System

Abstract

A system is provided.SOLUTION: A system comprising: means for capturing video data of an environment using a camera; means for transmitting the captured video data to a server; means for analyzing the video data and detecting an object or text by the server; means for receiving a voice command using a microphone; means for converting the voice command into text; means for generating feedback information based on the voice command and the analysis result by the server; and means for providing the feedback information to a user by voice.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] People with visual impairments have difficulty obtaining visual information in their daily lives, which causes many difficulties. For example, they need assistance in a variety of situations, such as getting directions when going out, choosing menu items at a restaurant, and knowing the location of objects at home. Current support tools are limited and insufficient for people with visual impairments to live independently. Therefore, there is a need for comprehensive support systems that will enable people with visual impairments to live more independently and facilitate their participation in society. [Means for solving the problem]

[0005] The present invention provides a system that provides comprehensive support for the lives of visually impaired people by combining devices including cameras, microphones, and speakers with AI technology. Specifically, a camera is used to capture surrounding video data and send that data to a server. The server analyzes the captured video data to detect objects and text. Voice commands received using a microphone are converted into text, and feedback information is generated on the server based on the analysis results and the voice commands. The generated feedback information is provided to the user via voice, allowing visually impaired people to obtain the information they need in real time. In this way, the present invention aims to provide an environment that makes it easier for visually impaired people to become independent.

[0006] A "camera" is a device for capturing video data.

[0007] A "server" is a computer system that receives and processes data sent from a client.

[0008] "Video data" is digital data of visual information captured by a camera.

[0009] "Analysis" refers to the process of analyzing and evaluating digital data.

[0010] "Object detection" is a technology that identifies specific objects from video data and extracts their positions and attributes.

[0011] "Text" is information that has been converted from audio or video data into a string of characters.

[0012] A "voice command" is a voice input containing instructions or requests made by a user to a system.

[0013] "Feedback information" is response information to the user that is generated based on the analysis results and the voice command.

[0014] A "speaker" is a device for reproducing digital audio data as an audio output.

[0015] "User" refers to individuals, including visually impaired people, who use this support system.

[0016] The "support system" is a comprehensive system for supporting visually impaired people, including a camera, microphone, speaker, server, and analysis means. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention provides a support system that makes it easy for visually impaired people to obtain real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[0039] First, the device activates the camera and captures video data of the surrounding area. The captured video data is then sent over the network to a server. Once the server receives the video data, it analyzes it using an AI model to detect objects and text within the video.

[0040] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server and converted into text data using voice recognition technology. For example, if a user asks a question such as "Where is the next traffic light?", the voice is converted into text.

[0041] The server generates the necessary feedback information for the user based on the converted text data and the results of video analysis. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[0042] The generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to understand the surrounding situation in real time and take appropriate action.

[0043] As a specific example, if a user wants a menu to be read aloud at a restaurant, the user would say into the microphone, "Please read the menu to me." The device would then capture a video of the menu with its camera and send it to the server. The server would then analyze the video and extract the text information written on the menu. This text information would then be generated as voice feedback and read aloud from the device's speaker. This would allow the user to accurately understand the menu contents and place their order smoothly.

[0044] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[0045] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[0049] The terminal initializes the camera device.

[0050] It captures a single frame from the camera and stores the data in memory.

[0051] Releases the camera device and ends the capture process.

[0052] Step 2:

[0053] The device transmits the captured video data to the server.

[0054] The terminal converts the captured video data into an appropriate format.

[0055] The converted data is transmitted to a server via a network.

[0056] The server receives the video data.

[0057] Step 3:

[0058] The server analyzes the video data and detects objects and text.

[0059] The server inputs the received video data into the AI ​​model.

[0060] The AI ​​model analyzes the video and detects objects and text within it.

[0061] The detection results (object type, location information, etc.) are extracted and stored in memory.

[0062] Step 4:

[0063] The device uses a microphone to capture the user's voice commands.

[0064] The terminal initializes the microphone device.

[0065] The user issues voice commands such as instructions and questions into the microphone.

[0066] The device captures audio from the microphone and saves it as audio data.

[0067] Step 5:

[0068] The device sends the captured audio data to the server.

[0069] The terminal converts the captured audio data into an appropriate format.

[0070] The converted voice data is transmitted to a server via a network.

[0071] The server receives the audio data.

[0072] Step 6:

[0073] The server converts the audio data into text.

[0074] The server inputs the received speech data into a speech recognition model.

[0075] A speech recognition model analyzes the audio data and converts it into text.

[0076] The converted text data is stored in memory.

[0077] Step 7:

[0078] The server generates feedback information based on voice commands and video analysis results.

[0079] The server acquires the text data of the voice command and the video analysis results.

