjusts them to a quality suitable for analysis. The adjusted image data is then compressed and sent to the server.

[0337] Step 3:

[0338] The server decompresses the received compressed image data and performs analysis using a convolutional neural network (CNN). This analysis detects road surface irregularities such as steps, slopes, and the possibility of freezing.

[0339] Step 4:

[0340] The server detects anomalies from the analysis results and generates a warning based on them. The generated warning information includes the type of anomaly and its location.

[0341] Step 5:

[0342] Data regarding the user's facial expressions and voice tone is transmitted to the server via the camera and microphone on the device worn by the user.

[0343] Step 6:

[0344] The server processes the received user data using an emotion engine to analyze the user's emotional state. The analysis results are used to adjust warning messages.

[0345] Step 7:

[0346] The server optimizes the content and presentation of warning messages based on the user's emotional state. For example, it might change to a calmer warning sound or use gentler language in text messages.

[0347] Step 8:

[0348] The device will notify the user of a final warning message. It will prompt the user to take appropriate action through on-screen displays and audio output.

[0349] Step 9:

[0350] Users check warnings received from their devices and adjust their direction of travel and actions accordingly. This decision-making process ensures safe and comfortable travel.

[0351] (Example 2)

[0352] 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".

[0353] There is a need to provide a system that can generate warnings that take into account not only abnormal road conditions but also the user's emotional state when a moving object is in motion. This will reduce the tension and confusion caused by the uniform warnings of conventional warning systems, thereby improving safety and comfort.

[0354] 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.

[0355] In this invention, the server includes means for processing road surface image information to analyze road surface conditions, means for recognizing the user's emotional state and combining it with the analysis results, and means for detecting anomalies based on the analysis results and emotional state and generating warnings that take the user's emotions into consideration. This makes it possible for the user to receive safe and accurate warnings that are appropriate to their emotional state.

[0356] An "imaging device" is a device attached to a moving object to acquire image information of the surroundings.

[0357] "Road surface condition" refers to information indicating the surface conditions of the road, including characteristics such as unevenness, slope, and slipperiness.

[0358] "Emotion recognition" is a technology that analyzes a user's emotional state and identifies it through facial expressions and tone of voice.

[0359] A "convolutional neural network" is a method of artificial intelligence that automatically learns the spatial layers and features of input data to perform classification and interpretation.

[0360] A "warning message" is a notification that conveys information about anomalies or safety issues detected by the system to the user.

[0361] A "user terminal" is a device used by a user to receive warning messages, and typically refers to a mobile device or computer.

[0362] "Abnormal" refers to conditions that are different from the norm in terms of road surface conditions or user circumstances, and that require special attention.

[0363] This invention is a system that uses a digital device attached to a mobile body. The system has the following functions:

[0364] The terminal uses a digital imaging device to acquire real-time image information of the road surface in front of the moving object. The acquired images are processed to be clear through a noise reduction filter and then sent to a server for analysis.

[0365] The server analyzes the received image information using convolutional neural network (CNN) technology to evaluate the road surface conditions. During the analysis, meaningful data such as road surface irregularities, slipperiness, and slope are extracted, and anomalies are detected as needed.

[0366] Simultaneously, the server utilizes emotion recognition technology to analyze facial expression and voice data transmitted by the user. This allows it to identify the user's emotional state and evaluate the impact of those emotions on their attention and sense of security.

[0367] The server then integrates the road surface condition analysis results with the user's emotional state to generate a warning message. This message is sensitive to the user's emotions and is adjusted to be either mild or urgent. For example, a warning such as "Pay attention to the road surface ahead" will be delivered in a particularly calm tone if the user is feeling stressed.

[0368] Finally, the generated warning message is notified to the user through the device. The notification is made via a visual display or an auditory assistance device, allowing the user to confirm the safety of their path based on the warning content.

[0369] As a concrete example, a user-provided prompt might be something like, "Generate an appropriate warning message based on the road conditions during travel and the user's emotional state." This allows the AI ​​model to generate individual warning messages in response to the request.

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The terminal uses an imaging device to acquire image information of the road surface in front of a moving object. The input is an image acquired in real time, which is then passed through a noise reduction filter. During the noise reduction process, unnecessary data is reduced, and a clear image is generated. The output is image data in a state suitable for analysis.

[0373] Step 2:

[0374] The terminal sends the denoised image data to the server. The server analyzes the received image data using a convolutional neural network (CNN). The input to the analysis is the processed image data, and the output is information about the road surface conditions, such as features like steps, slipperiness, and slope. This analysis process utilizes GPU acceleration to achieve rapid processing.

[0375] Step 3:

[0376] The server processes camera images and audio data transmitted by the user. This data serves as input, and emotion recognition technology analyzes the user's facial expressions and voice. The output is the user's emotional state, including emotional characteristics such as reassurance, tension, and relaxation. This process utilizes facial expression analysis models and voice tone analysis models.

[0377] Step 4:

[0378] The server generates a warning message based on the analysis results of the road surface conditions and the user's emotional state. The input consists of both analysis results, and the AI ​​generation model determines the warning content based on this data. The output is an emotionally sensitive warning message, with the urgency level adjusted as needed. The AI ​​generation model creates the warning message using the prompt "Generate an appropriate warning message based on the road surface conditions and the user's emotional state during travel."

[0379] Step 5:

[0380] The terminal receives warning messages sent from the server and notifies the user. The input is the warning message, and the output is presented to the user in visual or auditory form. The terminal provides warnings to the user in an intuitively understandable way through screen displays or earphones, supporting the user in checking the safety of their path.

[0381] (Application Example 2)

[0382] 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."

[0383] The present invention aims to solve the problem of ensuring safety based on road surface conditions while providing appropriate warnings that correspond to the user's emotional state during the operation of a moving object. Conventional technologies were capable of detecting road surface conditions and generating warnings, but they did not take into account the user's emotional state, and the appropriateness of the warning content was sometimes lacking.

[0384] 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.

[0385] In this invention, the server includes means for acquiring road surface image information from an imaging device attached to a mobile vehicle, means for processing the road surface image information to analyze the road surface condition, and means for recognizing the user's emotional state and adjusting warnings based on that emotional state. This enables the provision of optimal warnings according to the user's emotional state, allowing for safe and comfortable travel.

[0386] A "mobile object" is a device that can physically change its position, such as a vehicle or a drone.

[0387] An "imaging device" is a device that detects light and generates image data, and is usually a camera.

[0388] "Image information" refers to visual data acquired by an imaging device, and is fundamental data for performing specific processing and analysis.

[0389] "Road surface condition" refers to the physical characteristics and state of the ground surface that a moving object comes into contact with or is affected by.

[0390] "Analysis means" refers to a device or method for analyzing acquired data according to specific criteria and extracting useful information.

[0391] An "anomaly" refers to a phenomenon or pattern that deviates from the normal state or expected standards.

[0392] A "warning" is a message or signal that notifies the user in advance of a potential danger or abnormal situation.

[0393] "Emotional state" refers to a user's mental or emotional condition, which is usually perceived through facial expressions and voice.

[0394] "Adjustment" refers to changing specific parameters or settings according to specific conditions or requirements.

[0395] A "terminal" is an electronic device used for inputting, receiving, and processing information.

[0396] In this invention, various devices and a server equipped on a mobile vehicle are used to detect road surface conditions and generate warnings based on the user's emotional state.

[0397] The server acquires real-time image information of the road surface from an imaging device attached to a mobile vehicle. A high-resolution camera can be used as this imaging device. The acquired image information is preprocessed appropriately to remove noise. Subsequently, the road surface condition is analyzed using a convolutional neural network (CNN). This analysis can extract information such as steps, slipperiness, and slope, and detect anomalies. Frameworks such as TensorFlow and PyTorch can be used to implement the CNN.

