system

Abstract

We provide the system. [Solution] A means for acquiring images to photograph the surrounding environment, Image analysis means for analyzing acquired image data and generating identification information, A voice generation means that generates voice guidance based on the generated identification information, A voice output means that provides the generated voice guidance to the user, 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] For visually impaired persons, it is difficult to grasp the surrounding situation, and there are problems such as a decrease in safety and a lack of independence when moving. Also, there are various difficulties in daily life, and it is difficult to achieve full social participation at present. To solve these problems, a device that allows visually impaired persons to safely understand the surrounding situation and move independently is needed.

Means for Solving the Problems

[0005] This invention provides an AI-equipped camera device that enables visually impaired individuals to understand their surroundings in real time through voice guidance. Specifically, it includes an image acquisition means for capturing images of the surrounding environment, an image analysis means for analyzing the acquired image data and generating identification information, a voice generation means for generating voice guidance based on the generated identification information, and a voice output means for providing the generated voice guidance to the user. Furthermore, by incorporating functions to acquire the user's location information and provide arrival information for public transportation, and functions to detect obstacles from image data and propose avoidance routes, the invention aims to improve the safe movement and quality of life of visually impaired individuals.

[0006] "Image acquisition means" refers to a device or method that has the function of photographing the surrounding environment and generating video data.

[0007] "Image analysis means" refers to devices or methods for analyzing acquired video data to identify objects and situations within the environment.

[0008] "Speech generation means" refers to a device or method that converts identification information generated by analysis into a format that can be output as speech.

[0009] "Audio output means" refers to a device or method for playing back generated audio data to a user.

[0010] "Location information acquisition means" refers to a device or method that has the function of identifying the user's location and generating location data.

[0011] An "obstacle detection means" is a device or method that identifies obstacles from acquired image data and provides that information to the user.

[0012] "Avoidance route suggestion" refers to the process of calculating a safe travel route based on detected obstacle information and guiding the user along it. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system that enables visually impaired individuals to safely and efficiently perceive their surroundings and to move around and live their daily lives independently. This system uses an AI-equipped camera device to provide visual information as real-time voice guidance.

[0035] (System operation)

[0036] The device first captures video data by using its camera to photograph the user's surroundings. The acquired data is sent to a server for image analysis processing. Here, an AI algorithm is used to identify elements such as people, obstacles, and signals, and generate information about them.

[0037] The server creates voice guidance based on the analysis results and formats the guidance content as text. Next, a voice generation system converts the text into voice data and sends it to the terminal. The terminal plays the transmitted voice data to the user in real time through its speaker. This allows the user to understand their surroundings by listening.

[0038] Furthermore, the device uses its built-in GPS function to obtain the user's location information. This location information is sent to a server, which then provides information on the next public transport. The user is notified of estimated arrival times and route suggestions as voice guidance.

[0039] Furthermore, the terminal has additional functionality to detect obstacles and proposes avoidance routes for detected obstacles. The server analyzes the obstacles from the image data and calculates the optimal movement route. This makes it possible to assist movement while ensuring safety.

[0040] As a concrete example, imagine a user walking from the train station to their home. The device detects obstacles along the way, such as steps, utility poles, and vending machines, and provides voice guidance such as, "There's a step on the left," or "Be careful, there's a utility pole on the right." It also provides information like, "The next bus will arrive in 10 minutes," when approaching a bus stop, expanding the user's travel options.

[0041] These features enable visually impaired individuals to travel safely to their destinations and enrich their daily activities. Thus, the present invention provides an effective means to improve the independence and quality of life of visually impaired individuals.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The device detects when the user starts moving, activates its camera, and takes pictures of the surrounding environment.

[0045] Step 2:

[0046] The device transmits the captured video data to the server in real time and requests image analysis.

[0047] Step 3:

[0048] The server analyzes the received video data using an AI algorithm to identify the location and distance of people, obstacles, and signals.

[0049] Step 4:

[0050] The server generates text for voice guidance based on the image analysis results. This includes information such as obstacles and intersections ahead.

[0051] Step 5:

[0052] The server converts the generated voice guidance text into audio data and sends it to the terminal.

[0053] Step 6:

[0054] The device plays the received audio data to the user through its speaker, informing the user of their surroundings.

[0055] Step 7:

[0056] The device obtains the user's location information using its built-in GPS module and sends it to the server.

[0057] Step 8:

[0058] The server uses location information to retrieve information such as the arrival time of the next available public transport.

[0059] Step 9:

[0060] The server converts this traffic information into text and sends it to the terminal as voice guidance.

[0061] Step 10:

[0062] The terminal provides users with transmitted traffic information via voice, assisting them in using public transportation.

[0063] Step 11:

[0064] The terminal constantly monitors for obstacles and immediately sends the information to the server if any are detected.

[0065] Step 12:

[0066] The server analyzes obstacle information, calculates a safe alternative route, and outputs the recommended path as text.

[0067] Step 13:

[0068] The server converts this travel path information into audio data and sends it to the terminal.

[0069] Step 14:

[0070] The device provides voice guidance to the user regarding the provided alternative routes, supporting safe travel.

[0071] (Example 1)

[0072] 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."

[0073] There is a need to provide an environment where visually impaired individuals can safely and efficiently understand their surroundings and act independently. Conventional technologies have limitations in the speed and accuracy of acquiring and analyzing visual information, and real-time mobility assistance has not been sufficient. Furthermore, there was a need to appropriately provide the acquired information as voice guidance and present safe and optimal travel routes.

[0074] 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.

[0075] In this invention, the server includes imaging means for capturing images of the surrounding environment, data processing means for analyzing the acquired video information and generating identification information, and voice conversion means for generating voice instructions based on the generated identification information. This enables visually impaired individuals to recognize their surroundings in real time as voice guidance and move safely and efficiently.

[0076] "Imaging means" refers to a device or system for capturing images of the surrounding environment and acquiring video information.

[0077] "Data processing means" refers to a process or system for analyzing acquired video information and generating identification information.

[0078] "Voice conversion means" refers to a device or system for generating voice instructions based on generated identification information.

[0079] "Voice output means" refers to a device or function for conveying generated voice instructions to the user.

[0080] A "route guidance means" is a function or device that provides appropriate route information to assist users in their travel.

[0081] "Location data collection means" refers to a function or device that acquires the geographical location of a user and handles it as data.

[0082] An "obstacle analysis means" is a process or system for detecting obstacles from acquired video information and sensor information, and for suggesting avoidance routes to those obstacles.

[0083] This invention provides a system to support visually impaired individuals in safely and efficiently perceiving their surroundings and navigating independently. This system utilizes a mobile device equipped with an AI-powered camera to provide real-time information about the surrounding environment as audio.

[0084] The device uses a camera sensor to capture images of the user's surroundings. The resulting video data is quickly transmitted to the server. Encryption technology is used to ensure the security of this data transfer.

[0085] The server utilizes image processing software equipped with deep learning algorithms to analyze the received video data. Specifically, it employs algorithms such as YOLO and SSD for object detection and classification. This allows it to accurately identify elements such as people, obstacles, and traffic lights in the user's surroundings and generate identification information related to them.

[0086] The generated identification information is converted from text to audio data through a speech generation system. This process uses services such as Google® Text-to-Speech or Amazon Polly as the speech conversion engine. The converted audio data is sent from the server to the terminal, where it is used to provide instructions and guidance to the user through the terminal's speaker.

[0087] The terminal obtains the user's location information using its built-in GPS module. Based on this, the server can provide voice guidance regarding the arrival time and route of the next public transport. The terminal also uses an ultrasonic sensor to detect physical obstacles and notifies the user of alternative routes suggested by the server.

[0088] As a concrete example, consider a scenario where a user arrives at a train station and heads from the platform towards the exit. The terminal recognizes facilities such as stairs and elevators within the station and provides guidance such as, "There are stairs ahead. Please use the elevator on the right." Furthermore, if it detects a nearby shop, it can also provide information about a place to rest, such as, "There is a convenience store on the right."

[0089] A concrete example of a prompt message generated using an AI model would be: "Please explain mobility assistance using assistive technology for the visually impaired, and give specific examples of guidance along the way."

[0090] This system will enhance the safety of visually impaired individuals while traveling and enrich their daily lives.

[0091] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0092] Step 1:

[0093] The device uses a camera sensor to continuously capture images of the user's surroundings, acquiring real-time video information. This input video information includes environmental elements such as people, obstacles, and road signs around the user. Specifically, the device provides smooth video data by capturing images at a specific frame rate. This video information is output as basic data necessary for the next analysis step.

[0094] Step 2:

[0095] The device transmits the acquired video information to the server via the internet. During this process, the data is encrypted using a secure communication protocol. The input is the video data captured by the device, and the output is the transmitted video data. Specifically, the communication module within the device packets the data and transmits it efficiently.

[0096] Step 3:

[0097] The server analyzes the received video data. Here, it uses deep learning-based image analysis models, such as YOLO or SSD, to extract and identify objects like people, obstacles, and traffic lights. This method extracts features from the input video data and outputs them as identification information. Specifically, the overall and local features of the image are analyzed through multiple neural network layers.

[0098] Step 4:

[0099] The server generates text for voice guidance based on the identification information generated through analysis. This text is then converted into voice data by a speech conversion system. The input is the identification information generated by the server, and the output is the voice data for voice guidance. In terms of specific operation, natural language generation technology is used to express voice instructions.

[0100] Step 5:

[0101] Audio data is transmitted from the server to the terminal. Upon arrival of the audio data, the terminal plays it through its speaker, allowing the user to receive voice guidance in real time. Specifically, the terminal's speaker system adjusts the volume and sound quality to provide the user with clear and easy-to-understand guidance.

[0102] Step 6:

[0103] The device uses its built-in GPS module to obtain the user's location information. This location information is sent to a server to provide information on upcoming public transport and route guidance. The input is the location data obtained by the GPS, and the output is the location information sent to the server. Specifically, the device's GPS module tracks the location in real time, performing highly accurate location measurements.

[0104] Step 7:

[0105] The server can provide the optimal travel route based on acquired location information and obstacle detection. This information is presented to the user as voice guidance; the input is the user's location and obstacle information, and the output is expressed as guidance content. Specifically, the server runs a route optimization algorithm to generate suggestions that are helpful for the user's movement.

[0106] (Application Example 1)

[0107] 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."

[0108] Visually impaired individuals face challenges in safely and efficiently navigating urban environments and obtaining appropriate information when using public transportation. Current technology is insufficient for obstacle recognition and efficient guidance, making it difficult to improve the independence and quality of life of visually impaired individuals.

[0109] 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.

[0110] In this invention, the server includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and fault detection means. This enables visually impaired individuals to understand their surroundings in real time and travel safely to their destination.

[0111] "Data acquisition methods" refer to technologies used to collect data by photographing the surrounding environment.

[0112] "Data analysis means" refers to processing technology used to analyze acquired data and generate identification information, etc.

[0113] "Voice generation means" refers to technology that generates voice guidance based on identification information generated through analysis.

[0114] "Information output means" refers to technologies for providing users with generated voice guidance and other information.

[0115] "Position signal acquisition means" refers to signal reception and processing technology for accurately acquiring the user's location.

[0116] "Means of providing operational information" refers to technology that provides operational information for means of transportation based on acquired location information.

[0117] "Obstacle detection means" refers to technology that detects obstacles from data and proposes alternative routes to safely avoid them.

[0118] "Generative AI models" refer to AI technology used in data analysis to interpret images and provide voice guidance.

[0119] A "prompt statement" refers to guidelines or instructions for properly operating a generative AI model.

[0120] The system that realizes this invention is a technology that enables visually impaired people to move safely while perceiving their surroundings. The system includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and obstacle detection means.

[0121] The terminal uses a camera built into a device such as a smartphone to capture images of the surrounding environment in real time. The acquired data is transmitted to a server via the internet. On the server, a generative AI model is operated as a data analysis tool using AI frameworks such as TENSORFLOW® and PyTorch to identify obstacles, people, traffic lights, etc. from the acquired data.

[0122] The server uses an AI model to analyze identification information and then generates voice guidance via a speech generation system, employing the Google Cloud Text-to-Speech API or similar speech synthesis technologies. The generated voice data is then delivered to the user in real time through the device's speaker.

[0123] The device also uses its built-in GPS function to acquire the user's current location as a means of obtaining a location signal. This location signal is transmitted to a server, which then provides the user with operational information such as public transport arrival information and recommended routes via an operational information provision system.

[0124] As a concrete example, consider a scenario where a user is traveling from a train station to their home. This system detects steps and utility poles encountered along the way and provides guidance such as, "There is a step ahead," or "Please be careful, there is a utility pole on your right." Furthermore, as the user approaches a bus stop, it provides information such as, "The next bus will arrive in 10 minutes," assisting the user's journey.

[0125] An example of a prompt message is: "I want to develop a system that recognizes surrounding pedestrians, obstacles, and traffic signs in real time and provides voice guidance. Please tell me how to efficiently detect objects and generate voice guidance using Python and TensorFlow."

[0126] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0127] Step 1:

[0128] The device uses a camera to capture images of its surroundings in real time and acquire video data. The input is visual information of the surroundings, and the output is video data. This video data is used for subsequent analysis.

[0129] Step 2:

[0130] The terminal transmits the acquired video data to the server via the internet. At this stage, the input is the video data within the terminal, and the output is the video data within the server. The video data is transmitted in real time via a transmission protocol.

[0131] Step 3:

[0132] The server analyzes received video data using a generative AI model. The input is the received video data, and the output is identification information such as obstacles, people, and traffic lights. Data analysis is performed using TensorFlow or PyTorch, and the model is a pre-trained neural network.

[0133] Step 4:

[0134] The server generates voice guidance based on the identification information obtained through analysis. The input is identification information, and the output is guidance text in sentence format. The voice generation method uses the Google Cloud Text-to-Speech API to generate the voice guidance.

[0135] Step 5:

[0136] The server sends the generated voice guidance data back to the terminal. The input is voice data on the server, and the output is voice data on the terminal. It is transmitted in real time, and the user can receive guidance through the voice assistant.