[0080] Based on this data, the AI ​​model generates feedback.

[0081] Save the generated feedback information in text format.

[0082] Step 8:

[0083] The server transmits the generated feedback information to the terminal.

[0084] The server converts the generated feedback information into an appropriate format.

[0085] The converted data is transmitted to the terminal via the network.

[0086] The terminal receives the feedback information.

[0087] Step 9:

[0088] The device converts the feedback information into audio and plays it through the speaker.

[0089] The terminal inputs the received feedback information into a text-to-speech engine.

[0090] A text-to-speech engine converts the feedback information into audio.

[0091] The terminal reproduces the generated audio from a speaker and provides it to the user.

[0092] This series of steps allows visually impaired people to receive real-time information about their surroundings, improving their quality of life.

[0093] Example 1

[0094] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0095] It is difficult for visually impaired people to obtain real-time information about their surroundings in their daily lives. Particularly, locating objects outdoors or indoors, reading restaurant menus, and getting directions are problematic. Systems that solve these problems and support the visually impaired are needed to enable them to live independently.

[0096] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0097] In this invention, the server includes means for compressing and transferring received video data in real time, means for analyzing objects and text in the video using an AI model through deep learning, means for processing voice commands using voice recognition technology and converting them into text data, means for generating feedback appropriate for the user in natural language using a generative AI model, and means for transmitting feedback information with low latency using a communication protocol, thereby enabling visually impaired people to grasp their surroundings in real time and receive appropriate feedback.

[0098] A "camera" is a device that captures optical images and converts them into digital data.

[0099] "Video data" refers to image information captured by a camera expressed in digital format.

[0100] A "server" is a high-performance computer system that processes and stores data over a network.

[0101] A "microphone" is a device that captures sound as an acoustic signal and converts it into digital data.

[0102] A "voice command" is a voice instruction given by a user, which is an input that the system recognizes and processes.

[0103] "Text data" is a voice command expressed as text information.

[0104] "Feedback information" refers to instructions and guidance information provided by the system based on the analysis results and user requests.

[0105] "Real-time" refers to a state in which processing and response are carried out immediately without delay.

[0106] An "AI model" is an algorithm trained based on machine learning that is used to analyze data and make predictions.

[0107] "Deep learning" is a technology that uses multi-layer neural networks to extract and learn from data features.

[0108] "Speech recognition technology" is a technology that analyzes voice as digital data and converts it into text.

[0109] A "generative AI model" is an AI algorithm that generates output in natural language based on input data.

[0110] A "communication protocol" is a set of rules and procedures for sending and receiving data over a network.

[0111] "Low latency" refers to minimizing the time it takes to send, receive, and process data.

[0112] This invention is a system that supports visually impaired people in obtaining real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[0113] First, the device is equipped with a camera and microphone. The device activates the camera and captures video data of the surrounding area. This video data is then sent to a server via a network. Specifically, technology is used to compress the video data in real time and transfer it with low latency.

[0114] The server analyzes the received video data using an AI model, which uses deep learning object detection algorithms, such as the YOLO (You Only Look Once) model, to quickly and accurately detect objects and text in the video.

[0115] The device then uses a microphone to capture the user's voice commands. For example, when the user asks, "Where is the next traffic light?", the device sends the voice data to a server. The server then uses voice recognition technology (e.g., Google Speech-to-Text API) to convert the voice data into text data.

[0116] The server generates the necessary feedback information for the user based on the converted text data and the video analysis results. To generate the feedback, a generative AI model (such as GPT-3) is used to create feedback in natural language. For example, if a traffic light is detected through video analysis and its location is identified, the server generates feedback such as, "The next traffic light is 50 meters ahead on the right."

[0117] The generated feedback is sent to the device with low latency using a communication protocol, and the device's speaker provides this feedback information to the user via audio, allowing the user to understand the surrounding situation in real time and take appropriate action.

[0118] As a specific example of use, consider the case where a user wants to have a menu read aloud at a restaurant. In this case, the user requests, "Please read the menu aloud," into the microphone. The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video, extracts the text information written on the menu, generates it as voice feedback, and reads it aloud from the device's speaker. This allows the user to accurately understand the menu contents and place their order smoothly.

[0119] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[0120] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1:

[0123] The device activates the camera. The user operates the device to point the camera at the surroundings and capture video data. The captured video data is temporarily stored inside the device. The input is the camera, and the output is the captured video data. Specifically, the camera continuously captures frames and converts them into digital data.

[0124] Step 2:

[0125] The device compresses the video data captured by the device and sends it to the server via the network. The input is the captured video data, and the output is the compressed video data. Specifically, the device uses a video data compression algorithm to reduce the data volume and improve the transmission speed.