[0398] The server also incorporates an emotion recognition engine to recognize the user's emotional state. This engine captures the user's facial expressions with a camera and acquires their voice with a microphone, then evaluates their emotional state. Emotion recognition utilizes facial expression analysis and voice tone analysis. Therefore, facial recognition software and the Google Cloud Speech-to-Text API can be used.

[0399] Based on the analyzed road surface condition information and emotional state information, the server generates a warning message and sends it to the user's terminal. This warning message is adjusted to be either mild or urgent depending on the user's emotional state. By utilizing a generation AI model, it is possible to provide more natural and user-friendly messages.

[0400] For example, if the user is tense and the road ahead is slippery, the server will notify them in a calm tone with the message "Please pay attention ahead." On the other hand, if the user is relaxed, the server will use a visual display along with a normal warning sound to draw their attention.

[0401] An example of a prompt to input into the generation AI model is: "Generate the most appropriate warning message based on current road conditions and passenger sentiment."

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The server acquires real-time image information of the road surface from an imaging device mounted on a mobile vehicle. The input is image data captured by the imaging device, and the output is pre-processed road surface image information. In this processing, a noise reduction algorithm is applied to clear the image data and improve the accuracy of the analysis.

[0405] Step 2:

[0406] The server analyzes the road surface conditions using a convolutional neural network (CNN) on preprocessed image data. The input is denoised road surface image data, and the output is condition information such as road surface height, slipperiness, and slope. The CNN detects specific patterns and evaluates the possibility of anomalies.

[0407] Step 3:

[0408] The server acquires the user's facial expressions and voice from cameras and microphones installed inside the mobile device, and recognizes their emotional state using an emotion recognition engine. The input is the user's facial image and voice data, and the output is the user's emotional state (e.g., tense, anxious, relaxed). The emotional state is extracted by performing facial expression analysis and voice tone analysis.

[0409] Step 4:

[0410] The server generates warning messages based on analyzed road surface conditions and emotional states. The inputs are road surface condition information and emotional state information, and the output is a user-optimized warning message. In this step, a generation AI model is used to input prompts and generate a message with adjusted content.

[0411] Step 5:

[0412] The server notifies the user terminal of the generated warning message. The input is the generated warning message, and the output is the message displayed on the user terminal. The terminal presents this message to the user as an audio or visual instruction to support safe movement.

[0413] 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.

[0414] 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 those described above. 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 shown 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.

[0415] 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.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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".

[0429] This invention is a system for ensuring safety by monitoring road surface conditions in real time when users are moving in a wheelchair. This system has the following functions: imaging device, image processing, road surface analysis, anomaly detection, and warning notification.

[0430] The device is mounted on the wheelchair and uses an imaging device to periodically photograph the road surface in front of it. This makes it possible to accurately understand the road surface conditions at all times.

[0431] The terminal preprocesses the captured images and efficiently transmits the information to the server. A secure communication protocol is used during this process.

[0432] The receiving server uses advanced image analysis algorithms to analyze road surface conditions in real time. The analysis employs a convolutional neural network (CNN), enabling highly accurate anomaly detection.

[0433] The analysis results will record any hazards on the road surface as anomalies. Examples include the size of bumps or slippery areas that may be prone to freezing.

[0434] If an anomaly is detected, the server generates a warning message and notifies the terminal. This notification includes details about the type and location of the anomaly, enabling the user to take prompt action.

[0435] The device provides users with easily understandable warnings. For example, visual or audio warnings can be configured, allowing for information tailored to the user's needs.

[0436] This system allows wheelchair users to pay attention to their direction of travel, reducing the risk of falls and accidents. Specifically, it can detect icy surfaces and take evasive action, enabling safer movement.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] The device uses its camera to capture images of the road surface ahead at regular intervals. The acquired images are stored in temporary memory.

[0440] Step 2:

[0441] The device performs pre-processing on the captured image, including noise reduction and brightness adjustment. This process optimizes image quality and improves the accuracy of subsequent analysis.

[0442] Step 3:

[0443] The terminal compresses the pre-processed image data and sends it to the server. Data transmission is performed using a secure communication protocol.

[0444] Step 4:

[0445] The server performs analysis on the received image data using a convolutional neural network (CNN). This is used to evaluate factors such as road surface unevenness, slope, and slipperiness.

[0446] Step 5:

[0447] Based on the analysis results, the server determines whether there are any abnormalities in the road surface conditions. If an abnormality is detected, it generates warning information. This warning information includes the type of abnormality and its location.

[0448] Step 6:

[0449] The server sends the generated warning information to the terminal. The notification contains all the information necessary for subsequent user support.

[0450] Step 7:

[0451] The terminal displays warnings received from the server to the user. It uses on-screen warning messages and audio alerts to draw the user's attention.

[0452] Step 8:

[0453] The user checks the notification from their device and reconsiders their direction of travel. They should either change their course to avoid the anomaly or consider measures to continue moving cautiously.

[0454] (Example 1)

[0455] 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."

[0456] The aim is to solve the problem of increased risk of accidents and falls for wheelchair users who lack a way to accurately and in real time perceive road conditions while moving, especially in areas with unstable road surfaces or at times when visibility is poor.

[0457] 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.

[0458] In this invention, the server includes means for preprocessing road surface image information and transmitting it to an analysis device via data communication means, means for processing the image information using a convolutional neural network and analyzing the road surface condition, and means for detecting anomalies and generating warning information based on the analysis results. This enables wheelchair users to grasp the road surface condition in real time and obtain timely information to avoid danger.

[0459] A "mobile device" is a mechanical device that has the ability to move from one location to another.

[0460] An "imaging mechanism" is a device that acquires an image of an object using optical means.

[0461] "Image information" refers to information represented in digital or analog form that shows specific visual data.

[0462] "Preprocessing" refers to the initial data processing procedures performed to analyze data in a more appropriate format.

[0463] "Data communication means" refers to a method or device for sending and receiving digital data.

[0464] An "analysis device" is a mechanical device that automatically analyzes received data and generates meaningful information.

[0465] A "convolutional neural network" is a type of artificial intelligence that has a multi-layered structure and exhibits high performance, particularly in image recognition.

[0466] Anomaly detection is the process of recognizing phenomena or patterns that deviate from the normal state.

[0467] A "warning message" is a message containing detailed information to draw attention to a specific issue.

[0468] A "user device" is an electronic device that an individual operates and uses to receive information.

[0469] This invention provides technology to ensure user safety while moving, through a series of systems and programs mounted on a wheelchair, which is a mobile device. The main hardware involved is an imaging mechanism attached to the wheelchair, a data transfer terminal, and a server.

[0470] The terminal uses an imaging mechanism equipped with a high-resolution camera to periodically acquire image information of the road surface. This image information is pre-processed within the terminal, such as noise reduction and contrast adjustment, before being transmitted to the server via a secure protocol.

[0471] The server utilizes an advanced convolutional neural network (CNN) to process the received image information. The CNN is implemented using existing frameworks such as TensorFlow and accurately detects anomalies such as uneven road surfaces and slippery, icy areas. For detected anomalies, warning information is generated, including the type and location of the anomaly.

[0472] Users can receive the aforementioned warning information through the device's display or audio output. This output is provided as a visual or audio alert to help users move safely.

[0473] For example, if the terminal detects ice on the road surface, the server generates a warning such as "There is an icy area 30 meters ahead," and the terminal communicates this to the user via voice.