[0137] Step 6:

[0138] The device uses its built-in GPS to obtain the user's current location. The input is location coordinate data, and the output is GPS information. This information is used to calculate arrival times for public transportation.

[0139] Step 7:

[0140] The server uses GPS information and a service information provision system to provide users with public transport arrival information. The input is GPS data, and the output is service information. For example, it notifies users of the arrival time of the next bus.

[0141] Step 8:

[0142] The server proposes obstacle avoidance routes based on analyzed information and the user's movement history. Input is the user's movement history and environmental data, and output is alternative route guidance. This enables safe and efficient travel.

[0143] 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.

[0144] This invention is a system aimed at enabling visually impaired individuals to understand their surroundings and receive appropriate support based on their emotional state. This system combines a camera-equipped device with an emotion recognition engine to provide visual information as voice guidance while also offering further support based on the user's emotional state.

[0145] (System operation)

[0146] The device captures images of the surrounding environment with its camera while the user is moving and transmits the video data to the server in real time. The server analyzes the video data using an AI algorithm to identify the locations of people and obstacles. Based on the results, it generates voice guidance text, converts it into audio data, and sends it back to the device. The device then plays this audio data back to the user, supplementing the visual information.

[0147] In addition, the device analyzes the user's voice and physical information using an emotion recognition engine to identify their emotional state. Based on the identified emotional state, the server adjusts the tone and content of the voice guidance. For example, if it is determined that the user is feeling stressed, the guidance will be delivered in a calmer tone, and information that promotes relaxation will be provided.

[0148] (Specific example)

[0149] For users heading to a train station, the device guides them through obstacles and landmarks along the way. Simultaneously, it analyzes the user's tone of voice, pace, and general facial expressions, and if it detects anxiety, it provides reassuring voice guidance such as, "It's okay. Just go straight and you'll arrive at the station."

[0150] Furthermore, the device calculates the estimated arrival time based on the user's speed and destination location, and then informs the user of the next train time obtained from the server. In this case as well, it adapts its approach to the situation, summarizing the information concisely or providing detailed explanations depending on the user's emotional state.

[0151] Thus, the present invention supports safe and comfortable travel by not only supplementing visual information but also providing information that takes into account the user's emotions. This will improve the quality of life and promote social participation for visually impaired individuals.

[0152] The following describes the processing flow.

[0153] Step 1:

[0154] After startup, the device continuously captures images of its surroundings through its camera and acquires video data.

[0155] Step 2:

[0156] The device transmits the acquired video data to the server in real time and makes requests for image analysis and emotion analysis.

[0157] Step 3:

[0158] The server processes the received video data using an AI algorithm to identify surrounding objects and people. During this process, it also calculates information about their location and distance.

[0159] Step 4:

[0160] The server generates text for voice guidance based on the results of image analysis. This text includes the user's direction of travel, important landmarks, and obstacle information.

[0161] Step 5:

[0162] The server applies emotion recognition algorithms to identify the user's emotional state from their voice and video. It extracts features related to stress, anxiety, and other emotional states.

[0163] Step 6:

[0164] The server adjusts the tone and content of the voice guidance according to the user's emotional state, incorporating kind words and encouraging phrases.

[0165] Step 7:

[0166] The server converts the adjusted voice guidance text into audio data and sends that data to the terminal.

[0167] Step 8:

[0168] The device plays the received audio data to the user through its speaker, conveying environmental information in real time.

[0169] Step 9:

[0170] The device uses its built-in GPS module to obtain the user's current location and sends this information to the server.

[0171] Step 10:

[0172] The server matches location information with public transport data to obtain information on the next available train or bus, and then generates a notification.

[0173] Step 11:

[0174] The server converts the notification content into audio data and sends it to the terminal.

[0175] Step 12:

[0176] The device provides this voice data to the user, guiding them through public transport arrival times and transfer information.

[0177] Step 13:

[0178] The terminal monitors the surrounding environment for continuous obstacle detection and sends information to the server if a new obstacle is detected.

[0179] Step 14:

[0180] The server calculates an alternative route to address the detected obstacle and sends the adjusted navigation instructions as voice data to the terminal.

[0181] Step 15:

[0182] The device provides users with voice guidance to help them avoid obstacles, supporting safe passage.

[0183] (Example 2)

[0184] 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".

[0185] There is a problem in that it is difficult to accurately perceive the surrounding environment and provide appropriate guidance based on the user's emotional state while visually impaired people are traveling. Therefore, improvements in safety and comfort are required.

[0186] 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.

[0187] In this invention, the server includes data acquisition means for acquiring environmental information, data analysis means for analyzing the acquired data and generating feature information, and information generation means for generating guidance information based on the generated feature information. This enables visually impaired individuals to understand their surroundings through voice guidance while moving and to receive guidance that is tailored to the user's emotions.

[0188] "Environmental information" refers to visual or auditory data that indicates the surrounding conditions and changes.

[0189] "Data acquisition means" refers to a device or method for sensing and collecting environmental information.

[0190] "Data analysis means" refers to a device or method for analyzing acquired environmental information and extracting useful characteristic information.

[0191] "Feature information" refers to a collection of information that is considered important or useful, extracted through data analysis.

[0192] "Information generation means" refers to a device or method for creating guidance information to be provided to users based on characteristic information.

[0193] "Information output means" refers to a device or method for transmitting generated guidance information to a user.

[0194] "Emotion recognition means" refers to a device or method that analyzes a user's voice and biometric information to identify their emotional state.

[0195] "Information adjustment means" refers to a device or method for appropriately modifying the content and tone of guidance information according to an identified emotional state.

[0196] "Means of transportation" refer to the transportation systems and technologies that support people's physical movement.

[0197] "Information detection means" refers to a device or method for detecting specific events or situations (e.g., obstacles) using acquired data.

[0198] To implement this invention, a mobile terminal usable by visually impaired persons and a server connected to it via communication are used. The mobile terminal is equipped with a high-resolution camera, a voice input device, and an AI platform, while the server is equipped with a powerful processing unit for data analysis and emotion recognition. Each component operates as follows:

[0199] The device first captures the user's surroundings using a camera, acquiring data in real time. The frame rate and resolution of the captured images are adjusted to ensure that all necessary information for visually impaired individuals is captured. The acquired data is compressed within the device before being transmitted to a server using high-speed communication technology. This communication technology can utilize 5G or Wi-Fi networks.

[0200] To process the received video data, the server performs object detection and feature extraction by combining image recognition libraries and AI models, such as OpenCV and TensorFlow. In particular, it utilizes models with high-precision identification capabilities, such as YOLOv5, for object detection. This allows for the rapid and accurate identification of the locations of people and obstacles.

[0201] Based on these analysis results, the server generates appropriate guidance information. This involves using a generative AI model to construct natural-sounding sentences, which are then converted into audio data using speech synthesis technologies such as the Google Text-to-Speech API. This audio data is then quickly sent to the device and delivered to the user.

[0202] Furthermore, the device collects the user's voice using a microphone and performs emotion recognition in real time. For example, it identifies emotional states such as stress or calmness based on the tone and speed of the voice, and reflects this in the tone and content of the guidance information provided by the server.

[0203] As a concrete example, consider a user using this system while traveling to a train station. The terminal not only provides voice guidance about surrounding obstacles, but also offers reassuring messages based on emotion recognition, such as, "It's okay. Just go straight and you'll arrive at the station."

[0204] A concrete example of a prompt message would be to ask the generating AI model to "analyze the stress level the user is experiencing on their current travel route and generate a guidance message that provides the greatest sense of security."

[0205] This allows visually impaired individuals to receive visual information and emotionally responsive support for safe and comfortable movement. This invention promotes social participation and improves the quality of life for visually impaired individuals.

[0206] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0207] Step 1:

[0208] The device captures visual information of its surroundings using its built-in camera. The input at this time is real-time video data, and the device collects the information at an appropriate resolution and frame rate. The collected video data is first compressed within the device to reduce its data size. The compressed data becomes the output, which is then used in the next step.

[0209] Step 2:

[0210] The compressed video data is sent from the terminal to the server via a high-speed communication network. This process utilizes communication technologies such as 5G and Wi-Fi to transfer the data quickly and securely to the server. The output here is the transmitted compressed video data.

[0211] Step 3:

[0212] The server decompresses the received compressed video data and analyzes it. Using the decompressed raw video data as input, it applies an AI algorithm to detect and identify objects and obstacles within the image. Specifically, it utilizes an object detection model based on OpenCV and YOLOv5. The output consists of the object's position information and features obtained as a result of the analysis.

[0213] Step 4:

[0214] The server generates text for voice guidance based on the analysis results. By using a generative AI model to perform natural language processing, it constructs guidance text that is easily understandable to the user. The input for this process is detected object information, and the output is the generated voice text data.

[0215] Step 5:

[0216] The server uses speech synthesis technology to convert text data into speech data. Specifically, it uses a speech synthesis API to generate natural-sounding speech. The input for this step is the generated text, and the output is the data for the voice guidance.

[0217] Step 6:

[0218] The terminal plays audio data received from the server and provides guidance to the user in real time. The audio data is played through the terminal's speaker. The input here is the received audio data, and the output is clear voice guidance for the user.

[0219] Step 7:

[0220] The device acquires the user's voice via a microphone and analyzes it with an emotion recognition engine. In this step, the user's emotional state is identified based on the voice input data. The results of the emotion analysis are output and used in the next step.

[0221] Step 8:

[0222] The server adjusts the voice guidance based on the user's emotional state. For example, if an emotion indicating stress is detected, it will generate guidance in a calmer tone. The input for this step is the result of the emotion analysis, and the output is the adjusted voice guidance.

[0223] By performing these steps in sequence, we can provide visual information reinforcement and emotionally appropriate guidance to support the mobility of visually impaired individuals.

[0224] (Application Example 2)

[0225] 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".

[0226] To enable visually impaired individuals to move safely and comfortably, it is necessary not only to perceive their surroundings in real time, but also to provide appropriate support tailored to their emotional state at that time. However, conventional technologies have the challenge of not being able to respond flexibly while considering the user's emotional state.

[0227] 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.

[0228] In this invention, the server includes an image acquisition device for capturing the surrounding environment, an image analysis device for analyzing the acquired image data and generating target information, a voice generation device for generating voice guidance based on the generated target information, an emotion recognition device for analyzing the user's voice and physical information and identifying their emotional state, and a voice adjustment device for adjusting the tone and content of the voice guidance based on the identified emotional state. This enables visually impaired individuals to move safely while receiving appropriate support according to their emotional state.

[0229] An "image acquisition device" is a device that has the function of recording the surrounding environment using a camera or other photographic equipment.

[0230] An "image analysis device" is a device that processes acquired image data and has the function of identifying and generating target information such as people and obstacles.

[0231] A "voice generation device" is a device that has the function of creating voice guidance based on analyzed target information.

[0232] A "voice output device" is a device that has the function of allowing users to listen to generated voice guidance.

[0233] An "emotion recognition device" is a device that analyzes a user's voice and physical information to identify their emotional state.

[0234] A "voice adjustment device" is a device that has the function of adjusting the tone and content of voice guidance based on the identified emotional state.

[0235] A "location information acquisition device" is a device that has the function of measuring the user's current location and acquiring that location information.

[0236] An "object detection device" is a device that identifies objects from image data and proposes appropriate avoidance routes.

[0237] The system for implementing this invention has the function of recognizing the surrounding environment and providing appropriate support according to the user's emotional state, so that visually impaired persons can move safely and comfortably.

[0238] The server first receives image data from a terminal that includes an image acquisition device that captures the surrounding environment using a camera. Next, the received image data is processed by an image analysis device to identify objects and obstacles. Then, based on the target information generated by the image analysis device, a voice generation device creates voice guidance, which is then provided to the user by a voice output device.

[0239] Furthermore, the device collects the user's voice through the microphone and physical information acquired by sensors. This information is analyzed by an emotion recognition device to identify the user's emotional state. Based on the identified emotional state, a voice adjustment device adjusts the tone and content of the voice guidance to provide the user with an appropriate response.

[0240] For example, when a user is heading to a train station on a rainy day, the server guides the user to landmarks they can see along the way, and if the user is feeling anxious, it provides information in a calm tone, such as, "It's okay. There's a roof nearby." In addition, location information acquisition devices determine the user's current location and improve convenience by providing timely information about the arrival of transportation services.

[0241] For specific processing, we recommend using OpenCV for image analysis, Google Cloud Speech-to-Text for speech recognition, and TensorFlow or PyTorch for sentiment analysis. This allows for efficient processing of complex data and the provision of information tailored to user needs.

[0242] As an example of how to utilize a generative AI model, a good prompt would be, "Please tell me how a visual guide robot can report surrounding obstacles and adjust its voice tone according to the user's emotions."

[0243] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0244] Step 1:

[0245] The device captures images of its surroundings with its camera and sends the image data to the server in real time. In this step, the image data is the input, the data is compressed for transmission to the server, and the compressed image data is output.

[0246] Step 2:

[0247] The server processes the received image data using an image analysis device to identify target information such as people and obstacles. In this step, compressed image data is used as input, image analysis is performed using OpenCV, and the target information is output.

[0248] Step 3:

[0249] The server generates voice guidance using a voice generation device based on the target information. In this step, the target information is the input, and the voice guidance text is output using natural language generation technology.

[0250] Step 4:

[0251] The terminal provides the user with voice guidance text via a voice output device. In this step, the voice guidance text is input, and voice synthesis is performed to output the voice guidance.

[0252] Step 5:

[0253] The device analyzes the user's voice via the microphone and physical information acquired by sensors using an emotion recognition device. In this step, the user's voice data and physical information are inputs, and the emotional state is output using TensorFlow or PyTorch.

[0254] Step 6:

[0255] The server adjusts the tone and content of the voice guidance using a voice adjustment device based on the identified emotional state. In this step, the emotional state and voice guidance are inputs, and the tone-adjusted voice guidance is output.

[0256] Step 7:

[0257] The terminal uses a location information acquisition device to determine the user's current location and requests arrival information for the appropriate transportation service from the server. In this step, the current location is the input, and transportation service information is output based on that location information.

[0258] Step 8:

[0259] The server receives traffic service information and provides it to the user. In this step, traffic service information is input, and information corresponding to the user's request is output via voice guidance.