[0126] Step 3:

[0127] The server analyzes the received video data using an AI model. The input is compressed video data, and the output is the analysis results (location information of objects and text). Specifically, the server uses an AI model (for example, YOLO) to detect objects and text in the video, and obtains location information as a result.

[0128] Step 4:

[0129] The device activates the microphone and captures the user's voice command. The input is the user's speech, and the output is the captured voice data. Specifically, the microphone converts the acoustic signal into digital data and temporarily stores it.

[0130] Step 5:

[0131] The terminal transmits the captured audio data to the server. The input is the audio data, and the output is the audio data transmitted to the server. Specifically, the data is transmitted in real time via the network.

[0132] Step 6:

[0133] The server receives the voice data and converts it into text data using speech recognition technology. The input is the transmitted voice data, and the output is the converted text data. Specifically, speech recognition technology such as the Google Speech-to-Text API is used to convert the voice into text information.

[0134] Step 7:

[0135] The server generates feedback information based on the text data and video analysis results. The input is the converted text data and video analysis results, and the output is the generated feedback information. Specifically, it uses a generative AI model (e.g., GPT-3) to generate natural language feedback for the user.

[0136] Step 8:

[0137] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the feedback information sent to the terminal. Specifically, the data is sent with low latency using a communication protocol.

[0138] Step 9:

[0139] The device's speaker provides the user with audible feedback. The input is the transmitted feedback information, and the output is the feedback information provided as audio. Specifically, text is converted into audio using speech synthesis technology and output from the speaker.

[0140] Through the above processing steps, this system enables visually impaired people to understand their surroundings in real time and receive appropriate feedback.

[0141] (Application example 1)

[0142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0143] When visually impaired people use food delivery services, it is extremely difficult for them to understand the menu contents and delivery status. The lack of an appropriate means to confirm order details and track delivery locations without relying on visual information makes it difficult for them to order and receive meals autonomously. To solve this problem, a system is needed that allows visually impaired people to obtain real-time information about food delivery using voice commands.

[0144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0145] In this invention, the server includes a means for a visually impaired person to obtain information about food delivery services using voice commands, a means including a function to read out restaurant menus, and a means for notifying the delivery location and time by voice, thereby enabling a visually impaired person to check menu contents, confirm an order, and track the delivery location when using a food delivery service using voice commands.

[0146] A "camera" is a device for capturing video data of the surroundings.

[0147] A "server" is a device that has the computational resources to receive and analyze captured video data.

[0148] A "microphone" is a device for receiving voice commands.

[0149] A "voice command" is a voice instruction given by the user through a microphone.

[0150] "Video data" is data that includes visual information captured by a camera.

[0151] "Text data" is data obtained by converting a voice command into text format.

[0152] "Object detection" is a process of recognizing and identifying objects present in video data.

[0153] "Feedback information" is information for the user that is generated by the server based on the analysis results and voice commands.

[0154] "Blind people" refers to people who have visual impairments.

[0155] A "food delivery service" is a service that allows users to order food online and receive it via delivery.

[0156] "Menu" means the list of food offered by a restaurant or food delivery page.

[0157] "Voice notification" refers to the act of providing the generated feedback information to the user as voice.

[0158] "Delivery location tracking" is the process of confirming and notifying the current location of a food delivery person.

[0159] This invention is a system to support visually impaired people to use food delivery services safely and smoothly. This system is mainly composed of a camera, a microphone, a server, and a speaker. These elements work together to provide necessary information to visually impaired people in real time.

[0160] First, when a user speaks a voice command into the microphone, the microphone captures the voice data and sends it to the server. Voice commands include "read me the menu," "tell me the status of my order," "check delivery location," etc. The server then uses voice recognition technology to convert the voice data into text data.

[0161] Next, if a user wants to check the menu of a food delivery service, they use the device's camera to capture a video of the menu. This video data is sent to the server, which then analyzes the video data using a generative AI model to extract the text information of the menu. The extracted text information is converted into audio data and provided to the user through a speaker.

[0162] Specifically, the following scenarios are possible:

[0163] For example, if a visually impaired person issues the voice command "Read me the menu," the camera will activate, capture a video of the menu, and send it to the server. The server will analyze the video, convert the acquired text information into audio data, and provide feedback from the speaker, such as "Today's menu is hamburger, french fries, and salad."

[0164] Furthermore, if a user wants to know the status of their delivery, they can use the voice command "Tell me the delivery status." The server generates voice feedback based on the current delivery location and estimated delivery time, and provides information through the speaker, such as "The delivery person has left the store and is expected to arrive within 5 minutes."