[0474] Examples of prompt statements that can be used as input to a generative AI model are as follows:

[0475] "Design a system that analyzes road conditions in real time and detects anomalies to ensure the safe movement of wheelchair users. This system will use imaging devices and CNNs to identify dangerous road conditions and notify the user."

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The device uses a high-resolution camera mounted on the wheelchair to periodically capture images of the road surface ahead. The camera captures images once per second, obtaining digital image data as input. Specifically, the camera automatically triggers the shutter, and the acquired image is saved to the device's memory.

[0479] Step 2:

[0480] The device preprocesses the captured image data. It applies noise reduction filters and contrast adjustments to the digital image data obtained as input, generating clear image data as output. Specifically, it uses the OpenCV library to adjust the brightness and contrast of the image.

[0481] Step 3:

[0482] The terminal needs to transfer pre-processed image data to the server. As input, it securely sends the pre-processed image data to the server using the HTTPS protocol, and as output, it obtains confirmation of receipt. Specifically, the image is compressed into JPEG format, encrypted, and then transmitted.

[0483] Step 4:

[0484] The server analyzes the received image data. It uses a convolutional neural network (CNN) to analyze the transmitted image data as input, and outputs the road surface condition analysis results. Specifically, the server utilizes the TensorFlow framework to execute the analysis model and detect anomalies.

[0485] Step 5:

[0486] The server detects anomalies based on the analysis results and generates warning information. Using the CNN analysis results as input, it generates a warning message that includes the type and location of the anomaly as output. Specifically, it generates a text message such as "There is a frozen area 30 meters ahead."

[0487] Step 6:

[0488] The server sends the generated warning message to the terminal. As input, it securely sends the generated warning information to the terminal using the HTTPS protocol, and as output, the terminal confirms receipt. Specifically, it converts the warning data into JSON format and sends it securely.

[0489] Step 7:

[0490] The terminal notifies the user of the received warning information. Based on the warning information received from the server as input, it provides warnings in the form of audio or visual output. Specifically, it displays "Caution: Slippery surface ahead" on the terminal's display and emits an audio warning from the speaker.

[0491] (Application Example 1)

[0492] 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."

[0493] Ensuring safety during the movement of automated guided vehicles (AGVs) within factories is a challenge. In particular, it is necessary to establish a system that can detect obstacles such as slippery surfaces and steps in real time and promptly notify warnings, thereby reducing the risk of accidents and enabling safe goods transport.

[0494] 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.

[0495] In this invention, the server includes means for acquiring image information of the ground surface from an imaging device attached to a moving object, means for processing the image information of the ground surface to analyze the ground surface conditions and evaluate the safety in the direction of travel of the moving object, and means for detecting abnormalities and generating warnings based on the analysis results. This makes it possible to achieve safe movement in real time and prevent accidents in factories.

[0496] "Mobile equipment" refers to mechanical devices that are movable for transporting goods, and in particular includes automated guided vehicles (AGVs) used in factories.

[0497] An "imaging device" is a device such as a high-resolution camera attached to a moving object, used to acquire image information of the Earth's surface.

[0498] "Ground surface image information" refers to image data acquired by an imaging device, representing the state of the ground surface.

[0499] The "analysis method" is a means for processing acquired image information of the ground surface and evaluating its condition, and it utilizes a convolutional neural network (CNN).

[0500] An "abnormality" refers to an obstacle on the ground surface that could hinder the movement of a moving object, and specifically includes slippery areas and uneven surfaces.

[0501] A "warning" is a message sent to the user's device when an anomaly is detected, and it includes the type of anomaly and location information.

[0502] The system for realizing this invention consists of an imaging device attached to a mobile body, a server connected to it, and a user terminal. The server acquires image information of the ground surface using the imaging device, which consists of a high-resolution camera. The acquired image information is securely transmitted to the server via a wireless communication protocol. Specifically, communication technologies such as MQTT can be used.

[0503] The server analyzes the received image information using a convolutional neural network (CNN). The CNN evaluates the condition of the ground surface and implements advanced image processing to enhance safety. If an anomaly is detected as a result of the analysis, the server generates a warning message and notifies the user terminal. This message includes the type and location of the anomaly, allowing the user to take prompt action.

[0504] The user's terminal provides the notified warning in an intuitively understandable format. For example, it can be displayed as a voice assistant or a visual warning on the display, allowing the user to take immediate action. As a concrete example, it can detect a floor that has become slippery due to rain and automatically limit the speed of the moving object, allowing for continued safe movement.

[0505] An example of a prompt for a generated AI model might be, "Design a system for the safe movement of automated guided vehicles within a factory and provide an AI model that enables high-precision analysis." This prompt would then design the AI ​​model to support real-time anomaly detection and warning generation.

[0506] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0507] Step 1:

[0508] The terminal periodically acquires image information of the ground surface using an imaging device mounted on the mobile device. The imaging interval can be adjusted according to the speed of the mobile device and environmental conditions. The input is the captured raw image data, and the output is an image file in digital format.

[0509] Step 2:

[0510] The terminal preprocesses the acquired image data. It compresses the data, reduces noise, and converts it into a format suitable for communication. This processing allows the image data to be efficiently transmitted to the server. The input is the image data acquired in step 1, and the output is the processed image data.

[0511] Step 3:

[0512] The terminal sends the pre-processed image data to the server. A secure communication protocol such as MQTT is used for this transmission. The input is the image data processed in step 2, and the output is the image data that has arrived at the server.

[0513] Step 4:

[0514] The server analyzes the received image data using a Convolutional Neural Network (CNN). CNN is a deep learning technique for accurately detecting anomalies on the ground surface (such as slippery areas or uneven surfaces). The input is the image data received by the server, and the output is the anomaly information resulting from the analysis.

[0515] Step 5:

[0516] The server generates a warning message based on the analysis results. This message, which includes the type and location of the anomaly, is designed to allow the receiving user to take prompt action. The input is the anomaly information obtained in step 4, and the output is the warning message.

[0517] Step 6:

[0518] The terminal receives warning messages from the server and notifies the user. This notification is made via audio or visual means, allowing the user to immediately recognize and take action. The input is the warning message sent from the server, and the output is the presentation of warning information to the user.

[0519] Step 7:

[0520] Based on the notified warning messages, the user adjusts the direction and speed of the moving object as needed. This action ensures real-time safety. The input is the warning information received from the terminal, and the output is the user's actions to achieve safe movement.

[0521] 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.

[0522] This invention relates to a system that uses a device attached to a moving object to understand road surface conditions and provide appropriate warnings according to the user's emotional state. This system comprises an imaging device, an image processing device, an emotion recognition engine, and a warning generation device.

[0523] The terminal first acquires an image of the road surface ahead using an imaging device while moving. This image is processed in real time, noise is removed, and then it is sent to the server.

[0524] The server uses a convolutional neural network (CNN) to analyze image data and evaluate road surface conditions. It acquires information such as steps, slipperiness, and slope, and detects anomalies.

[0525] Next, the server uses an emotion engine to recognize the user's emotional state from camera images and audio data. This process identifies the user's emotions using facial expression analysis and voice tone analysis.

[0526] Based on the analyzed road surface conditions and emotional state, the server generates appropriate warning messages. These warnings are tailored to the user's emotional state, using mild language or, in some cases, urgent language.

[0527] The final warning message is sent to the user via the device. The user can review the warning and use it to determine if it is safe to proceed.

[0528] For example, if a user is feeling tense and there is a slippery surface ahead, the emotion engine will recognize this and gently notify them with a message like, "Pay attention to the road surface ahead." Conversely, if the user is relaxed, it will use normal warning sounds and visual indicators to draw attention. This allows users to receive information tailored to their emotional state, enabling them to travel safely and comfortably.