[0260] 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.

[0261] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0262] 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.

[0263] [Second Embodiment]

[0264] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0265] 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.

[0266] 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).

[0267] 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.

[0268] 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.

[0269] 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).

[0270] 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.

[0271] 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.

[0272] 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.

[0273] 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.

[0274] 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.

[0275] 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".

[0276] This invention is a system that enables visually impaired individuals to safely and efficiently perceive their surroundings and to move around and live their daily lives independently. This system uses an AI-equipped camera device to provide visual information as real-time voice guidance.

[0277] (System operation)

[0278] The terminal first takes pictures of the user's surroundings with a camera to obtain video data. The acquired data is sent to the server for image analysis processing. Here, an AI algorithm is used to identify elements such as people, obstacles, signals, etc., and generate information about them.

[0279] Based on the analysis results, the server creates voice guidance and formats the guidance content as text. Next, the text is converted into voice data by a voice generation system and sent to the terminal. The terminal plays the sent voice data to the user in real time through a speaker. In this way, the user can grasp the surrounding situation by listening.

[0280] Furthermore, the terminal uses its built-in GPS function to obtain the user's location information. This location information is sent to the server, and information on the next public transportation is provided. Arrival predictions, route suggestions, etc. are notified to the user as voice guidance.

[0281] Also, the terminal has an additional function for detecting obstacles and proposes an avoidance route for the detected obstacles. The server analyzes the obstacles from the image data and calculates an optimal movement route. This makes it possible to assist movement while ensuring safety.

[0282] As a specific example, assume that the user is walking from the station to their home. The terminal detects obstacles such as steps, utility poles, and vending machines along the way and provides voice guides such as "There is a step on the left" and "Be careful as there is a utility pole on the right". Also, when approaching a bus stop, it guides "The next bus will arrive in 10 minutes", expanding the options for movement.

[0283] With these functions, visually impaired people can move safely to their destinations and enrich their daily activities. Thus, the present invention provides an effective means for improving the independence and quality of life of visually impaired people.

[0284] The following describes the processing flow.

[0285] Step 1:

[0286] The terminal detects the start of the user's movement, activates the camera, and takes pictures of the surrounding environment.

[0287] Step 2:

[0288] The terminal transmits the captured video data to the server in real time and requests image analysis.

[0289] Step 3:

[0290] The server analyzes the received video data with an AI algorithm to identify the positions and distances of people, obstacles, and signals.

[0291] Step 4:

[0292] Based on the image analysis results, the server generates the text for voice guidance. For example, it includes information about obstacles ahead on the road or intersections.

[0293] Step 5:

[0294] The server converts the generated voice guidance text into voice data and transmits it to the terminal.

[0295] Step 6:

[0296] The terminal plays the received voice data to the user through the speaker to inform the user of the surrounding situation.

[0297] Step 7:

[0298] The terminal obtains the user's location information with the built-in GPS module and transmits this to the server.

[0299] Step 8:

[0300] Based on the location information, the server obtains information such as the arrival times of the next available public transportation.

[0301] Step 9:

[0302] The server converts this traffic information into text and transmits it to the terminal as voice guidance.

[0303] Step 10:

[0304] The terminal provides the transmitted traffic information to the user as voice and supports the use of public transportation.

[0305] Step 11:

[0306] The terminal constantly monitors whether there are any obstacles, and if any occur, it immediately transmits the information to the server.

[0307] Step 12:

[0308] The server analyzes the obstacle information, calculates a safe avoidance route, and converts the recommended movement route into text.

[0309] Step 13:

[0310] The server converts this movement route information into voice data and transmits it to the terminal.

[0311] Step 14:

[0312] The terminal guides the user with the provided avoidance route as voice and supports safe movement.

[0313] (Example 1)

[0314] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] There is a need to provide an environment where visually impaired individuals can safely and efficiently understand their surroundings and act independently. Conventional technologies have limitations in the speed and accuracy of acquiring and analyzing visual information, and real-time mobility assistance has not been sufficient. Furthermore, there was a need to appropriately provide the acquired information as voice guidance and present safe and optimal travel routes.

[0316] 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.

[0317] In this invention, the server includes imaging means for capturing images of the surrounding environment, data processing means for analyzing the acquired video information and generating identification information, and voice conversion means for generating voice instructions based on the generated identification information. This enables visually impaired individuals to recognize their surroundings in real time as voice guidance and move safely and efficiently.

[0318] "Imaging means" refers to a device or system for capturing images of the surrounding environment and acquiring video information.

[0319] "Data processing means" refers to a process or system for analyzing acquired video information and generating identification information.

[0320] "Voice conversion means" refers to a device or system for generating voice instructions based on generated identification information.

[0321] "Voice output means" refers to a device or function for conveying generated voice instructions to the user.

[0322] A "route guidance means" is a function or device that provides appropriate route information to assist users in their travel.

[0323] "Location data collection means" refers to a function or device that acquires the geographical location of a user and handles it as data.

[0324] An "obstacle analysis means" is a process or system for detecting obstacles from acquired video information and sensor information, and for suggesting avoidance routes to those obstacles.

[0325] This invention provides a system to support visually impaired individuals in safely and efficiently perceiving their surroundings and navigating independently. This system utilizes a mobile device equipped with an AI-powered camera to provide real-time information about the surrounding environment as audio.

[0326] The device uses a camera sensor to capture images of the user's surroundings. The resulting video data is quickly transmitted to the server. Encryption technology is used to ensure the security of this data transfer.

[0327] The server utilizes image processing software equipped with deep learning algorithms to analyze the received video data. Specifically, it employs algorithms such as YOLO and SSD for object detection and classification. This allows it to accurately identify elements such as people, obstacles, and traffic lights in the user's surroundings and generate identification information related to them.

[0328] The generated identification information is converted from text to audio data through a speech generation system. This process utilizes services such as Google Text-to-Speech or Amazon Polly as the speech conversion engine. The converted audio data is sent from the server to the device, where it provides instructions and guidance to the user using the device's speaker.

[0329] The terminal obtains the user's location information using its built-in GPS module. Based on this, the server can provide voice guidance regarding the arrival time and route of the next public transport. The terminal also uses an ultrasonic sensor to detect physical obstacles and notifies the user of alternative routes suggested by the server.

[0330] As a concrete example, consider a scenario where a user arrives at a train station and heads from the platform towards the exit. The terminal recognizes facilities such as stairs and elevators within the station and provides guidance such as, "There are stairs ahead. Please use the elevator on the right." Furthermore, if it detects a nearby shop, it can also provide information about a place to rest, such as, "There is a convenience store on the right."

[0331] A concrete example of a prompt message generated using an AI model would be: "Please explain mobility assistance using assistive technology for the visually impaired, and give specific examples of guidance along the way."

[0332] This system will enhance the safety of visually impaired individuals while traveling and enrich their daily lives.

[0333] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0334] Step 1:

[0335] The device uses a camera sensor to continuously capture images of the user's surroundings, acquiring real-time video information. This input video information includes environmental elements such as people, obstacles, and road signs around the user. Specifically, the device provides smooth video data by capturing images at a specific frame rate. This video information is output as basic data necessary for the next analysis step.

[0336] Step 2:

[0337] The device transmits the acquired video information to the server via the internet. During this process, the data is encrypted using a secure communication protocol. The input is the video data captured by the device, and the output is the transmitted video data. Specifically, the communication module within the device packets the data and transmits it efficiently.

[0338] Step 3:

[0339] The server analyzes the received video data. Here, it uses deep learning-based image analysis models, such as YOLO or SSD, to extract and identify objects like people, obstacles, and traffic lights. This method extracts features from the input video data and outputs them as identification information. Specifically, the overall and local features of the image are analyzed through multiple neural network layers.

[0340] Step 4:

[0341] The server generates text for voice guidance based on the identification information generated through analysis. This text is then converted into voice data by a speech conversion system. The input is the identification information generated by the server, and the output is the voice data for voice guidance. In terms of specific operation, natural language generation technology is used to express voice instructions.

[0342] Step 5:

[0343] Audio data is transmitted from the server to the terminal. Upon arrival of the audio data, the terminal plays it through its speaker, allowing the user to receive voice guidance in real time. Specifically, the terminal's speaker system adjusts the volume and sound quality to provide the user with clear and easy-to-understand guidance.

[0344] Step 6:

[0345] The device uses its built-in GPS module to obtain the user's location information. This location information is sent to a server to provide information on upcoming public transport and route guidance. The input is the location data obtained by the GPS, and the output is the location information sent to the server. Specifically, the device's GPS module tracks the location in real time, performing highly accurate location measurements.

[0346] Step 7:

[0347] The server can provide the optimal travel route based on acquired location information and obstacle detection. This information is presented to the user as voice guidance; the input is the user's location and obstacle information, and the output is expressed as guidance content. Specifically, the server runs a route optimization algorithm to generate suggestions that are helpful for the user's movement.

[0348] (Application Example 1)

[0349] 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."

[0350] Visually impaired individuals face challenges in safely and efficiently navigating urban environments and obtaining appropriate information when using public transportation. Current technology is insufficient for obstacle recognition and efficient guidance, making it difficult to improve the independence and quality of life of visually impaired individuals.

[0351] 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.

[0352] In this invention, the server includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and fault detection means. This enables visually impaired individuals to understand their surroundings in real time and travel safely to their destination.

[0353] "Data acquisition methods" refer to technologies used to collect data by photographing the surrounding environment.

[0354] "Data analysis means" refers to processing technology used to analyze acquired data and generate identification information, etc.

[0355] "Voice generation means" refers to technology that generates voice guidance based on identification information generated through analysis.

[0356] "Information output means" refers to technologies for providing users with generated voice guidance and other information.

[0357] "Position signal acquisition means" refers to signal reception and processing technology for accurately acquiring the user's location.

[0358] "Means of providing operational information" refers to technology that provides operational information for means of transportation based on acquired location information.

[0359] "Obstacle detection means" refers to technology that detects obstacles from data and proposes alternative routes to safely avoid them.

[0360] "Generative AI models" refer to AI technology used in data analysis to interpret images and provide voice guidance.

[0361] A "prompt statement" refers to guidelines or instructions for properly operating a generative AI model.

[0362] The system that realizes this invention is a technology that enables visually impaired people to move safely while perceiving their surroundings. The system includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and obstacle detection means.

[0363] The terminal uses a camera built into a device such as a smartphone to capture images of the surrounding environment in real time. The acquired data is sent to a server via the internet. On the server, a generative AI model is run using AI frameworks such as TensorFlow and PyTorch as a means of data analysis, and it identifies obstacles, people, traffic lights, etc. from the acquired data.

[0364] The server uses an AI model to analyze identification information and then generates voice guidance via a speech generation system, employing the Google Cloud Text-to-Speech API or similar speech synthesis technologies. The generated voice data is then delivered to the user in real time through the device's speaker.

[0365] The device also uses its built-in GPS function to acquire the user's current location as a means of obtaining a location signal. This location signal is transmitted to a server, which then provides the user with operational information such as public transport arrival information and recommended routes via an operational information provision system.

[0366] As a concrete example, consider a scenario where a user is traveling from a train station to their home. This system detects steps and utility poles encountered along the way and provides guidance such as, "There is a step ahead," or "Please be careful, there is a utility pole on your right." Furthermore, as the user approaches a bus stop, it provides information such as, "The next bus will arrive in 10 minutes," assisting the user's journey.

[0367] An example of a prompt message is: "I want to develop a system that recognizes surrounding pedestrians, obstacles, and traffic signs in real time and provides voice guidance. Please tell me how to efficiently detect objects and generate voice guidance using Python and TensorFlow."

[0368] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0369] Step 1:

[0370] The device uses a camera to capture images of its surroundings in real time and acquire video data. The input is visual information of the surroundings, and the output is video data. This video data is used for subsequent analysis.

[0371] Step 2:

[0372] The terminal transmits the acquired video data to the server via the internet. At this stage, the input is the video data within the terminal, and the output is the video data within the server. The video data is transmitted in real time via a transmission protocol.

[0373] Step 3:

[0374] The server analyzes received video data using a generative AI model. The input is the received video data, and the output is identification information such as obstacles, people, and traffic lights. Data analysis is performed using TensorFlow or PyTorch, and the model is a pre-trained neural network.

[0375] Step 4:

[0376] The server generates voice guidance based on the identification information obtained through analysis. The input is identification information, and the output is guidance text in sentence format. The voice generation method uses the Google Cloud Text-to-Speech API to generate the voice guidance.

[0377] Step 5:

[0378] The server sends the generated voice guidance data back to the terminal. The input is voice data on the server, and the output is voice data on the terminal. It is transmitted in real time, and the user can receive guidance through the voice assistant.

[0379] Step 6:

[0380] The device uses its built-in GPS to obtain the user's current location. The input is location coordinate data, and the output is GPS information. This information is used to calculate arrival times for public transportation.

[0381] Step 7:

[0382] The server uses GPS information and a service information provision system to provide users with public transport arrival information. The input is GPS data, and the output is service information. For example, it notifies users of the arrival time of the next bus.

[0383] Step 8:

[0384] The server proposes obstacle avoidance routes based on analyzed information and the user's movement history. Input is the user's movement history and environmental data, and output is alternative route guidance. This enables safe and efficient travel.

[0385] 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.

[0386] This invention is a system aimed at enabling visually impaired individuals to understand their surroundings and receive appropriate support based on their emotional state. This system combines a camera-equipped device with an emotion recognition engine to provide visual information as voice guidance while also offering further support based on the user's emotional state.

[0387] (System operation)

[0388] The device captures images of the surrounding environment with its camera while the user is moving and transmits the video data to the server in real time. The server analyzes the video data using an AI algorithm to identify the locations of people and obstacles. Based on the results, it generates voice guidance text, converts it into audio data, and sends it back to the device. The device then plays this audio data back to the user, supplementing the visual information.

[0389] In addition, the device analyzes the user's voice and physical information using an emotion recognition engine to identify their emotional state. Based on the identified emotional state, the server adjusts the tone and content of the voice guidance. For example, if it is determined that the user is feeling stressed, the guidance will be delivered in a calmer tone, and information that promotes relaxation will be provided.

[0390] (Specific example)

[0391] For users heading to a train station, the device guides them through obstacles and landmarks along the way. Simultaneously, it analyzes the user's tone of voice, pace, and general facial expressions, and if it detects anxiety, it provides reassuring voice guidance such as, "It's okay. Just go straight and you'll arrive at the station."

[0392] Furthermore, the device calculates the estimated arrival time based on the user's speed and destination location, and then informs the user of the next train time obtained from the server. In this case as well, it adapts its approach to the situation, summarizing the information concisely or providing detailed explanations depending on the user's emotional state.

[0393] Thus, the present invention supports safe and comfortable travel by not only supplementing visual information but also providing information that takes into account the user's emotions. This will improve the quality of life and promote social participation for visually impaired individuals.

[0394] The following describes the processing flow.

[0395] Step 1:

[0396] After startup, the device continuously captures images of its surroundings through its camera and acquires video data.

[0397] Step 2:

[0398] The device transmits the acquired video data to the server in real time and makes requests for image analysis and emotion analysis.

[0399] Step 3:

[0400] The server processes the received video data using an AI algorithm to identify surrounding objects and people. During this process, it also calculates information about their location and distance.

[0401] Step 4:

[0402] The server generates text for voice guidance based on the results of image analysis. This text includes the user's direction of travel, important landmarks, and obstacle information.

[0403] Step 5:

[0404] The server applies emotion recognition algorithms to identify the user's emotional state from their voice and video. It extracts features related to stress, anxiety, and other emotional states.

[0405] Step 6:

[0406] The server adjusts the tone and content of the voice guidance according to the user's emotional state, incorporating kind words and encouraging phrases.

[0407] Step 7:

[0408] The server converts the adjusted voice guidance text into audio data and sends that data to the terminal.

[0409] Step 8:

[0410] The device plays the received audio data to the user through its speaker, conveying environmental information in real time.

[0411] Step 9:

[0412] The device uses its built-in GPS module to obtain the user's current location and sends this information to the server.

[0413] Step 10:

[0414] The server matches location information with public transport data to obtain information on the next available train or bus, and then generates a notification.

[0415] Step 11:

[0416] The server converts the notification content into audio data and sends it to the terminal.

[0417] Step 12:

[0418] The device provides this voice data to the user, guiding them through public transport arrival times and transfer information.

[0419] Step 13:

[0420] The terminal monitors the surrounding environment for continuous obstacle detection and sends information to the server if a new obstacle is detected.

[0421] Step 14:

[0422] The server calculates an alternative route to address the detected obstacle and sends the adjusted navigation instructions as voice data to the terminal.

[0423] Step 15:

[0424] The device provides users with voice guidance to help them avoid obstacles, supporting safe passage.

[0425] (Example 2)

[0426] 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".

[0427] There is a problem in that it is difficult to accurately perceive the surrounding environment and provide appropriate guidance based on the user's emotional state while visually impaired people are traveling. Therefore, improvements in safety and comfort are required.

[0428] 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.

[0429] In this invention, the server includes data acquisition means for acquiring environmental information, data analysis means for analyzing the acquired data and generating feature information, and information generation means for generating guidance information based on the generated feature information. This enables visually impaired individuals to understand their surroundings through voice guidance while moving and to receive guidance that is tailored to the user's emotions.

[0430] "Environmental information" refers to visual or auditory data that indicates the surrounding conditions and changes.

[0431] "Data acquisition means" refers to a device or method for sensing and collecting environmental information.

[0432] "Data analysis means" refers to a device or method for analyzing acquired environmental information and extracting useful characteristic information.

[0433] "Feature information" refers to a collection of information that is considered important or useful, extracted through data analysis.

[0434] "Information generation means" refers to a device or method for creating guidance information to be provided to users based on characteristic information.

[0435] "Information output means" refers to a device or method for transmitting generated guidance information to a user.

[0436] "Emotion recognition means" refers to a device or method that analyzes a user's voice and biometric information to identify their emotional state.

[0437] "Information adjustment means" refers to a device or method for appropriately modifying the content and tone of guidance information according to an identified emotional state.

[0438] "Means of transportation" refer to the transportation systems and technologies that support people's physical movement.

[0439] "Information detection means" refers to a device or method for detecting specific events or situations (e.g., obstacles) using acquired data.

[0440] To implement this invention, a mobile terminal usable by visually impaired persons and a server connected to it via communication are used. The mobile terminal is equipped with a high-resolution camera, a voice input device, and an AI platform, while the server is equipped with a powerful processing unit for data analysis and emotion recognition. Each component operates as follows:

[0441] The device first captures the user's surroundings using a camera, acquiring data in real time. The frame rate and resolution of the captured images are adjusted to ensure that all necessary information for visually impaired individuals is captured. The acquired data is compressed within the device before being transmitted to a server using high-speed communication technology. This communication technology can utilize 5G or Wi-Fi networks.

[0442] To process the received video data, the server performs object detection and feature extraction by combining image recognition libraries and AI models, such as OpenCV and TensorFlow. In particular, it utilizes models with high-precision identification capabilities, such as YOLOv5, for object detection. This allows for the rapid and accurate identification of the locations of people and obstacles.

[0443] Based on these analysis results, the server generates appropriate guidance information. This involves using a generative AI model to construct natural-sounding sentences, which are then converted into audio data using speech synthesis technologies such as the Google Text-to-Speech API. This audio data is then quickly sent to the device and delivered to the user.

[0444] Furthermore, the device collects the user's voice using a microphone and performs emotion recognition in real time. For example, it identifies emotional states such as stress or calmness based on the tone and speed of the voice, and reflects this in the tone and content of the guidance information provided by the server.

[0445] As a concrete example, consider a user using this system while traveling to a train station. The terminal not only provides voice guidance about surrounding obstacles, but also offers reassuring messages based on emotion recognition, such as, "It's okay. Just go straight and you'll arrive at the station."

[0446] A concrete example of a prompt message would be to ask the generating AI model to "analyze the stress level the user is experiencing on their current travel route and generate a guidance message that provides the greatest sense of security."

[0447] This allows visually impaired individuals to receive visual information and emotionally responsive support for safe and comfortable movement. This invention promotes social participation and improves the quality of life for visually impaired individuals.

[0448] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0449] Step 1:

[0450] The device captures visual information of its surroundings using its built-in camera. The input at this time is real-time video data, and the device collects the information at an appropriate resolution and frame rate. The collected video data is first compressed within the device to reduce its data size. The compressed data becomes the output, which is then used in the next step.

[0451] Step 2:

[0452] The compressed video data is sent from the terminal to the server via a high-speed communication network. This process utilizes communication technologies such as 5G and Wi-Fi to transfer the data quickly and securely to the server. The output here is the transmitted compressed video data.

[0453] Step 3:

[0454] The server decompresses the received compressed video data and analyzes it. Using the decompressed raw video data as input, it applies an AI algorithm to detect and identify objects and obstacles within the image. Specifically, it utilizes an object detection model based on OpenCV and YOLOv5. The output consists of the object's position information and features obtained as a result of the analysis.

[0455] Step 4:

[0456] The server generates text for voice guidance based on the analysis results. By using a generative AI model to perform natural language processing, it constructs guidance text that is easily understandable to the user. The input for this process is detected object information, and the output is the generated voice text data.

[0457] Step 5:

[0458] The server uses speech synthesis technology to convert text data into speech data. Specifically, it uses a speech synthesis API to generate natural-sounding speech. The input for this step is the generated text, and the output is the data for the voice guidance.

[0459] Step 6:

[0460] The terminal plays audio data received from the server and provides guidance to the user in real time. The audio data is played through the terminal's speaker. The input here is the received audio data, and the output is clear voice guidance for the user.

[0461] Step 7:

[0462] The device acquires the user's voice via a microphone and analyzes it with an emotion recognition engine. In this step, the user's emotional state is identified based on the voice input data. The results of the emotion analysis are output and used in the next step.

[0463] Step 8:

[0464] The server adjusts the voice guidance based on the user's emotional state. For example, if an emotion indicating stress is detected, it will generate guidance in a calmer tone. The input for this step is the result of the emotion analysis, and the output is the adjusted voice guidance.

[0465] By performing these steps in sequence, we can provide visual information reinforcement and emotionally appropriate guidance to support the mobility of visually impaired individuals.

[0466] (Application Example 2)

[0467] 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."

[0468] To enable visually impaired individuals to move safely and comfortably, it is necessary not only to perceive their surroundings in real time, but also to provide appropriate support tailored to their emotional state at that time. However, conventional technologies have the challenge of not being able to respond flexibly while considering the user's emotional state.

[0469] 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.

[0470] In this invention, the server includes an image acquisition device for capturing the surrounding environment, an image analysis device for analyzing the acquired image data and generating target information, a voice generation device for generating voice guidance based on the generated target information, an emotion recognition device for analyzing the user's voice and physical information and identifying their emotional state, and a voice adjustment device for adjusting the tone and content of the voice guidance based on the identified emotional state. This enables visually impaired individuals to move safely while receiving appropriate support according to their emotional state.

[0471] An "image acquisition device" is a device that has the function of recording the surrounding environment using a camera or other photographic equipment.

[0472] An "image analysis device" is a device that processes acquired image data and has the function of identifying and generating target information such as people and obstacles.

[0473] A "voice generation device" is a device that has the function of creating voice guidance based on analyzed target information.

[0474] A "voice output device" is a device that has the function of allowing users to listen to generated voice guidance.

[0475] An "emotion recognition device" is a device that analyzes a user's voice and physical information to identify their emotional state.

[0476] A "voice adjustment device" is a device that has the function of adjusting the tone and content of voice guidance based on the identified emotional state.

[0477] A "location information acquisition device" is a device that has the function of measuring the user's current location and acquiring that location information.

[0478] An "object detection device" is a device that identifies objects from image data and proposes appropriate avoidance routes.

[0479] The system for implementing this invention has the function of recognizing the surrounding environment and providing appropriate support according to the user's emotional state, so that visually impaired persons can move safely and comfortably.

[0480] The server first receives image data from a terminal that includes an image acquisition device that captures the surrounding environment using a camera. Next, the received image data is processed by an image analysis device to identify objects and obstacles. Then, based on the target information generated by the image analysis device, a voice generation device creates voice guidance, which is then provided to the user by a voice output device.

[0481] Furthermore, the device collects the user's voice through the microphone and physical information acquired by sensors. This information is analyzed by an emotion recognition device to identify the user's emotional state. Based on the identified emotional state, a voice adjustment device adjusts the tone and content of the voice guidance to provide the user with an appropriate response.

[0482] For example, when a user is heading to a train station on a rainy day, the server guides the user to landmarks they can see along the way, and if the user is feeling anxious, it provides information in a calm tone, such as, "It's okay. There's a roof nearby." In addition, location information acquisition devices determine the user's current location and improve convenience by providing timely information about the arrival of transportation services.

[0483] For specific processing, we recommend using OpenCV for image analysis, Google Cloud Speech-to-Text for speech recognition, and TensorFlow or PyTorch for sentiment analysis. This allows for efficient processing of complex data and the provision of information tailored to user needs.

[0484] As an example of how to utilize a generative AI model, a good prompt would be, "Please tell me how a visual guide robot can report surrounding obstacles and adjust its voice tone according to the user's emotions."

[0485] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0486] Step 1:

[0487] The device captures images of its surroundings with its camera and sends the image data to the server in real time. In this step, the image data is the input, the data is compressed for transmission to the server, and the compressed image data is output.

[0488] Step 2:

[0489] The server processes the received image data using an image analysis device to identify target information such as people and obstacles. In this step, compressed image data is used as input, image analysis is performed using OpenCV, and the target information is output.

[0490] Step 3:

[0491] The server generates voice guidance using a voice generation device based on the target information. In this step, the target information is the input, and the voice guidance text is output using natural language generation technology.

[0492] Step 4:

[0493] The terminal provides the user with voice guidance text via a voice output device. In this step, the voice guidance text is input, and voice synthesis is performed to output the voice guidance.

[0494] Step 5:

[0495] The device analyzes the user's voice via the microphone and physical information acquired by sensors using an emotion recognition device. In this step, the user's voice data and physical information are inputs, and the emotional state is output using TensorFlow or PyTorch.

[0496] Step 6:

[0497] The server adjusts the tone and content of the voice guidance using a voice adjustment device based on the identified emotional state. In this step, the emotional state and voice guidance are inputs, and the tone-adjusted voice guidance is output.

[0498] Step 7:

[0499] The terminal uses a location information acquisition device to determine the user's current location and requests arrival information for the appropriate transportation service from the server. In this step, the current location is the input, and transportation service information is output based on that location information.

[0500] Step 8:

[0501] The server receives traffic service information and provides it to the user. In this step, traffic service information is input, and information corresponding to the user's request is output via voice guidance.

[0502] 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.

[0503] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0504] 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.

[0505] [Third Embodiment]

[0506] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0507] 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.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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).

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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".

[0518] This invention is a system that enables visually impaired individuals to safely and efficiently perceive their surroundings and to move around and live their daily lives independently. This system uses an AI-equipped camera device to provide visual information as real-time voice guidance.

[0519] (System operation)

[0520] The device first captures video data by using its camera to photograph the user's surroundings. The acquired data is sent to a server for image analysis processing. Here, an AI algorithm is used to identify elements such as people, obstacles, and signals, and generate information about them.

[0521] The server creates voice guidance based on the analysis results and formats the guidance content as text. Next, a voice generation system converts the text into voice data and sends it to the terminal. The terminal plays the transmitted voice data to the user in real time through its speaker. This allows the user to understand their surroundings by listening.

[0522] Furthermore, the device uses its built-in GPS function to obtain the user's location information. This location information is sent to a server, which then provides information on the next public transport. The user is notified of estimated arrival times and route suggestions as voice guidance.

[0523] Furthermore, the terminal has additional functionality to detect obstacles and proposes avoidance routes for detected obstacles. The server analyzes the obstacles from the image data and calculates the optimal movement route. This makes it possible to assist movement while ensuring safety.