[0529] The following describes the processing flow.

[0530] Step 1:

[0531] The device uses an imaging device attached to the wheelchair to capture images of the road surface ahead at regular intervals. This image data is temporarily stored on the device.

[0532] Step 2:

[0533] The terminal applies noise reduction processing to the saved images and adjusts them to a quality suitable for analysis. The adjusted image data is then compressed and sent to the server.

[0534] Step 3:

[0535] The server decompresses the received compressed image data and performs analysis using a convolutional neural network (CNN). This analysis detects road surface irregularities such as steps, slopes, and the possibility of freezing.

[0536] Step 4:

[0537] The server detects anomalies from the analysis results and generates a warning based on them. The generated warning information includes the type of anomaly and its location.

[0538] Step 5:

[0539] Data regarding the user's facial expressions and voice tone is transmitted to the server via the camera and microphone on the device worn by the user.

[0540] Step 6:

[0541] The server processes the received user data using an emotion engine to analyze the user's emotional state. The analysis results are used to adjust warning messages.

[0542] Step 7:

[0543] The server optimizes the content and presentation of warning messages based on the user's emotional state. For example, it might change to a calmer warning sound or use gentler language in text messages.

[0544] Step 8:

[0545] The device will notify the user of a final warning message. It will prompt the user to take appropriate action through on-screen displays and audio output.

[0546] Step 9:

[0547] Users check warnings received from their devices and adjust their direction of travel and actions accordingly. This decision-making process ensures safe and comfortable travel.

[0548] (Example 2)

[0549] 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."

[0550] There is a need to provide a system that can generate warnings that take into account not only abnormal road conditions but also the user's emotional state when a moving object is in motion. This will reduce the tension and confusion caused by the uniform warnings of conventional warning systems, thereby improving safety and comfort.

[0551] 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.

[0552] In this invention, the server includes means for processing road surface image information to analyze road surface conditions, means for recognizing the user's emotional state and combining it with the analysis results, and means for detecting anomalies based on the analysis results and emotional state and generating warnings that take the user's emotions into consideration. This makes it possible for the user to receive safe and accurate warnings that are appropriate to their emotional state.

[0553] An "imaging device" is a device attached to a moving object to acquire image information of the surroundings.

[0554] "Road surface condition" refers to information indicating the surface conditions of the road, including characteristics such as unevenness, slope, and slipperiness.

[0555] "Emotion recognition" is a technology that analyzes a user's emotional state and identifies it through facial expressions and tone of voice.

[0556] A "convolutional neural network" is a method of artificial intelligence that automatically learns the spatial layers and features of input data to perform classification and interpretation.

[0557] A "warning message" is a notification that conveys information about anomalies or safety issues detected by the system to the user.

[0558] A "user terminal" is a device used by a user to receive warning messages, and typically refers to a mobile device or computer.

[0559] "Abnormal" refers to conditions that are different from the norm in terms of road surface conditions or user circumstances, and that require special attention.

[0560] This invention is a system that uses a digital device attached to a mobile body. The system has the following functions:

[0561] The terminal uses a digital imaging device to acquire real-time image information of the road surface in front of the moving object. The acquired images are processed to be clear through a noise reduction filter and then sent to a server for analysis.

[0562] The server analyzes the received image information using convolutional neural network (CNN) technology to evaluate the road surface conditions. During the analysis, meaningful data such as road surface irregularities, slipperiness, and slope are extracted, and anomalies are detected as needed.

[0563] Simultaneously, the server utilizes emotion recognition technology to analyze facial expression and voice data transmitted by the user. This allows it to identify the user's emotional state and evaluate the impact of those emotions on their attention and sense of security.

[0564] The server then integrates the road surface condition analysis results with the user's emotional state to generate a warning message. This message is sensitive to the user's emotions and is adjusted to be either mild or urgent. For example, a warning such as "Pay attention to the road surface ahead" will be delivered in a particularly calm tone if the user is feeling stressed.

[0565] Finally, the generated warning message is notified to the user through the device. The notification is made via a visual display or an auditory assistance device, allowing the user to confirm the safety of their path based on the warning content.

[0566] As a concrete example, a user-provided prompt might be something like, "Generate an appropriate warning message based on the road conditions during travel and the user's emotional state." This allows the AI ​​model to generate individual warning messages in response to the request.

[0567] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0568] Step 1:

[0569] The terminal uses an imaging device to acquire image information of the road surface in front of a moving object. The input is an image acquired in real time, which is then passed through a noise reduction filter. During the noise reduction process, unnecessary data is reduced, and a clear image is generated. The output is image data in a state suitable for analysis.

[0570] Step 2:

[0571] The terminal sends the denoised image data to the server. The server analyzes the received image data using a convolutional neural network (CNN). The input to the analysis is the processed image data, and the output is information about the road surface conditions, such as features like steps, slipperiness, and slope. This analysis process utilizes GPU acceleration to achieve rapid processing.

[0572] Step 3:

[0573] The server processes camera images and audio data transmitted by the user. This data serves as input, and emotion recognition technology analyzes the user's facial expressions and voice. The output is the user's emotional state, including emotional characteristics such as reassurance, tension, and relaxation. This process utilizes facial expression analysis models and voice tone analysis models.

[0574] Step 4:

[0575] The server generates a warning message based on the analysis results of the road surface conditions and the user's emotional state. The input consists of both analysis results, and the AI ​​generation model determines the warning content based on this data. The output is an emotionally sensitive warning message, with the urgency level adjusted as needed. The AI ​​generation model creates the warning message using the prompt "Generate an appropriate warning message based on the road surface conditions and the user's emotional state during travel."

[0576] Step 5:

[0577] The terminal receives warning messages sent from the server and notifies the user. The input is the warning message, and the output is presented to the user in visual or auditory form. The terminal provides warnings to the user in an intuitively understandable way through screen displays or earphones, supporting the user in checking the safety of their path.

[0578] (Application Example 2)

[0579] 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."

[0580] The present invention aims to solve the problem of ensuring safety based on road surface conditions while providing appropriate warnings that correspond to the user's emotional state during the operation of a moving object. Conventional technologies were capable of detecting road surface conditions and generating warnings, but they did not take into account the user's emotional state, and the appropriateness of the warning content was sometimes lacking.

[0581] 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.

[0582] In this invention, the server includes means for acquiring road surface image information from an imaging device attached to a mobile vehicle, means for processing the road surface image information to analyze the road surface condition, and means for recognizing the user's emotional state and adjusting warnings based on that emotional state. This enables the provision of optimal warnings according to the user's emotional state, allowing for safe and comfortable travel.

[0583] A "mobile object" is a device that can physically change its position, such as a vehicle or a drone.

[0584] An "imaging device" is a device that detects light and generates image data, and is usually a camera.

[0585] "Image information" refers to visual data acquired by an imaging device, and is fundamental data for performing specific processing and analysis.

[0586] "Road surface condition" refers to the physical characteristics and state of the ground surface that a moving object comes into contact with or is affected by.

[0587] "Analysis means" refers to a device or method for analyzing acquired data according to specific criteria and extracting useful information.

[0588] An "anomaly" refers to a phenomenon or pattern that deviates from the normal state or expected standards.

[0589] A "warning" is a message or signal that notifies the user in advance of a potential danger or abnormal situation.

[0590] "Emotional state" refers to a user's mental or emotional condition, which is usually perceived through facial expressions and voice.

[0591] "Adjustment" refers to changing specific parameters or settings according to specific conditions or requirements.

[0592] A "terminal" is an electronic device used for inputting, receiving, and processing information.