[0524] As a concrete example, imagine a user walking from the train station to their home. The device detects obstacles along the way, such as steps, utility poles, and vending machines, and provides voice guidance such as, "There's a step on the left," or "Be careful, there's a utility pole on the right." It also provides information like, "The next bus will arrive in 10 minutes," when approaching a bus stop, expanding the user's travel options.

[0525] These features enable visually impaired individuals to travel safely to their destinations and enrich their daily activities. Thus, the present invention provides an effective means to improve the independence and quality of life of visually impaired individuals.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The device detects when the user starts moving, activates its camera, and takes pictures of the surrounding environment.

[0529] Step 2:

[0530] The device transmits the captured video data to the server in real time and requests image analysis.

[0531] Step 3:

[0532] The server analyzes the received video data using an AI algorithm to identify the location and distance of people, obstacles, and signals.

[0533] Step 4:

[0534] The server generates text for voice guidance based on the image analysis results. This includes information such as obstacles and intersections ahead.

[0535] Step 5:

[0536] The server converts the generated voice guidance text into audio data and sends it to the terminal.

[0537] Step 6:

[0538] The device plays the received audio data to the user through its speaker, informing the user of their surroundings.

[0539] Step 7:

[0540] The device obtains the user's location information using its built-in GPS module and sends it to the server.

[0541] Step 8:

[0542] The server uses location information to retrieve information such as the arrival time of the next available public transport.

[0543] Step 9:

[0544] The server converts this traffic information into text and sends it to the terminal as voice guidance.

[0545] Step 10:

[0546] The terminal provides users with transmitted traffic information via voice, assisting them in using public transportation.

[0547] Step 11:

[0548] The terminal constantly monitors for obstacles and immediately sends the information to the server if any are detected.

[0549] Step 12:

[0550] The server analyzes obstacle information, calculates a safe alternative route, and outputs the recommended path as text.

[0551] Step 13:

[0552] The server converts this travel path information into audio data and sends it to the terminal.

[0553] Step 14:

[0554] The device provides voice guidance to the user regarding the provided alternative routes, supporting safe travel.

[0555] (Example 1)

[0556] 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."

[0557] There is a need to provide an environment where visually impaired individuals can safely and efficiently understand their surroundings and act independently. Conventional technologies have limitations in the speed and accuracy of acquiring and analyzing visual information, and real-time mobility assistance has not been sufficient. Furthermore, there was a need to appropriately provide the acquired information as voice guidance and present safe and optimal travel routes.

[0558] 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.

[0559] In this invention, the server includes imaging means for capturing images of the surrounding environment, data processing means for analyzing the acquired video information and generating identification information, and voice conversion means for generating voice instructions based on the generated identification information. This enables visually impaired individuals to recognize their surroundings in real time as voice guidance and move safely and efficiently.

[0560] "Imaging means" refers to a device or system for capturing images of the surrounding environment and acquiring video information.

[0561] "Data processing means" refers to a process or system for analyzing acquired video information and generating identification information.

[0562] "Voice conversion means" refers to a device or system for generating voice instructions based on generated identification information.

[0563] "Voice output means" refers to a device or function for conveying generated voice instructions to the user.

[0564] A "route guidance means" is a function or device that provides appropriate route information to assist users in their travel.

[0565] "Location data collection means" refers to a function or device that acquires the geographical location of a user and handles it as data.

[0566] An "obstacle analysis means" is a process or system for detecting obstacles from acquired video information and sensor information, and for suggesting avoidance routes to those obstacles.

[0567] This invention provides a system to support visually impaired individuals in safely and efficiently perceiving their surroundings and navigating independently. This system utilizes a mobile device equipped with an AI-powered camera to provide real-time information about the surrounding environment as audio.

[0568] The device uses a camera sensor to capture images of the user's surroundings. The resulting video data is quickly transmitted to the server. Encryption technology is used to ensure the security of this data transfer.

[0569] The server utilizes image processing software equipped with deep learning algorithms to analyze the received video data. Specifically, it employs algorithms such as YOLO and SSD for object detection and classification. This allows it to accurately identify elements such as people, obstacles, and traffic lights in the user's surroundings and generate identification information related to them.

[0570] The generated identification information is converted from text to audio data through a speech generation system. This process utilizes services such as Google Text-to-Speech or Amazon Polly as the speech conversion engine. The converted audio data is sent from the server to the device, where it provides instructions and guidance to the user using the device's speaker.

[0571] The terminal obtains the user's location information using its built-in GPS module. Based on this, the server can provide voice guidance regarding the arrival time and route of the next public transport. The terminal also uses an ultrasonic sensor to detect physical obstacles and notifies the user of alternative routes suggested by the server.

[0572] As a concrete example, consider a scenario where a user arrives at a train station and heads from the platform towards the exit. The terminal recognizes facilities such as stairs and elevators within the station and provides guidance such as, "There are stairs ahead. Please use the elevator on the right." Furthermore, if it detects a nearby shop, it can also provide information about a place to rest, such as, "There is a convenience store on the right."

[0573] A concrete example of a prompt message generated using an AI model would be: "Please explain mobility assistance using assistive technology for the visually impaired, and give specific examples of guidance along the way."

[0574] This system will enhance the safety of visually impaired individuals while traveling and enrich their daily lives.

[0575] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0576] Step 1:

[0577] The device uses a camera sensor to continuously capture images of the user's surroundings, acquiring real-time video information. This input video information includes environmental elements such as people, obstacles, and road signs around the user. Specifically, the device provides smooth video data by capturing images at a specific frame rate. This video information is output as basic data necessary for the next analysis step.

[0578] Step 2:

[0579] The device transmits the acquired video information to the server via the internet. During this process, the data is encrypted using a secure communication protocol. The input is the video data captured by the device, and the output is the transmitted video data. Specifically, the communication module within the device packets the data and transmits it efficiently.

[0580] Step 3:

[0581] The server analyzes the received video data. Here, it uses deep learning-based image analysis models, such as YOLO or SSD, to extract and identify objects like people, obstacles, and traffic lights. This method extracts features from the input video data and outputs them as identification information. Specifically, the overall and local features of the image are analyzed through multiple neural network layers.

[0582] Step 4:

[0583] The server generates text for voice guidance based on the identification information generated through analysis. This text is then converted into voice data by a speech conversion system. The input is the identification information generated by the server, and the output is the voice data for voice guidance. In terms of specific operation, natural language generation technology is used to express voice instructions.

[0584] Step 5:

[0585] Audio data is transmitted from the server to the terminal. Upon arrival of the audio data, the terminal plays it through its speaker, allowing the user to receive voice guidance in real time. Specifically, the terminal's speaker system adjusts the volume and sound quality to provide the user with clear and easy-to-understand guidance.

[0586] Step 6:

[0587] The device uses its built-in GPS module to obtain the user's location information. This location information is sent to a server to provide information on upcoming public transport and route guidance. The input is the location data obtained by the GPS, and the output is the location information sent to the server. Specifically, the device's GPS module tracks the location in real time, performing highly accurate location measurements.

[0588] Step 7:

[0589] The server can provide the optimal travel route based on acquired location information and obstacle detection. This information is presented to the user as voice guidance; the input is the user's location and obstacle information, and the output is expressed as guidance content. Specifically, the server runs a route optimization algorithm to generate suggestions that are helpful for the user's movement.

[0590] (Application Example 1)

[0591] 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."

[0592] Visually impaired individuals face challenges in safely and efficiently navigating urban environments and obtaining appropriate information when using public transportation. Current technology is insufficient for obstacle recognition and efficient guidance, making it difficult to improve the independence and quality of life of visually impaired individuals.

[0593] 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.

[0594] In this invention, the server includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and fault detection means. This enables visually impaired individuals to understand their surroundings in real time and travel safely to their destination.

[0595] "Data acquisition methods" refer to technologies used to collect data by photographing the surrounding environment.

[0596] "Data analysis means" refers to processing technology used to analyze acquired data and generate identification information, etc.

[0597] "Voice generation means" refers to technology that generates voice guidance based on identification information generated through analysis.

[0598] "Information output means" refers to technologies for providing users with generated voice guidance and other information.

[0599] "Position signal acquisition means" refers to signal reception and processing technology for accurately acquiring the user's location.

[0600] "Means of providing operational information" refers to technology that provides operational information for means of transportation based on acquired location information.

[0601] "Obstacle detection means" refers to technology that detects obstacles from data and proposes alternative routes to safely avoid them.

[0602] "Generative AI models" refer to AI technology used in data analysis to interpret images and provide voice guidance.

[0603] A "prompt statement" refers to guidelines or instructions for properly operating a generative AI model.

[0604] The system that realizes this invention is a technology that enables visually impaired people to move safely while perceiving their surroundings. The system includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and obstacle detection means.

[0605] The terminal uses a camera built into a device such as a smartphone to capture images of the surrounding environment in real time. The acquired data is sent to a server via the internet. On the server, a generative AI model is run using AI frameworks such as TensorFlow and PyTorch as a means of data analysis, and it identifies obstacles, people, traffic lights, etc. from the acquired data.

[0606] The server uses an AI model to analyze identification information and then generates voice guidance via a speech generation system, employing the Google Cloud Text-to-Speech API or similar speech synthesis technologies. The generated voice data is then delivered to the user in real time through the device's speaker.

[0607] The device also uses its built-in GPS function to acquire the user's current location as a means of obtaining a location signal. This location signal is transmitted to a server, which then provides the user with operational information such as public transport arrival information and recommended routes via an operational information provision system.

[0608] As a concrete example, consider a scenario where a user is traveling from a train station to their home. This system detects steps and utility poles encountered along the way and provides guidance such as, "There is a step ahead," or "Please be careful, there is a utility pole on your right." Furthermore, as the user approaches a bus stop, it provides information such as, "The next bus will arrive in 10 minutes," assisting the user's journey.

[0609] An example of a prompt message is: "I want to develop a system that recognizes surrounding pedestrians, obstacles, and traffic signs in real time and provides voice guidance. Please tell me how to efficiently detect objects and generate voice guidance using Python and TensorFlow."

[0610] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0611] Step 1:

[0612] The device uses a camera to capture images of its surroundings in real time and acquire video data. The input is visual information of the surroundings, and the output is video data. This video data is used for subsequent analysis.

[0613] Step 2:

[0614] The terminal transmits the acquired video data to the server via the internet. At this stage, the input is the video data within the terminal, and the output is the video data within the server. The video data is transmitted in real time via a transmission protocol.

[0615] Step 3:

[0616] The server analyzes received video data using a generative AI model. The input is the received video data, and the output is identification information such as obstacles, people, and traffic lights. Data analysis is performed using TensorFlow or PyTorch, and the model is a pre-trained neural network.

[0617] Step 4:

[0618] The server generates voice guidance based on the identification information obtained through analysis. The input is identification information, and the output is guidance text in sentence format. The voice generation method uses the Google Cloud Text-to-Speech API to generate the voice guidance.

[0619] Step 5:

[0620] The server sends the generated voice guidance data back to the terminal. The input is voice data on the server, and the output is voice data on the terminal. It is transmitted in real time, and the user can receive guidance through the voice assistant.

[0621] Step 6:

[0622] The device uses its built-in GPS to obtain the user's current location. The input is location coordinate data, and the output is GPS information. This information is used to calculate arrival times for public transportation.

[0623] Step 7:

[0624] The server uses GPS information and a service information provision system to provide users with public transport arrival information. The input is GPS data, and the output is service information. For example, it notifies users of the arrival time of the next bus.

[0625] Step 8:

[0626] The server proposes obstacle avoidance routes based on analyzed information and the user's movement history. Input is the user's movement history and environmental data, and output is alternative route guidance. This enables safe and efficient travel.

[0627] 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.

[0628] This invention is a system aimed at enabling visually impaired individuals to understand their surroundings and receive appropriate support based on their emotional state. This system combines a camera-equipped device with an emotion recognition engine to provide visual information as voice guidance while also offering further support based on the user's emotional state.

[0629] (System operation)

[0630] The device captures images of the surrounding environment with its camera while the user is moving and transmits the video data to the server in real time. The server analyzes the video data using an AI algorithm to identify the locations of people and obstacles. Based on the results, it generates voice guidance text, converts it into audio data, and sends it back to the device. The device then plays this audio data back to the user, supplementing the visual information.

[0631] In addition, the device analyzes the user's voice and physical information using an emotion recognition engine to identify their emotional state. Based on the identified emotional state, the server adjusts the tone and content of the voice guidance. For example, if it is determined that the user is feeling stressed, the guidance will be delivered in a calmer tone, and information that promotes relaxation will be provided.

[0632] (Specific example)

[0633] For users heading to a train station, the device guides them through obstacles and landmarks along the way. Simultaneously, it analyzes the user's tone of voice, pace, and general facial expressions, and if it detects anxiety, it provides reassuring voice guidance such as, "It's okay. Just go straight and you'll arrive at the station."

[0634] Furthermore, the device calculates the estimated arrival time based on the user's speed and destination location, and then informs the user of the next train time obtained from the server. In this case as well, it adapts its approach to the situation, summarizing the information concisely or providing detailed explanations depending on the user's emotional state.

[0635] Thus, the present invention supports safe and comfortable travel by not only supplementing visual information but also providing information that takes into account the user's emotions. This will improve the quality of life and promote social participation for visually impaired individuals.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] After startup, the device continuously captures images of its surroundings through its camera and acquires video data.

[0639] Step 2:

[0640] The device transmits the acquired video data to the server in real time and makes requests for image analysis and emotion analysis.

[0641] Step 3:

[0642] The server processes the received video data using an AI algorithm to identify surrounding objects and people. During this process, it also calculates information about their location and distance.

[0643] Step 4:

[0644] The server generates text for voice guidance based on the results of image analysis. This text includes the user's direction of travel, important landmarks, and obstacle information.

[0645] Step 5:

[0646] The server applies emotion recognition algorithms to identify the user's emotional state from their voice and video. It extracts features related to stress, anxiety, and other emotional states.

[0647] Step 6:

[0648] The server adjusts the tone and content of the voice guidance according to the user's emotional state, incorporating kind words and encouraging phrases.

[0649] Step 7:

[0650] The server converts the adjusted voice guidance text into audio data and sends that data to the terminal.

[0651] Step 8:

[0652] The device plays the received audio data to the user through its speaker, conveying environmental information in real time.

[0653] Step 9:

[0654] The device uses its built-in GPS module to obtain the user's current location and sends this information to the server.

[0655] Step 10:

[0656] The server matches location information with public transport data to obtain information on the next available train or bus, and then generates a notification.

[0657] Step 11:

[0658] The server converts the notification content into audio data and sends it to the terminal.

[0659] Step 12:

[0660] The device provides this voice data to the user, guiding them through public transport arrival times and transfer information.

[0661] Step 13:

[0662] The terminal monitors the surrounding environment for continuous obstacle detection and sends information to the server if a new obstacle is detected.

[0663] Step 14:

[0664] The server calculates an alternative route to address the detected obstacle and sends the adjusted navigation instructions as voice data to the terminal.

[0665] Step 15:

[0666] The device provides users with voice guidance to help them avoid obstacles, supporting safe passage.

[0667] (Example 2)

[0668] 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."

[0669] There is a problem in that it is difficult to accurately perceive the surrounding environment and provide appropriate guidance based on the user's emotional state while visually impaired people are traveling. Therefore, improvements in safety and comfort are required.

[0670] 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.

[0671] In this invention, the server includes data acquisition means for acquiring environmental information, data analysis means for analyzing the acquired data and generating feature information, and information generation means for generating guidance information based on the generated feature information. This enables visually impaired individuals to understand their surroundings through voice guidance while moving and to receive guidance that is tailored to the user's emotions.

[0672] "Environmental information" refers to visual or auditory data that indicates the surrounding conditions and changes.

[0673] "Data acquisition means" refers to a device or method for sensing and collecting environmental information.

[0674] "Data analysis means" refers to a device or method for analyzing acquired environmental information and extracting useful characteristic information.

[0675] "Feature information" refers to a collection of information that is considered important or useful, extracted through data analysis.

[0676] "Information generation means" refers to a device or method for creating guidance information to be provided to users based on characteristic information.

[0677] "Information output means" refers to a device or method for transmitting generated guidance information to a user.

[0678] "Emotion recognition means" refers to a device or method that analyzes a user's voice and biometric information to identify their emotional state.

[0679] "Information adjustment means" refers to a device or method for appropriately modifying the content and tone of guidance information according to an identified emotional state.

[0680] "Means of transportation" refer to the transportation systems and technologies that support people's physical movement.

[0681] "Information detection means" refers to a device or method for detecting specific events or situations (e.g., obstacles) using acquired data.

[0682] To implement this invention, a mobile terminal usable by visually impaired persons and a server connected to it via communication are used. The mobile terminal is equipped with a high-resolution camera, a voice input device, and an AI platform, while the server is equipped with a powerful processing unit for data analysis and emotion recognition. Each component operates as follows:

[0683] The device first captures the user's surroundings using a camera, acquiring data in real time. The frame rate and resolution of the captured images are adjusted to ensure that all necessary information for visually impaired individuals is captured. The acquired data is compressed within the device before being transmitted to a server using high-speed communication technology. This communication technology can utilize 5G or Wi-Fi networks.

[0684] To process the received video data, the server performs object detection and feature extraction by combining image recognition libraries and AI models, such as OpenCV and TensorFlow. In particular, it utilizes models with high-precision identification capabilities, such as YOLOv5, for object detection. This allows for the rapid and accurate identification of the locations of people and obstacles.

[0685] Based on these analysis results, the server generates appropriate guidance information. This involves using a generative AI model to construct natural-sounding sentences, which are then converted into audio data using speech synthesis technologies such as the Google Text-to-Speech API. This audio data is then quickly sent to the device and delivered to the user.

[0686] Furthermore, the device collects the user's voice using a microphone and performs emotion recognition in real time. For example, it identifies emotional states such as stress or calmness based on the tone and speed of the voice, and reflects this in the tone and content of the guidance information provided by the server.

[0687] As a concrete example, consider a user using this system while traveling to a train station. The terminal not only provides voice guidance about surrounding obstacles, but also offers reassuring messages based on emotion recognition, such as, "It's okay. Just go straight and you'll arrive at the station."

[0688] A concrete example of a prompt message would be to ask the generating AI model to "analyze the stress level the user is experiencing on their current travel route and generate a guidance message that provides the greatest sense of security."

[0689] This allows visually impaired individuals to receive visual information and emotionally responsive support for safe and comfortable movement. This invention promotes social participation and improves the quality of life for visually impaired individuals.

[0690] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0691] Step 1:

[0692] The device captures visual information of its surroundings using its built-in camera. The input at this time is real-time video data, and the device collects the information at an appropriate resolution and frame rate. The collected video data is first compressed within the device to reduce its data size. The compressed data becomes the output, which is then used in the next step.

[0693] Step 2:

[0694] The compressed video data is sent from the terminal to the server via a high-speed communication network. This process utilizes communication technologies such as 5G and Wi-Fi to transfer the data quickly and securely to the server. The output here is the transmitted compressed video data.

[0695] Step 3:

[0696] The server decompresses the received compressed video data and analyzes it. Using the decompressed raw video data as input, it applies an AI algorithm to detect and identify objects and obstacles within the image. Specifically, it utilizes an object detection model based on OpenCV and YOLOv5. The output consists of the object's position information and features obtained as a result of the analysis.

[0697] Step 4:

[0698] The server generates text for voice guidance based on the analysis results. By using a generative AI model to perform natural language processing, it constructs guidance text that is easily understandable to the user. The input for this process is detected object information, and the output is the generated voice text data.

[0699] Step 5:

[0700] The server uses speech synthesis technology to convert text data into speech data. Specifically, it uses a speech synthesis API to generate natural-sounding speech. The input for this step is the generated text, and the output is the data for the voice guidance.

[0701] Step 6:

[0702] The terminal plays audio data received from the server and provides guidance to the user in real time. The audio data is played through the terminal's speaker. The input here is the received audio data, and the output is clear voice guidance for the user.

[0703] Step 7:

[0704] The device acquires the user's voice via a microphone and analyzes it with an emotion recognition engine. In this step, the user's emotional state is identified based on the voice input data. The results of the emotion analysis are output and used in the next step.

[0705] Step 8:

[0706] The server adjusts the voice guidance based on the user's emotional state. For example, if an emotion indicating stress is detected, it will generate guidance in a calmer tone. The input for this step is the result of the emotion analysis, and the output is the adjusted voice guidance.

[0707] By performing these steps in sequence, we can provide visual information reinforcement and emotionally appropriate guidance to support the mobility of visually impaired individuals.

[0708] (Application Example 2)

[0709] 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."

[0710] To enable visually impaired individuals to move safely and comfortably, it is necessary not only to perceive their surroundings in real time, but also to provide appropriate support tailored to their emotional state at that time. However, conventional technologies have the challenge of not being able to respond flexibly while considering the user's emotional state.

[0711] 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.

[0712] In this invention, the server includes an image acquisition device for capturing the surrounding environment, an image analysis device for analyzing the acquired image data and generating target information, a voice generation device for generating voice guidance based on the generated target information, an emotion recognition device for analyzing the user's voice and physical information and identifying their emotional state, and a voice adjustment device for adjusting the tone and content of the voice guidance based on the identified emotional state. This enables visually impaired individuals to move safely while receiving appropriate support according to their emotional state.

[0713] An "image acquisition device" is a device that has the function of recording the surrounding environment using a camera or other photographic equipment.

[0714] An "image analysis device" is a device that processes acquired image data and has the function of identifying and generating target information such as people and obstacles.

[0715] A "voice generation device" is a device that has the function of creating voice guidance based on analyzed target information.

[0716] A "voice output device" is a device that has the function of allowing users to listen to generated voice guidance.

[0717] An "emotion recognition device" is a device that analyzes a user's voice and physical information to identify their emotional state.

[0718] A "voice adjustment device" is a device that has the function of adjusting the tone and content of voice guidance based on the identified emotional state.

[0719] A "location information acquisition device" is a device that has the function of measuring the user's current location and acquiring that location information.

[0720] An "object detection device" is a device that identifies objects from image data and proposes appropriate avoidance routes.

[0721] The system for implementing this invention has the function of recognizing the surrounding environment and providing appropriate support according to the user's emotional state, so that visually impaired persons can move safely and comfortably.

[0722] The server first receives image data from a terminal that includes an image acquisition device that captures the surrounding environment using a camera. Next, the received image data is processed by an image analysis device to identify objects and obstacles. Then, based on the target information generated by the image analysis device, a voice generation device creates voice guidance, which is then provided to the user by a voice output device.

[0723] Furthermore, the device collects the user's voice through the microphone and physical information acquired by sensors. This information is analyzed by an emotion recognition device to identify the user's emotional state. Based on the identified emotional state, a voice adjustment device adjusts the tone and content of the voice guidance to provide the user with an appropriate response.

[0724] For example, when a user is heading to a train station on a rainy day, the server guides the user to landmarks they can see along the way, and if the user is feeling anxious, it provides information in a calm tone, such as, "It's okay. There's a roof nearby." In addition, location information acquisition devices determine the user's current location and improve convenience by providing timely information about the arrival of transportation services.

[0725] For specific processing, we recommend using OpenCV for image analysis, Google Cloud Speech-to-Text for speech recognition, and TensorFlow or PyTorch for sentiment analysis. This allows for efficient processing of complex data and the provision of information tailored to user needs.

[0726] As an example of how to utilize a generative AI model, a good prompt would be, "Please tell me how a visual guide robot can report surrounding obstacles and adjust its voice tone according to the user's emotions."

[0727] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0728] Step 1:

[0729] The device captures images of its surroundings with its camera and sends the image data to the server in real time. In this step, the image data is the input, the data is compressed for transmission to the server, and the compressed image data is output.

[0730] Step 2:

[0731] The server processes the received image data using an image analysis device to identify target information such as people and obstacles. In this step, compressed image data is used as input, image analysis is performed using OpenCV, and the target information is output.

[0732] Step 3:

[0733] The server generates voice guidance using a voice generation device based on the target information. In this step, the target information is the input, and the voice guidance text is output using natural language generation technology.

[0734] Step 4:

[0735] The terminal provides the user with voice guidance text via a voice output device. In this step, the voice guidance text is input, and voice synthesis is performed to output the voice guidance.

[0736] Step 5:

[0737] The device analyzes the user's voice via the microphone and physical information acquired by sensors using an emotion recognition device. In this step, the user's voice data and physical information are inputs, and the emotional state is output using TensorFlow or PyTorch.

[0738] Step 6:

[0739] The server adjusts the tone and content of the voice guidance using a voice adjustment device based on the identified emotional state. In this step, the emotional state and voice guidance are inputs, and the tone-adjusted voice guidance is output.

[0740] Step 7:

[0741] The terminal uses a location information acquisition device to determine the user's current location and requests arrival information for the appropriate transportation service from the server. In this step, the current location is the input, and transportation service information is output based on that location information.

[0742] Step 8:

[0743] The server receives traffic service information and provides it to the user. In this step, traffic service information is input, and information corresponding to the user's request is output via voice guidance.

[0744] 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.

[0745] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0746] 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.

[0747] [Fourth Embodiment]

[0748] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0749] 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.

[0750] 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).

[0751] 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.

[0752] 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.

[0753] 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).

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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".

[0761] This invention is a system that enables visually impaired individuals to safely and efficiently perceive their surroundings and to move around and live their daily lives independently. This system uses an AI-equipped camera device to provide visual information as real-time voice guidance.

[0762] (System operation)

[0763] The device first captures video data by using its camera to photograph the user's surroundings. The acquired data is sent to a server for image analysis processing. Here, an AI algorithm is used to identify elements such as people, obstacles, and signals, and generate information about them.

[0764] The server creates voice guidance based on the analysis results and formats the guidance content as text. Next, a voice generation system converts the text into voice data and sends it to the terminal. The terminal plays the transmitted voice data to the user in real time through its speaker. This allows the user to understand their surroundings by listening.

[0765] Furthermore, the device uses its built-in GPS function to obtain the user's location information. This location information is sent to a server, which then provides information on the next public transport. The user is notified of estimated arrival times and route suggestions as voice guidance.

[0766] Furthermore, the terminal has additional functionality to detect obstacles and proposes avoidance routes for detected obstacles. The server analyzes the obstacles from the image data and calculates the optimal movement route. This makes it possible to assist movement while ensuring safety.

[0767] As a concrete example, imagine a user walking from the train station to their home. The device detects obstacles along the way, such as steps, utility poles, and vending machines, and provides voice guidance such as, "There's a step on the left," or "Be careful, there's a utility pole on the right." It also provides information like, "The next bus will arrive in 10 minutes," when approaching a bus stop, expanding the user's travel options.

[0768] These features enable visually impaired individuals to travel safely to their destinations and enrich their daily activities. Thus, the present invention provides an effective means to improve the independence and quality of life of visually impaired individuals.

[0769] The following describes the processing flow.

[0770] Step 1:

[0771] The device detects when the user starts moving, activates its camera, and takes pictures of the surrounding environment.

[0772] Step 2:

[0773] The device transmits the captured video data to the server in real time and requests image analysis.

[0774] Step 3:

[0775] The server analyzes the received video data using an AI algorithm to identify the location and distance of people, obstacles, and signals.

[0776] Step 4:

[0777] The server generates text for voice guidance based on the image analysis results. This includes information such as obstacles and intersections ahead.

[0778] Step 5:

[0779] The server converts the generated voice guidance text into audio data and sends it to the terminal.

[0780] Step 6:

[0781] The device plays the received audio data to the user through its speaker, informing the user of their surroundings.

[0782] Step 7:

[0783] The device obtains the user's location information using its built-in GPS module and sends it to the server.

[0784] Step 8:

[0785] The server uses location information to retrieve information such as the arrival time of the next available public transport.

[0786] Step 9:

[0787] The server converts this traffic information into text and sends it to the terminal as voice guidance.

[0788] Step 10:

[0789] The terminal provides users with transmitted traffic information via voice, assisting them in using public transportation.

[0790] Step 11:

[0791] The terminal constantly monitors for obstacles and immediately sends the information to the server if any are detected.