[0593] In this invention, various devices and a server equipped on a mobile vehicle are used to detect road surface conditions and generate warnings based on the user's emotional state.

[0594] The server acquires real-time image information of the road surface from an imaging device attached to a mobile vehicle. A high-resolution camera can be used as this imaging device. The acquired image information is preprocessed appropriately to remove noise. Subsequently, the road surface condition is analyzed using a convolutional neural network (CNN). This analysis can extract information such as steps, slipperiness, and slope, and detect anomalies. Frameworks such as TensorFlow and PyTorch can be used to implement the CNN.

[0595] The server also incorporates an emotion recognition engine to recognize the user's emotional state. This engine captures the user's facial expressions with a camera and acquires their voice with a microphone, then evaluates their emotional state. Emotion recognition utilizes facial expression analysis and voice tone analysis. Therefore, facial recognition software and the Google Cloud Speech-to-Text API can be used.

[0596] Based on the analyzed road surface condition information and emotional state information, the server generates a warning message and sends it to the user's terminal. This warning message is adjusted to be either mild or urgent depending on the user's emotional state. By utilizing a generation AI model, it is possible to provide more natural and user-friendly messages.

[0597] For example, if the user is tense and the road ahead is slippery, the server will notify them in a calm tone with the message "Please pay attention ahead." On the other hand, if the user is relaxed, the server will use a visual display along with a normal warning sound to draw their attention.

[0598] An example of a prompt to input into the generation AI model is: "Generate the most appropriate warning message based on current road conditions and passenger sentiment."

[0599] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0600] Step 1:

[0601] The server acquires real-time image information of the road surface from an imaging device mounted on a mobile vehicle. The input is image data captured by the imaging device, and the output is pre-processed road surface image information. In this processing, a noise reduction algorithm is applied to clear the image data and improve the accuracy of the analysis.

[0602] Step 2:

[0603] The server analyzes the road surface conditions using a convolutional neural network (CNN) on preprocessed image data. The input is denoised road surface image data, and the output is condition information such as road surface height, slipperiness, and slope. The CNN detects specific patterns and evaluates the possibility of anomalies.

[0604] Step 3:

[0605] The server acquires the user's facial expressions and voice from cameras and microphones installed inside the mobile device, and recognizes their emotional state using an emotion recognition engine. The input is the user's facial image and voice data, and the output is the user's emotional state (e.g., tense, anxious, relaxed). The emotional state is extracted by performing facial expression analysis and voice tone analysis.

[0606] Step 4:

[0607] The server generates warning messages based on analyzed road surface conditions and emotional states. The inputs are road surface condition information and emotional state information, and the output is a user-optimized warning message. In this step, a generation AI model is used to input prompts and generate a message with adjusted content.

[0608] Step 5:

[0609] The server notifies the user terminal of the generated warning message. The input is the generated warning message, and the output is the message displayed on the user terminal. The terminal presents this message to the user as an audio or visual instruction to support safe movement.

[0610] 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.

[0611] 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 those described above. 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 shown 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.

[0612] 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.

[0613] [Fourth Embodiment]

[0614] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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".

[0627] This invention is a system for ensuring safety by monitoring road surface conditions in real time when users are moving in a wheelchair. This system has the following functions: imaging device, image processing, road surface analysis, anomaly detection, and warning notification.

[0628] The device is mounted on the wheelchair and uses an imaging device to periodically photograph the road surface in front of it. This makes it possible to accurately understand the road surface conditions at all times.

[0629] The terminal preprocesses the captured images and efficiently transmits the information to the server. A secure communication protocol is used during this process.

[0630] The receiving server uses advanced image analysis algorithms to analyze road surface conditions in real time. The analysis employs a convolutional neural network (CNN), enabling highly accurate anomaly detection.

[0631] The analysis results will record any hazards on the road surface as anomalies. Examples include the size of bumps or slippery areas that may be prone to freezing.

[0632] If an anomaly is detected, the server generates a warning message and notifies the terminal. This notification includes details about the type and location of the anomaly, enabling the user to take prompt action.

[0633] The device provides users with easily understandable warnings. For example, visual or audio warnings can be configured, allowing for information tailored to the user's needs.

[0634] This system allows wheelchair users to pay attention to their direction of travel, reducing the risk of falls and accidents. Specifically, it can detect icy surfaces and take evasive action, enabling safer movement.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The device uses its camera to capture images of the road surface ahead at regular intervals. The acquired images are stored in temporary memory.

[0638] Step 2:

[0639] The device performs pre-processing on the captured image, including noise reduction and brightness adjustment. This process optimizes image quality and improves the accuracy of subsequent analysis.

[0640] Step 3:

[0641] The terminal compresses the pre-processed image data and sends it to the server. Data transmission is performed using a secure communication protocol.

[0642] Step 4:

[0643] The server performs analysis on the received image data using a convolutional neural network (CNN). This is used to evaluate factors such as road surface unevenness, slope, and slipperiness.

[0644] Step 5:

[0645] Based on the analysis results, the server determines whether there are any abnormalities in the road surface conditions. If an abnormality is detected, it generates warning information. This warning information includes the type of abnormality and its location.

[0646] Step 6:

[0647] The server sends the generated warning information to the terminal. The notification contains all the information necessary for subsequent user support.

[0648] Step 7:

[0649] The terminal displays warnings received from the server to the user. It uses on-screen warning messages and audio alerts to draw the user's attention.

[0650] Step 8:

[0651] The user checks the notification from their device and reconsiders their direction of travel. They should either change their course to avoid the anomaly or consider measures to continue moving cautiously.

[0652] (Example 1)

[0653] 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".

[0654] The aim is to solve the problem of increased risk of accidents and falls for wheelchair users who lack a way to accurately and in real time perceive road conditions while moving, especially in areas with unstable road surfaces or at times when visibility is poor.

[0655] 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.

[0656] In this invention, the server includes means for preprocessing road surface image information and transmitting it to an analysis device via data communication means, means for processing the image information using a convolutional neural network and analyzing the road surface condition, and means for detecting anomalies and generating warning information based on the analysis results. This enables wheelchair users to grasp the road surface condition in real time and obtain timely information to avoid danger.

[0657] A "mobile device" is a mechanical device that has the ability to move from one location to another.

[0658] An "imaging mechanism" is a device that acquires an image of an object using optical means.

[0659] "Image information" refers to information represented in digital or analog form that shows specific visual data.

[0660] "Preprocessing" refers to the initial data processing procedures performed to analyze data in a more appropriate format.

[0661] "Data communication means" refers to a method or device for sending and receiving digital data.

[0662] An "analysis device" is a mechanical device that automatically analyzes received data and generates meaningful information.

[0663] A "convolutional neural network" is a type of artificial intelligence that has a multi-layered structure and exhibits high performance, particularly in image recognition.

[0664] Anomaly detection is the process of recognizing phenomena or patterns that deviate from the normal state.

[0665] A "warning message" is a message containing detailed information to draw attention to a specific issue.

[0666] A "user device" is an electronic device that an individual operates and uses to receive information.

[0667] This invention provides technology to ensure user safety while moving, through a series of systems and programs mounted on a wheelchair, which is a mobile device. The main hardware involved is an imaging mechanism attached to the wheelchair, a data transfer terminal, and a server.

[0668] The terminal uses an imaging mechanism equipped with a high-resolution camera to periodically acquire image information of the road surface. This image information is pre-processed within the terminal, such as noise reduction and contrast adjustment, before being transmitted to the server via a secure protocol.

[0669] The server utilizes an advanced convolutional neural network (CNN) to process the received image information. The CNN is implemented using existing frameworks such as TensorFlow and accurately detects anomalies such as uneven road surfaces and slippery, icy areas. For detected anomalies, warning information is generated, including the type and location of the anomaly.