[0792] Step 12:

[0793] The server analyzes obstacle information, calculates a safe alternative route, and outputs the recommended path as text.

[0794] Step 13:

[0795] The server converts this travel path information into audio data and sends it to the terminal.

[0796] Step 14:

[0797] The device provides voice guidance to the user regarding the provided alternative routes, supporting safe travel.

[0798] (Example 1)

[0799] 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".

[0800] There is a need to provide an environment where visually impaired individuals can safely and efficiently understand their surroundings and act independently. Conventional technologies have limitations in the speed and accuracy of acquiring and analyzing visual information, and real-time mobility assistance has not been sufficient. Furthermore, there was a need to appropriately provide the acquired information as voice guidance and present safe and optimal travel routes.

[0801] 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.

[0802] In this invention, the server includes imaging means for capturing images of the surrounding environment, data processing means for analyzing the acquired video information and generating identification information, and voice conversion means for generating voice instructions based on the generated identification information. This enables visually impaired individuals to recognize their surroundings in real time as voice guidance and move safely and efficiently.

[0803] "Imaging means" refers to a device or system for capturing images of the surrounding environment and acquiring video information.

[0804] "Data processing means" refers to a process or system for analyzing acquired video information and generating identification information.

[0805] "Voice conversion means" refers to a device or system for generating voice instructions based on generated identification information.

[0806] "Voice output means" refers to a device or function for conveying generated voice instructions to the user.

[0807] A "route guidance means" is a function or device that provides appropriate route information to assist users in their travel.

[0808] "Location data collection means" refers to a function or device that acquires the geographical location of a user and handles it as data.

[0809] An "obstacle analysis means" is a process or system for detecting obstacles from acquired video information and sensor information, and for suggesting avoidance routes to those obstacles.

[0810] This invention provides a system to support visually impaired individuals in safely and efficiently perceiving their surroundings and navigating independently. This system utilizes a mobile device equipped with an AI-powered camera to provide real-time information about the surrounding environment as audio.

[0811] The device uses a camera sensor to capture images of the user's surroundings. The resulting video data is quickly transmitted to the server. Encryption technology is used to ensure the security of this data transfer.

[0812] The server utilizes image processing software equipped with deep learning algorithms to analyze the received video data. Specifically, it employs algorithms such as YOLO and SSD for object detection and classification. This allows it to accurately identify elements such as people, obstacles, and traffic lights in the user's surroundings and generate identification information related to them.

[0813] The generated identification information is converted from text to audio data through a speech generation system. This process utilizes services such as Google Text-to-Speech or Amazon Polly as the speech conversion engine. The converted audio data is sent from the server to the device, where it provides instructions and guidance to the user using the device's speaker.

[0814] The terminal obtains the user's location information using its built-in GPS module. Based on this, the server can provide voice guidance regarding the arrival time and route of the next public transport. The terminal also uses an ultrasonic sensor to detect physical obstacles and notifies the user of alternative routes suggested by the server.

[0815] As a concrete example, consider a scenario where a user arrives at a train station and heads from the platform towards the exit. The terminal recognizes facilities such as stairs and elevators within the station and provides guidance such as, "There are stairs ahead. Please use the elevator on the right." Furthermore, if it detects a nearby shop, it can also provide information about a place to rest, such as, "There is a convenience store on the right."

[0816] A concrete example of a prompt message generated using an AI model would be: "Please explain mobility assistance using assistive technology for the visually impaired, and give specific examples of guidance along the way."

[0817] This system will enhance the safety of visually impaired individuals while traveling and enrich their daily lives.

[0818] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0819] Step 1:

[0820] The device uses a camera sensor to continuously capture images of the user's surroundings, acquiring real-time video information. This input video information includes environmental elements such as people, obstacles, and road signs around the user. Specifically, the device provides smooth video data by capturing images at a specific frame rate. This video information is output as basic data necessary for the next analysis step.

[0821] Step 2:

[0822] The device transmits the acquired video information to the server via the internet. During this process, the data is encrypted using a secure communication protocol. The input is the video data captured by the device, and the output is the transmitted video data. Specifically, the communication module within the device packets the data and transmits it efficiently.

[0823] Step 3:

[0824] The server analyzes the received video data. Here, it uses deep learning-based image analysis models, such as YOLO or SSD, to extract and identify objects like people, obstacles, and traffic lights. This method extracts features from the input video data and outputs them as identification information. Specifically, the overall and local features of the image are analyzed through multiple neural network layers.

[0825] Step 4:

[0826] The server generates text for voice guidance based on the identification information generated through analysis. This text is then converted into voice data by a speech conversion system. The input is the identification information generated by the server, and the output is the voice data for voice guidance. In terms of specific operation, natural language generation technology is used to express voice instructions.

[0827] Step 5:

[0828] Audio data is transmitted from the server to the terminal. Upon arrival of the audio data, the terminal plays it through its speaker, allowing the user to receive voice guidance in real time. Specifically, the terminal's speaker system adjusts the volume and sound quality to provide the user with clear and easy-to-understand guidance.

[0829] Step 6:

[0830] The device uses its built-in GPS module to obtain the user's location information. This location information is sent to a server to provide information on upcoming public transport and route guidance. The input is the location data obtained by the GPS, and the output is the location information sent to the server. Specifically, the device's GPS module tracks the location in real time, performing highly accurate location measurements.

[0831] Step 7:

[0832] The server can provide the optimal travel route based on acquired location information and obstacle detection. This information is presented to the user as voice guidance; the input is the user's location and obstacle information, and the output is expressed as guidance content. Specifically, the server runs a route optimization algorithm to generate suggestions that are helpful for the user's movement.

[0833] (Application Example 1)

[0834] 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".

[0835] Visually impaired individuals face challenges in safely and efficiently navigating urban environments and obtaining appropriate information when using public transportation. Current technology is insufficient for obstacle recognition and efficient guidance, making it difficult to improve the independence and quality of life of visually impaired individuals.

[0836] 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.

[0837] In this invention, the server includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and fault detection means. This enables visually impaired individuals to understand their surroundings in real time and travel safely to their destination.

[0838] "Data acquisition methods" refer to technologies used to collect data by photographing the surrounding environment.

[0839] "Data analysis means" refers to processing technology used to analyze acquired data and generate identification information, etc.

[0840] "Voice generation means" refers to technology that generates voice guidance based on identification information generated through analysis.

[0841] "Information output means" refers to technologies for providing users with generated voice guidance and other information.

[0842] "Position signal acquisition means" refers to signal reception and processing technology for accurately acquiring the user's location.

[0843] "Means of providing operational information" refers to technology that provides operational information for means of transportation based on acquired location information.

[0844] "Obstacle detection means" refers to technology that detects obstacles from data and proposes alternative routes to safely avoid them.

[0845] "Generative AI models" refer to AI technology used in data analysis to interpret images and provide voice guidance.

[0846] A "prompt statement" refers to guidelines or instructions for properly operating a generative AI model.

[0847] The system that realizes this invention is a technology that enables visually impaired people to move safely while perceiving their surroundings. The system includes data acquisition means, data analysis means, voice generation means, information output means, position signal acquisition means, operation information provision means, and obstacle detection means.

[0848] The terminal uses a camera built into a device such as a smartphone to capture images of the surrounding environment in real time. The acquired data is sent to a server via the internet. On the server, a generative AI model is run using AI frameworks such as TensorFlow and PyTorch as a means of data analysis, and it identifies obstacles, people, traffic lights, etc. from the acquired data.

[0849] The server uses an AI model to analyze identification information and then generates voice guidance via a speech generation system, employing the Google Cloud Text-to-Speech API or similar speech synthesis technologies. The generated voice data is then delivered to the user in real time through the device's speaker.

[0850] The device also uses its built-in GPS function to acquire the user's current location as a means of obtaining a location signal. This location signal is transmitted to a server, which then provides the user with operational information such as public transport arrival information and recommended routes via an operational information provision system.

[0851] As a concrete example, consider a scenario where a user is traveling from a train station to their home. This system detects steps and utility poles encountered along the way and provides guidance such as, "There is a step ahead," or "Please be careful, there is a utility pole on your right." Furthermore, as the user approaches a bus stop, it provides information such as, "The next bus will arrive in 10 minutes," assisting the user's journey.

[0852] An example of a prompt message is: "I want to develop a system that recognizes surrounding pedestrians, obstacles, and traffic signs in real time and provides voice guidance. Please tell me how to efficiently detect objects and generate voice guidance using Python and TensorFlow."

[0853] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0854] Step 1:

[0855] The device uses a camera to capture images of its surroundings in real time and acquire video data. The input is visual information of the surroundings, and the output is video data. This video data is used for subsequent analysis.

[0856] Step 2:

[0857] The terminal transmits the acquired video data to the server via the internet. At this stage, the input is the video data within the terminal, and the output is the video data within the server. The video data is transmitted in real time via a transmission protocol.

[0858] Step 3:

[0859] The server analyzes received video data using a generative AI model. The input is the received video data, and the output is identification information such as obstacles, people, and traffic lights. Data analysis is performed using TensorFlow or PyTorch, and the model is a pre-trained neural network.

[0860] Step 4:

[0861] The server generates voice guidance based on the identification information obtained through analysis. The input is identification information, and the output is guidance text in sentence format. The voice generation method uses the Google Cloud Text-to-Speech API to generate the voice guidance.

[0862] Step 5:

[0863] The server sends the generated voice guidance data back to the terminal. The input is voice data on the server, and the output is voice data on the terminal. It is transmitted in real time, and the user can receive guidance through the voice assistant.

[0864] Step 6:

[0865] The device uses its built-in GPS to obtain the user's current location. The input is location coordinate data, and the output is GPS information. This information is used to calculate arrival times for public transportation.

[0866] Step 7:

[0867] The server uses GPS information and a service information provision system to provide users with public transport arrival information. The input is GPS data, and the output is service information. For example, it notifies users of the arrival time of the next bus.

[0868] Step 8:

[0869] The server proposes obstacle avoidance routes based on analyzed information and the user's movement history. Input is the user's movement history and environmental data, and output is alternative route guidance. This enables safe and efficient travel.

[0870] 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.

[0871] This invention is a system aimed at enabling visually impaired individuals to understand their surroundings and receive appropriate support based on their emotional state. This system combines a camera-equipped device with an emotion recognition engine to provide visual information as voice guidance while also offering further support based on the user's emotional state.

[0872] (System operation)

[0873] The device captures images of the surrounding environment with its camera while the user is moving and transmits the video data to the server in real time. The server analyzes the video data using an AI algorithm to identify the locations of people and obstacles. Based on the results, it generates voice guidance text, converts it into audio data, and sends it back to the device. The device then plays this audio data back to the user, supplementing the visual information.

[0874] In addition, the device analyzes the user's voice and physical information using an emotion recognition engine to identify their emotional state. Based on the identified emotional state, the server adjusts the tone and content of the voice guidance. For example, if it is determined that the user is feeling stressed, the guidance will be delivered in a calmer tone, and information that promotes relaxation will be provided.

[0875] (Specific example)

[0876] For users heading to a train station, the device guides them through obstacles and landmarks along the way. Simultaneously, it analyzes the user's tone of voice, pace, and general facial expressions, and if it detects anxiety, it provides reassuring voice guidance such as, "It's okay. Just go straight and you'll arrive at the station."

[0877] Furthermore, the device calculates the estimated arrival time based on the user's speed and destination location, and then informs the user of the next train time obtained from the server. In this case as well, it adapts its approach to the situation, summarizing the information concisely or providing detailed explanations depending on the user's emotional state.

[0878] Thus, the present invention supports safe and comfortable travel by not only supplementing visual information but also providing information that takes into account the user's emotions. This will improve the quality of life and promote social participation for visually impaired individuals.

[0879] The following describes the processing flow.

[0880] Step 1:

[0881] After startup, the device continuously captures images of its surroundings through its camera and acquires video data.

[0882] Step 2:

[0883] The device transmits the acquired video data to the server in real time and makes requests for image analysis and emotion analysis.

[0884] Step 3:

[0885] The server processes the received video data using an AI algorithm to identify surrounding objects and people. During this process, it also calculates information about their location and distance.

[0886] Step 4:

[0887] The server generates text for voice guidance based on the results of image analysis. This text includes the user's direction of travel, important landmarks, and obstacle information.

[0888] Step 5:

[0889] The server applies emotion recognition algorithms to identify the user's emotional state from their voice and video. It extracts features related to stress, anxiety, and other emotional states.

[0890] Step 6:

[0891] The server adjusts the tone and content of the voice guidance according to the user's emotional state, incorporating kind words and encouraging phrases.

[0892] Step 7:

[0893] The server converts the adjusted voice guidance text into audio data and sends that data to the terminal.

[0894] Step 8:

[0895] The device plays the received audio data to the user through its speaker, conveying environmental information in real time.

[0896] Step 9:

[0897] The device uses its built-in GPS module to obtain the user's current location and sends this information to the server.

[0898] Step 10:

[0899] The server matches location information with public transport data to obtain information on the next available train or bus, and then generates a notification.

[0900] Step 11:

[0901] The server converts the notification content into audio data and sends it to the terminal.

[0902] Step 12:

[0903] The device provides this voice data to the user, guiding them through public transport arrival times and transfer information.

[0904] Step 13:

[0905] The terminal monitors the surrounding environment for continuous obstacle detection and sends information to the server if a new obstacle is detected.

[0906] Step 14:

[0907] The server calculates an alternative route to address the detected obstacle and sends the adjusted navigation instructions as voice data to the terminal.

[0908] Step 15:

[0909] The device provides users with voice guidance to help them avoid obstacles, supporting safe passage.

[0910] (Example 2)

[0911] 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".

[0912] There is a problem in that it is difficult to accurately perceive the surrounding environment and provide appropriate guidance based on the user's emotional state while visually impaired people are traveling. Therefore, improvements in safety and comfort are required.

[0913] 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.

[0914] In this invention, the server includes data acquisition means for acquiring environmental information, data analysis means for analyzing the acquired data and generating feature information, and information generation means for generating guidance information based on the generated feature information. This enables visually impaired individuals to understand their surroundings through voice guidance while moving and to receive guidance that is tailored to the user's emotions.

[0915] "Environmental information" refers to visual or auditory data that indicates the surrounding conditions and changes.

[0916] "Data acquisition means" refers to a device or method for sensing and collecting environmental information.

[0917] "Data analysis means" refers to a device or method for analyzing acquired environmental information and extracting useful characteristic information.

[0918] "Feature information" refers to a collection of information that is considered important or useful, extracted through data analysis.

[0919] "Information generation means" refers to a device or method for creating guidance information to be provided to users based on characteristic information.

[0920] "Information output means" refers to a device or method for transmitting generated guidance information to a user.

[0921] "Emotion recognition means" refers to a device or method that analyzes a user's voice and biometric information to identify their emotional state.

[0922] "Information adjustment means" refers to a device or method for appropriately modifying the content and tone of guidance information according to an identified emotional state.

[0923] "Means of transportation" refer to the transportation systems and technologies that support people's physical movement.

[0924] "Information detection means" refers to a device or method for detecting specific events or situations (e.g., obstacles) using acquired data.

[0925] To implement this invention, a mobile terminal usable by visually impaired persons and a server connected to it via communication are used. The mobile terminal is equipped with a high-resolution camera, a voice input device, and an AI platform, while the server is equipped with a powerful processing unit for data analysis and emotion recognition. Each component operates as follows:

[0926] The device first captures the user's surroundings using a camera, acquiring data in real time. The frame rate and resolution of the captured images are adjusted to ensure that all necessary information for visually impaired individuals is captured. The acquired data is compressed within the device before being transmitted to a server using high-speed communication technology. This communication technology can utilize 5G or Wi-Fi networks.

[0927] To process the received video data, the server performs object detection and feature extraction by combining image recognition libraries and AI models, such as OpenCV and TensorFlow. In particular, it utilizes models with high-precision identification capabilities, such as YOLOv5, for object detection. This allows for the rapid and accurate identification of the locations of people and obstacles.

[0928] Based on these analysis results, the server generates appropriate guidance information. This involves using a generative AI model to construct natural-sounding sentences, which are then converted into audio data using speech synthesis technologies such as the Google Text-to-Speech API. This audio data is then quickly sent to the device and delivered to the user.

[0929] Furthermore, the device collects the user's voice using a microphone and performs emotion recognition in real time. For example, it identifies emotional states such as stress or calmness based on the tone and speed of the voice, and reflects this in the tone and content of the guidance information provided by the server.

[0930] As a concrete example, consider a user using this system while traveling to a train station. The terminal not only provides voice guidance about surrounding obstacles, but also offers reassuring messages based on emotion recognition, such as, "It's okay. Just go straight and you'll arrive at the station."

[0931] A concrete example of a prompt message would be to ask the generating AI model to "analyze the stress level the user is experiencing on their current travel route and generate a guidance message that provides the greatest sense of security."

[0932] This allows visually impaired individuals to receive visual information and emotionally responsive support for safe and comfortable movement. This invention promotes social participation and improves the quality of life for visually impaired individuals.

[0933] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0934] Step 1:

[0935] The device captures visual information of its surroundings using its built-in camera. The input at this time is real-time video data, and the device collects the information at an appropriate resolution and frame rate. The collected video data is first compressed within the device to reduce its data size. The compressed data becomes the output, which is then used in the next step.

[0936] Step 2:

[0937] The compressed video data is sent from the terminal to the server via a high-speed communication network. This process utilizes communication technologies such as 5G and Wi-Fi to transfer the data quickly and securely to the server. The output here is the transmitted compressed video data.

[0938] Step 3:

[0939] The server decompresses the received compressed video data and analyzes it. Using the decompressed raw video data as input, it applies an AI algorithm to detect and identify objects and obstacles within the image. Specifically, it utilizes an object detection model based on OpenCV and YOLOv5. The output consists of the object's position information and features obtained as a result of the analysis.

[0940] Step 4:

[0941] The server generates text for voice guidance based on the analysis results. By using a generative AI model to perform natural language processing, it constructs guidance text that is easily understandable to the user. The input for this process is detected object information, and the output is the generated voice text data.

[0942] Step 5:

[0943] The server uses speech synthesis technology to convert text data into speech data. Specifically, it uses a speech synthesis API to generate natural-sounding speech. The input for this step is the generated text, and the output is the data for the voice guidance.

[0944] Step 6:

[0945] The terminal plays audio data received from the server and provides guidance to the user in real time. The audio data is played through the terminal's speaker. The input here is the received audio data, and the output is clear voice guidance for the user.

[0946] Step 7:

[0947] The device acquires the user's voice via a microphone and analyzes it with an emotion recognition engine. In this step, the user's emotional state is identified based on the voice input data. The results of the emotion analysis are output and used in the next step.

[0948] Step 8:

[0949] The server adjusts the voice guidance based on the user's emotional state. For example, if an emotion indicating stress is detected, it will generate guidance in a calmer tone. The input for this step is the result of the emotion analysis, and the output is the adjusted voice guidance.

[0950] By performing these steps in sequence, we can provide visual information reinforcement and emotionally appropriate guidance to support the mobility of visually impaired individuals.

[0951] (Application Example 2)

[0952] 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".

[0953] To enable visually impaired individuals to move safely and comfortably, it is necessary not only to perceive their surroundings in real time, but also to provide appropriate support tailored to their emotional state at that time. However, conventional technologies have the challenge of not being able to respond flexibly while considering the user's emotional state.

[0954] 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.

[0955] In this invention, the server includes an image acquisition device for capturing the surrounding environment, an image analysis device for analyzing the acquired image data and generating target information, a voice generation device for generating voice guidance based on the generated target information, an emotion recognition device for analyzing the user's voice and physical information and identifying their emotional state, and a voice adjustment device for adjusting the tone and content of the voice guidance based on the identified emotional state. This enables visually impaired individuals to move safely while receiving appropriate support according to their emotional state.

[0956] An "image acquisition device" is a device that has the function of recording the surrounding environment using a camera or other photographic equipment.

[0957] An "image analysis device" is a device that processes acquired image data and has the function of identifying and generating target information such as people and obstacles.

[0958] A "voice generation device" is a device that has the function of creating voice guidance based on analyzed target information.

[0959] A "voice output device" is a device that has the function of allowing users to listen to generated voice guidance.

[0960] An "emotion recognition device" is a device that analyzes a user's voice and physical information to identify their emotional state.

[0961] A "voice adjustment device" is a device that has the function of adjusting the tone and content of voice guidance based on the identified emotional state.

[0962] A "location information acquisition device" is a device that has the function of measuring the user's current location and acquiring that location information.

[0963] An "object detection device" is a device that identifies objects from image data and proposes appropriate avoidance routes.

[0964] The system for implementing this invention has the function of recognizing the surrounding environment and providing appropriate support according to the user's emotional state, so that visually impaired persons can move safely and comfortably.

[0965] The server first receives image data from a terminal that includes an image acquisition device that captures the surrounding environment using a camera. Next, the received image data is processed by an image analysis device to identify objects and obstacles. Then, based on the target information generated by the image analysis device, a voice generation device creates voice guidance, which is then provided to the user by a voice output device.

[0966] Furthermore, the device collects the user's voice through the microphone and physical information acquired by sensors. This information is analyzed by an emotion recognition device to identify the user's emotional state. Based on the identified emotional state, a voice adjustment device adjusts the tone and content of the voice guidance to provide the user with an appropriate response.

[0967] For example, when a user is heading to a train station on a rainy day, the server guides the user to landmarks they can see along the way, and if the user is feeling anxious, it provides information in a calm tone, such as, "It's okay. There's a roof nearby." In addition, location information acquisition devices determine the user's current location and improve convenience by providing timely information about the arrival of transportation services.

[0968] For specific processing, we recommend using OpenCV for image analysis, Google Cloud Speech-to-Text for speech recognition, and TensorFlow or PyTorch for sentiment analysis. This allows for efficient processing of complex data and the provision of information tailored to user needs.

[0969] As an example of how to utilize a generative AI model, a good prompt would be, "Please tell me how a visual guide robot can report surrounding obstacles and adjust its voice tone according to the user's emotions."

[0970] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0971] Step 1:

[0972] The device captures images of its surroundings with its camera and sends the image data to the server in real time. In this step, the image data is the input, the data is compressed for transmission to the server, and the compressed image data is output.

[0973] Step 2:

[0974] The server processes the received image data using an image analysis device to identify target information such as people and obstacles. In this step, compressed image data is used as input, image analysis is performed using OpenCV, and the target information is output.

[0975] Step 3:

[0976] The server generates voice guidance using a voice generation device based on the target information. In this step, the target information is the input, and the voice guidance text is output using natural language generation technology.

[0977] Step 4:

[0978] The terminal provides the user with voice guidance text via a voice output device. In this step, the voice guidance text is input, and voice synthesis is performed to output the voice guidance.

[0979] Step 5:

[0980] The device analyzes the user's voice via the microphone and physical information acquired by sensors using an emotion recognition device. In this step, the user's voice data and physical information are inputs, and the emotional state is output using TensorFlow or PyTorch.

[0981] Step 6:

[0982] The server adjusts the tone and content of the voice guidance using a voice adjustment device based on the identified emotional state. In this step, the emotional state and voice guidance are inputs, and the tone-adjusted voice guidance is output.

[0983] Step 7:

[0984] The terminal uses a location information acquisition device to determine the user's current location and requests arrival information for the appropriate transportation service from the server. In this step, the current location is the input, and transportation service information is output based on that location information.

[0985] Step 8:

[0986] The server receives traffic service information and provides it to the user. In this step, traffic service information is input, and information corresponding to the user's request is output via voice guidance.

[0987] 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.

[0988] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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.

[0993] 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.

[0994] 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.

[0995] 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."

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] 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.

[1003] 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.

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] The following is further disclosed regarding the embodiments described above.

[1009] (Claim 1)

[1010] A means for acquiring images to photograph the surrounding environment,

[1011] Image analysis means for analyzing acquired image data and generating identification information,

[1012] A voice generation means that generates voice guidance based on the generated identification information,

[1013] A voice output means that provides the generated voice guidance to the user,

[1014] A system that includes this.

[1015] (Claim 2)

[1016] The system further includes a means for acquiring the user's location information,

[1017] The system according to claim 1, which provides public transport arrival information based on acquired location information.

[1018] (Claim 3)

[1019] The system according to claim 1, further comprising obstacle detection means for detecting obstacles from acquired image data and proposing avoidance routes.

[1020] "Example 1"

[1021] (Claim 1)

[1022] An imaging device for photographing the surrounding environment,

[1023] A data processing means that analyzes acquired video information to generate identification information,

[1024] A voice conversion means that generates voice instructions based on the generated identification information,

[1025] A voice output means that provides the generated voice instructions to the user,

[1026] A route guidance means that provides route information for assistance in movement,

[1027] A system that includes this.

[1028] (Claim 2)

[1029] The system further includes location data collection means for collecting user location data,

[1030] The system according to claim 1, which provides arrival information for transportation services based on collected location data.

[1031] (Claim 3)

[1032] The system according to claim 1, further comprising obstacle analysis means for detecting obstacles from acquired video information and suggesting avoidance routes.

[1033] "Application Example 1"

[1034] (Claim 1)

[1035] A means of acquiring data for photographing the surrounding environment,

[1036] A data analysis means that analyzes acquired data to generate identification information,

[1037] A voice generation means that generates voice guidance based on the generated identification information,

[1038] Information output means for providing the generated voice guidance to the user,

[1039] A means for acquiring a position signal to obtain the user's position,

[1040] An operation information providing means that provides operation information of a means of transport based on acquired position signals,

[1041] A fault detection means that detects faults from acquired data and proposes alternative routes,

[1042] A system that includes this.

[1043] (Claim 2)

[1044] The system according to claim 1, which notifies the user of operational information via an audio output means.

[1045] (Claim 3)

[1046] The system according to claim 1, wherein a data analysis means interprets an image using a generative AI model, and an audio output means provides voice guidance based on a prompt sentence.

[1047] "Example 2 of combining an emotion engine"

[1048] (Claim 1)

[1049] A means of acquiring data for obtaining environmental information,

[1050] A data analysis means that analyzes acquired data to generate feature information,

[1051] Information generation means for generating guidance information based on generated feature information,

[1052] An information output means that provides the generated guidance information to the user,

[1053] An emotion recognition means for identifying the emotional state of the user,

[1054] Information adjustment means that adjusts guidance information based on identified emotional states,

[1055] A system that includes this.

[1056] (Claim 2)

[1057] Further means of obtaining the user's location information,

[1058] The system according to claim 1, which provides arrival information of a means of transport based on acquired location information.

[1059] (Claim 3)

[1060] The system according to claim 1, further comprising information detection means for detecting obstacles from acquired data and proposing avoidance routes.

[1061] "Application example 2 when combining with an emotional engine"

[1062] (Claim 1)

[1063] An image acquisition device for capturing the surrounding environment,

[1064] An image analysis device that analyzes acquired image data to generate target information,

[1065] A voice generation device that generates voice guidance based on the generated target information,

[1066] An audio output device that provides the generated audio guidance to the user,

[1067] An emotion recognition device that analyzes the user's voice and physical information to identify their emotional state,

[1068] A voice adjustment device that adjusts the tone and content of voice guidance based on identified emotional states,

[1069] A system that includes this.

[1070] (Claim 2)

[1071] The device further includes a location information acquisition device that acquires the user's location information.

[1072] The system according to claim 1, which provides arrival information for a transportation service based on acquired location information.

[1073] (Claim 3)

[1074] The system according to claim 1, further comprising an object detection device that detects objects from acquired image data and proposes an avoidance route. [Explanation of Symbols]

[1075] 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 images to photograph the surrounding environment, Image analysis means for analyzing acquired image data and generating identification information, A voice generation means that generates voice guidance based on the generated identification information, A voice output means that provides the generated voice guidance to the user, A system that includes this.

2. The system further includes a means for acquiring the user's location information, The system according to claim 1, which provides public transport arrival information based on acquired location information.

3. The system according to claim 1, further comprising obstacle detection means for detecting obstacles from acquired image data and proposing avoidance routes.

Images