[0670] Users can receive the aforementioned warning information through the device's display or audio output. This output is provided as a visual or audio alert to help users move safely.

[0671] For example, if the terminal detects ice on the road surface, the server generates a warning such as "There is an icy area 30 meters ahead," and the terminal communicates this to the user via voice.

[0672] Examples of prompt statements that can be used as input to a generative AI model are as follows:

[0673] "Design a system that analyzes road conditions in real time and detects anomalies to ensure the safe movement of wheelchair users. This system will use imaging devices and CNNs to identify dangerous road conditions and notify the user."

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The device uses a high-resolution camera mounted on the wheelchair to periodically capture images of the road surface ahead. The camera captures images once per second, obtaining digital image data as input. Specifically, the camera automatically triggers the shutter, and the acquired image is saved to the device's memory.

[0677] Step 2:

[0678] The device preprocesses the captured image data. It applies noise reduction filters and contrast adjustments to the digital image data obtained as input, generating clear image data as output. Specifically, it uses the OpenCV library to adjust the brightness and contrast of the image.

[0679] Step 3:

[0680] The terminal needs to transfer pre-processed image data to the server. As input, it securely sends the pre-processed image data to the server using the HTTPS protocol, and as output, it obtains confirmation of receipt. Specifically, the image is compressed into JPEG format, encrypted, and then transmitted.

[0681] Step 4:

[0682] The server analyzes the received image data. It uses a convolutional neural network (CNN) to analyze the transmitted image data as input, and outputs the road surface condition analysis results. Specifically, the server utilizes the TensorFlow framework to execute the analysis model and detect anomalies.

[0683] Step 5:

[0684] The server detects anomalies based on the analysis results and generates warning information. Using the CNN analysis results as input, it generates a warning message that includes the type and location of the anomaly as output. Specifically, it generates a text message such as "There is a frozen area 30 meters ahead."

[0685] Step 6:

[0686] The server sends the generated warning message to the terminal. As input, it securely sends the generated warning information to the terminal using the HTTPS protocol, and as output, the terminal confirms receipt. Specifically, it converts the warning data into JSON format and sends it securely.

[0687] Step 7:

[0688] The terminal notifies the user of the received warning information. Based on the warning information received from the server as input, it provides warnings in the form of audio or visual output. Specifically, it displays "Caution: Slippery surface ahead" on the terminal's display and emits an audio warning from the speaker.

[0689] (Application Example 1)

[0690] 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".

[0691] Ensuring safety during the movement of automated guided vehicles (AGVs) within factories is a challenge. In particular, it is necessary to establish a system that can detect obstacles such as slippery surfaces and steps in real time and promptly notify warnings, thereby reducing the risk of accidents and enabling safe goods transport.

[0692] 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.

[0693] In this invention, the server includes means for acquiring image information of the ground surface from an imaging device attached to a moving object, means for processing the image information of the ground surface to analyze the ground surface conditions and evaluate the safety in the direction of travel of the moving object, and means for detecting abnormalities and generating warnings based on the analysis results. This makes it possible to achieve safe movement in real time and prevent accidents in factories.

[0694] "Mobile equipment" refers to mechanical devices that are movable for transporting goods, and in particular includes automated guided vehicles (AGVs) used in factories.

[0695] An "imaging device" is a device such as a high-resolution camera attached to a moving object, used to acquire image information of the Earth's surface.

[0696] "Ground surface image information" refers to image data acquired by an imaging device, representing the state of the ground surface.

[0697] The "analysis method" is a means for processing acquired image information of the ground surface and evaluating its condition, and it utilizes a convolutional neural network (CNN).

[0698] An "abnormality" refers to an obstacle on the ground surface that could hinder the movement of a moving object, and specifically includes slippery areas and uneven surfaces.

[0699] A "warning" is a message sent to the user's device when an anomaly is detected, and it includes the type of anomaly and location information.

[0700] The system for realizing this invention consists of an imaging device attached to a mobile body, a server connected to it, and a user terminal. The server acquires image information of the ground surface using the imaging device, which consists of a high-resolution camera. The acquired image information is securely transmitted to the server via a wireless communication protocol. Specifically, communication technologies such as MQTT can be used.

[0701] The server analyzes the received image information using a convolutional neural network (CNN). The CNN evaluates the condition of the ground surface and implements advanced image processing to enhance safety. If an anomaly is detected as a result of the analysis, the server generates a warning message and notifies the user terminal. This message includes the type and location of the anomaly, allowing the user to take prompt action.

[0702] The user's terminal provides the notified warning in an intuitively understandable format. For example, it can be displayed as a voice assistant or a visual warning on the display, allowing the user to take immediate action. As a concrete example, it can detect a floor that has become slippery due to rain and automatically limit the speed of the moving object, allowing for continued safe movement.

[0703] An example of a prompt for a generated AI model might be, "Design a system for the safe movement of automated guided vehicles within a factory and provide an AI model that enables high-precision analysis." This prompt would then design the AI ​​model to support real-time anomaly detection and warning generation.

[0704] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0705] Step 1:

[0706] The terminal periodically acquires image information of the ground surface using an imaging device mounted on the mobile device. The imaging interval can be adjusted according to the speed of the mobile device and environmental conditions. The input is the captured raw image data, and the output is an image file in digital format.

[0707] Step 2:

[0708] The terminal preprocesses the acquired image data. It compresses the data, reduces noise, and converts it into a format suitable for communication. This processing allows the image data to be efficiently transmitted to the server. The input is the image data acquired in step 1, and the output is the processed image data.

[0709] Step 3:

[0710] The terminal sends the pre-processed image data to the server. A secure communication protocol such as MQTT is used for this transmission. The input is the image data processed in step 2, and the output is the image data that has arrived at the server.

[0711] Step 4:

[0712] The server analyzes the received image data using a Convolutional Neural Network (CNN). CNN is a deep learning technique for accurately detecting anomalies on the ground surface (such as slippery areas or uneven surfaces). The input is the image data received by the server, and the output is the anomaly information resulting from the analysis.

[0713] Step 5:

[0714] The server generates a warning message based on the analysis results. This message, which includes the type and location of the anomaly, is designed to allow the receiving user to take prompt action. The input is the anomaly information obtained in step 4, and the output is the warning message.

[0715] Step 6:

[0716] The terminal receives warning messages from the server and notifies the user. This notification is made via audio or visual means, allowing the user to immediately recognize and take action. The input is the warning message sent from the server, and the output is the presentation of warning information to the user.

[0717] Step 7:

[0718] Based on the notified warning messages, the user adjusts the direction and speed of the moving object as needed. This action ensures real-time safety. The input is the warning information received from the terminal, and the output is the user's actions to achieve safe movement.

[0719] 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.

[0720] This invention relates to a system that uses a device attached to a moving object to understand road surface conditions and provide appropriate warnings according to the user's emotional state. This system comprises an imaging device, an image processing device, an emotion recognition engine, and a warning generation device.

[0721] The terminal first acquires an image of the road surface ahead using an imaging device while moving. This image is processed in real time, noise is removed, and then it is sent to the server.

[0722] The server uses a convolutional neural network (CNN) to analyze image data and evaluate road surface conditions. It acquires information such as steps, slipperiness, and slope, and detects anomalies.

[0723] Next, the server uses an emotion engine to recognize the user's emotional state from camera images and audio data. This process identifies the user's emotions using facial expression analysis and voice tone analysis.

[0724] Based on the analyzed road surface conditions and emotional state, the server generates appropriate warning messages. These warnings are tailored to the user's emotional state, using mild language or, in some cases, urgent language.

[0725] The final warning message is sent to the user via the device. The user can review the warning and use it to determine if it is safe to proceed.

[0726] For example, if a user is feeling tense and there is a slippery surface ahead, the emotion engine will recognize this and gently notify them with a message like, "Pay attention to the road surface ahead." Conversely, if the user is relaxed, it will use normal warning sounds and visual indicators to draw attention. This allows users to receive information tailored to their emotional state, enabling them to travel safely and comfortably.

[0727] The following describes the processing flow.

[0728] Step 1:

[0729] The device uses an imaging device attached to the wheelchair to capture images of the road surface ahead at regular intervals. This image data is temporarily stored on the device.

[0730] Step 2:

[0731] The terminal applies noise reduction processing to the saved images and adjusts them to a quality suitable for analysis. The adjusted image data is then compressed and sent to the server.

[0732] Step 3:

[0733] The server decompresses the received compressed image data and performs analysis using a convolutional neural network (CNN). This analysis detects road surface irregularities such as steps, slopes, and the possibility of freezing.

[0734] Step 4:

[0735] The server detects anomalies from the analysis results and generates a warning based on them. The generated warning information includes the type of anomaly and its location.

[0736] Step 5:

[0737] Data regarding the user's facial expressions and voice tone is transmitted to the server via the camera and microphone on the device worn by the user.

[0738] Step 6:

[0739] The server processes the received user data using an emotion engine to analyze the user's emotional state. The analysis results are used to adjust warning messages.

[0740] Step 7:

[0741] The server optimizes the content and presentation of warning messages based on the user's emotional state. For example, it might change to a calmer warning sound or use gentler language in text messages.

[0742] Step 8:

[0743] The device will notify the user of a final warning message. It will prompt the user to take appropriate action through on-screen displays and audio output.

[0744] Step 9:

[0745] Users check warnings received from their devices and adjust their direction of travel and actions accordingly. This decision-making process ensures safe and comfortable travel.

[0746] (Example 2)

[0747] 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".

[0748] There is a need to provide a system that can generate warnings that take into account not only abnormal road conditions but also the user's emotional state when a moving object is in motion. This will reduce the tension and confusion caused by the uniform warnings of conventional warning systems, thereby improving safety and comfort.

[0749] 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.

[0750] In this invention, the server includes means for processing road surface image information to analyze road surface conditions, means for recognizing the user's emotional state and combining it with the analysis results, and means for detecting anomalies based on the analysis results and emotional state and generating warnings that take the user's emotions into consideration. This makes it possible for the user to receive safe and accurate warnings that are appropriate to their emotional state.

[0751] An "imaging device" is a device attached to a moving object to acquire image information of the surroundings.

[0752] "Road surface condition" refers to information indicating the surface conditions of the road, including characteristics such as unevenness, slope, and slipperiness.

[0753] "Emotion recognition" is a technology that analyzes a user's emotional state and identifies it through facial expressions and tone of voice.

[0754] A "convolutional neural network" is a method of artificial intelligence that automatically learns the spatial layers and features of input data to perform classification and interpretation.

[0755] A "warning message" is a notification that conveys information about anomalies or safety issues detected by the system to the user.

[0756] A "user terminal" is a device used by a user to receive warning messages, and typically refers to a mobile device or computer.

[0757] "Abnormal" refers to conditions that are different from the norm in terms of road surface conditions or user circumstances, and that require special attention.

[0758] This invention is a system that uses a digital device attached to a mobile body. The system has the following functions:

[0759] The terminal uses a digital imaging device to acquire real-time image information of the road surface in front of the moving object. The acquired images are processed to be clear through a noise reduction filter and then sent to a server for analysis.

[0760] The server analyzes the received image information using convolutional neural network (CNN) technology to evaluate the road surface conditions. During the analysis, meaningful data such as road surface irregularities, slipperiness, and slope are extracted, and anomalies are detected as needed.

[0761] Simultaneously, the server utilizes emotion recognition technology to analyze facial expression and voice data transmitted by the user. This allows it to identify the user's emotional state and evaluate the impact of those emotions on their attention and sense of security.

[0762] The server then integrates the road surface condition analysis results with the user's emotional state to generate a warning message. This message is sensitive to the user's emotions and is adjusted to be either mild or urgent. For example, a warning such as "Pay attention to the road surface ahead" will be delivered in a particularly calm tone if the user is feeling stressed.

[0763] Finally, the generated warning message is notified to the user through the device. The notification is made via a visual display or an auditory assistance device, allowing the user to confirm the safety of their path based on the warning content.

[0764] As a concrete example, a user-provided prompt might be something like, "Generate an appropriate warning message based on the road conditions during travel and the user's emotional state." This allows the AI ​​model to generate individual warning messages in response to the request.

[0765] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0766] Step 1:

[0767] The terminal uses an imaging device to acquire image information of the road surface in front of a moving object. The input is an image acquired in real time, which is then passed through a noise reduction filter. During the noise reduction process, unnecessary data is reduced, and a clear image is generated. The output is image data in a state suitable for analysis.

[0768] Step 2:

[0769] The terminal sends the denoised image data to the server. The server analyzes the received image data using a convolutional neural network (CNN). The input to the analysis is the processed image data, and the output is information about the road surface conditions, such as features like steps, slipperiness, and slope. This analysis process utilizes GPU acceleration to achieve rapid processing.

[0770] Step 3:

[0771] The server processes camera images and audio data transmitted by the user. This data serves as input, and emotion recognition technology analyzes the user's facial expressions and voice. The output is the user's emotional state, including emotional characteristics such as reassurance, tension, and relaxation. This process utilizes facial expression analysis models and voice tone analysis models.

[0772] Step 4:

[0773] The server generates a warning message based on the analysis results of the road surface conditions and the user's emotional state. The input consists of both analysis results, and the AI ​​generation model determines the warning content based on this data. The output is an emotionally sensitive warning message, with the urgency level adjusted as needed. The AI ​​generation model creates the warning message using the prompt "Generate an appropriate warning message based on the road surface conditions and the user's emotional state during travel."

[0774] Step 5:

[0775] The terminal receives warning messages sent from the server and notifies the user. The input is the warning message, and the output is presented to the user in visual or auditory form. The terminal provides warnings to the user in an intuitively understandable way through screen displays or earphones, supporting the user in checking the safety of their path.

[0776] (Application Example 2)

[0777] 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".

[0778] The present invention aims to solve the problem of ensuring safety based on road surface conditions while providing appropriate warnings that correspond to the user's emotional state during the operation of a moving object. Conventional technologies were capable of detecting road surface conditions and generating warnings, but they did not take into account the user's emotional state, and the appropriateness of the warning content was sometimes lacking.

[0779] 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.

[0780] In this invention, the server includes means for acquiring road surface image information from an imaging device attached to a mobile vehicle, means for processing the road surface image information to analyze the road surface condition, and means for recognizing the user's emotional state and adjusting warnings based on that emotional state. This enables the provision of optimal warnings according to the user's emotional state, allowing for safe and comfortable travel.

[0781] A "mobile object" is a device that can physically change its position, such as a vehicle or a drone.

[0782] An "imaging device" is a device that detects light and generates image data, and is usually a camera.

[0783] "Image information" refers to visual data acquired by an imaging device, and is fundamental data for performing specific processing and analysis.

[0784] "Road surface condition" refers to the physical characteristics and state of the ground surface that a moving object comes into contact with or is affected by.

[0785] "Analysis means" refers to a device or method for analyzing acquired data according to specific criteria and extracting useful information.

[0786] An "anomaly" refers to a phenomenon or pattern that deviates from the normal state or expected standards.

[0787] A "warning" is a message or signal that notifies the user in advance of a potential danger or abnormal situation.

[0788] "Emotional state" refers to a user's mental or emotional condition, which is usually perceived through facial expressions and voice.

[0789] "Adjustment" refers to changing specific parameters or settings according to specific conditions or requirements.

[0790] A "terminal" is an electronic device used for inputting, receiving, and processing information.

[0791] In this invention, various devices and a server equipped on a mobile vehicle are used to detect road surface conditions and generate warnings based on the user's emotional state.

[0792] The server acquires real-time image information of the road surface from an imaging device attached to a mobile vehicle. A high-resolution camera can be used as this imaging device. The acquired image information is preprocessed appropriately to remove noise. Subsequently, the road surface condition is analyzed using a convolutional neural network (CNN). This analysis can extract information such as steps, slipperiness, and slope, and detect anomalies. Frameworks such as TensorFlow and PyTorch can be used to implement the CNN.

[0793] The server also incorporates an emotion recognition engine to recognize the user's emotional state. This engine captures the user's facial expressions with a camera and acquires their voice with a microphone, then evaluates their emotional state. Emotion recognition utilizes facial expression analysis and voice tone analysis. Therefore, facial recognition software and the Google Cloud Speech-to-Text API can be used.

[0794] Based on the analyzed road surface condition information and emotional state information, the server generates a warning message and sends it to the user's terminal. This warning message is adjusted to be either mild or urgent depending on the user's emotional state. By utilizing a generation AI model, it is possible to provide more natural and user-friendly messages.

[0795] For example, if the user is tense and the road ahead is slippery, the server will notify them in a calm tone with the message "Please pay attention ahead." On the other hand, if the user is relaxed, the server will use a visual display along with a normal warning sound to draw their attention.

[0796] An example of a prompt to input into the generation AI model is: "Generate the most appropriate warning message based on current road conditions and passenger sentiment."

[0797] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0798] Step 1:

[0799] The server acquires real-time image information of the road surface from an imaging device mounted on a mobile vehicle. The input is image data captured by the imaging device, and the output is pre-processed road surface image information. In this processing, a noise reduction algorithm is applied to clear the image data and improve the accuracy of the analysis.

[0800] Step 2:

[0801] The server analyzes the road surface conditions using a convolutional neural network (CNN) on preprocessed image data. The input is denoised road surface image data, and the output is condition information such as road surface height, slipperiness, and slope. The CNN detects specific patterns and evaluates the possibility of anomalies.

[0802] Step 3:

[0803] The server acquires the user's facial expressions and voice from cameras and microphones installed inside the mobile device, and recognizes their emotional state using an emotion recognition engine. The input is the user's facial image and voice data, and the output is the user's emotional state (e.g., tense, anxious, relaxed). The emotional state is extracted by performing facial expression analysis and voice tone analysis.

[0804] Step 4:

[0805] The server generates warning messages based on analyzed road surface conditions and emotional states. The inputs are road surface condition information and emotional state information, and the output is a user-optimized warning message. In this step, a generation AI model is used to input prompts and generate a message with adjusted content.

[0806] Step 5:

[0807] The server notifies the user terminal of the generated warning message. The input is the generated warning message, and the output is the message displayed on the user terminal. The terminal presents this message to the user as an audio or visual instruction to support safe movement.

[0808] 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.

[0809] 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 those described above. 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 shown 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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."

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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 to be incorporated by reference.

[0829] The following is further disclosed regarding the embodiments described above.

[0830] (Claim 1)

[0831] A means for acquiring road surface image information from an imaging device attached to a mobile body,

[0832] Means for processing the aforementioned road surface image information to analyze the road surface condition,

[0833] A means for detecting an anomaly and generating a warning based on the aforementioned analysis results,

[0834] A means for notifying the user terminal of the aforementioned warning,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, wherein the analysis means evaluates the road surface condition using a convolutional neural network.

[0838] (Claim 3)

[0839] The system according to claim 1, wherein the notification means generates a warning message including the type of anomaly and location information.

[0840] "Example 1"

[0841] (Claim 1)

[0842] A means for acquiring road surface image information from an imaging mechanism attached to a mobile device,

[0843] A means for preprocessing the road surface image information and transmitting it to an analysis device via data communication means,

[0844] The aforementioned analysis device includes means for processing image information using a convolutional neural network to analyze the road surface condition,

[0845] A means for detecting anomalies based on the aforementioned analysis results and generating warning information,

[0846] Means for notifying the user device of the aforementioned warning information and providing the warning by displaying or audibly,

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, wherein the preprocessing means performs image noise reduction and contrast adjustment.

[0850] (Claim 3)

[0851] The system according to claim 1, wherein the communication means transfers data using a secure protocol.

[0852] "Application Example 1"

[0853] (Claim 1)

[0854] A means for acquiring image information of the Earth's surface from an imaging device attached to a mobile body,

[0855] A means for processing the image information of the ground surface to analyze the ground surface condition and evaluate the safety of the moving object in the direction of travel,

[0856] A means for detecting an anomaly and generating a warning based on the aforementioned analysis results,

[0857] Means for notifying the user terminal of the aforementioned warning and controlling or adjusting the operation of the mobile device,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, wherein the analysis means performs an advanced evaluation of the ground surface conditions using a convolutional neural network to realize safe movement.

[0861] (Claim 3)

[0862] The system according to claim 1, wherein the notification means generates a warning message including safety measures based on the type of anomaly and its location information, and supports real-time operational adjustment of the mobile body.

[0863] "Example 2 of combining an emotion engine"

[0864] (Claim 1)

[0865] A means for acquiring road surface image information from an imaging device attached to a mobile body,

[0866] Means for processing the aforementioned road surface image information to analyze the road surface condition,

[0867] A means for recognizing the user's emotional state and combining it with the analysis results,

[0868] A means for detecting anomalies based on the aforementioned analysis results and emotional state, and for generating warnings that take the user's emotions into consideration,

[0869] A means for notifying the user terminal of the aforementioned warning,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, wherein the analysis means uses a convolutional neural network to evaluate the road surface condition and employs emotion recognition technology to analyze facial expressions and voice.

[0873] (Claim 3)

[0874] The system according to claim 1, wherein the notification means generates a tailored warning message based on the type and location information of the anomaly and the user's emotions.

[0875] "Application example 2 when combining with an emotional engine"

[0876] (Claim 1)

[0877] A means for acquiring road surface image information from an imaging device attached to a mobile body,

[0878] Means for processing the aforementioned road surface image information to analyze the road surface condition,

[0879] A means for detecting an anomaly and generating a warning based on the aforementioned analysis results,

[0880] Means for recognizing the user's emotional state and adjusting warnings based on the said emotional state,

[0881] A means for notifying the user terminal of the aforementioned warning,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, wherein the analysis means evaluates the road surface condition using a convolutional neural network.

[0885] (Claim 3)

[0886] The system according to claim 1, wherein the notification means generates a warning message including the type of anomaly and location information, and further adjusts the warning message according to the user's emotional state. [Explanation of Symbols]

[0887] 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 for acquiring road surface image information from an imaging device attached to a mobile body, Means for processing the aforementioned road surface image information to analyze the road surface condition, A means for detecting an anomaly and generating a warning based on the aforementioned analysis results, A means for notifying the user terminal of the aforementioned warning, A system that includes this.

2. The system according to claim 1, wherein the analysis means evaluates the road surface condition using a convolutional neural network.

3. The system according to claim 1, wherein the notification means generates a warning message including the type of abnormality and location information.

Images