[0165] The main hardware used is as follows:

[0166] Camera: a device that captures visual data of the surroundings

[0167] Microphone: A device that receives voice commands

[0168] Server: A device with the computational resources to analyze video and audio data

[0169] speaker: a device that provides audio feedback

[0170] The main software used is as follows:

[0171] Speech recognition system: Technology that converts voice data into text data

[0172] Generative AI model: Technology that analyzes video data and detects objects and text

[0173] Text-to-speech system: Technology that converts text data into voice data

[0174] Examples of prompt sentences include:

[0175] "Analyze the latest menu image and output the menu contents as text."

[0176] The above is a specific embodiment for carrying out the present invention. The system of the present invention enables visually impaired people to use food delivery services safely and efficiently.

[0177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0178] Step 1:

[0179] When a user speaks a voice command into a microphone, for example, "read me the menu," the microphone captures the voice data, which becomes the input.

[0180] Step 2:

[0181] The device sends the captured voice data to the server. The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, the voice data is analyzed to understand the user's intent.

[0182] Step 3:

[0183] A user uses a camera to capture a menu from a food delivery service. This video data becomes the input. The camera then performs specific operations to capture an image of the menu.

[0184] Step 4:

[0185] The video data captured by the device is sent to the server. The server uses a generative AI model to analyze the received video data and extract the text information for the menu. The input is video data and the output is text information. Specifically, the video data is analyzed and character recognition is performed.

[0186] Step 5:

[0187] The server converts the extracted text information into voice data. This text information is the input and the voice data is the output. The specific operation is the process of converting text into voice.

[0188] Step 6:

[0189] The terminal plays the converted voice data on the speaker and provides it to the user. The input is voice data and the output is voice feedback. Specifically, the speaker plays the voice.

[0190] Step 7:

[0191] If a user wants to know the status of their delivery, they can say "Tell me the status of my delivery" into the microphone. The microphone captures the voice data and sends it to the server. This voice data becomes the input.

[0192] Step 8:

[0193] The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, it analyzes the voice and converts the user's request into text.

[0194] Step 9:

[0195] The server generates voice feedback based on the current delivery location and estimated delivery time. This location data and time data are input, and the output is voice feedback. Specifically, the server obtains data from the location information system and generates voice notification of the delivery status.

[0196] Step 10:

[0197] The device plays the generated audio feedback on a speaker and provides it to the user. The input is audio data and the output is audio feedback. Specifically, the speaker plays the audio.

[0198] This will enable visually impaired people to check the menu contents and quickly find out the delivery status via voice.

[0199] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0200] This invention provides a support system for visually impaired people to obtain real-time information about their surroundings in daily life, and to recognize the user's emotions and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[0201] First, the device activates the camera to capture video data of the surrounding area, which is then sent to the server via the network. The server then analyzes the video data and detects objects and text.

[0202] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server, where it is converted into text using voice recognition technology. For example, if a user asks a question like, "Where is the next traffic light?", the voice is converted into text.

[0203] Furthermore, the server uses an emotion engine to recognize the user's emotions when analyzing the voice command. The recognized emotion information is taken into consideration when generating feedback information. For example, if the user expresses anxiety, the feedback will be adjusted to be more polite and detailed.

[0204] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[0205] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[0206] As a specific example, consider the case where a user wants a menu read out loud at a restaurant. The user turns to the microphone and requests, "Please read the menu out loud." The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video and extracts the text information written on the menu. Next, it uses an emotion engine to recognize emotions from the user's voice and reflects this in the feedback provided. For example, if the user is nervous, it provides friendly voice feedback such as, "Sorry to keep you waiting. I'll read it out in order."

[0207] It can also be applied to locating objects within the home. When a user asks, "Where are my keys?", the device captures the entire room with its camera and sends the video data to a server. The server then identifies the "keys" in the video and generates feedback such as "The keys are on the table" based on that location information. Furthermore, an emotion engine is used to recognize emotions from the user's voice, and if the user appears anxious, it provides reassuring feedback such as "Your keys are in a place where you can easily find them."

[0208] As described above, the assistance system of the present invention not only enables visually impaired people to obtain the information they need in their daily lives in real time, but also provides more optimal feedback through emotion recognition, thereby further improving their quality of life.

[0209] The processing flow will be explained below.

[0210] Step 1:

[0211] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[0212] The terminal initializes the camera device.

[0213] It captures a single frame from the camera and stores the data in memory.

[0214] Releases the camera device and ends the capture process.

[0215] Step 2:

[0216] The device transmits the captured video data to the server.

[0217] The terminal converts the captured video data into an appropriate format.

[0218] The converted data is transmitted to a server via a network.

[0219] The server receives the video data.

[0220] Step 3:

[0221] The server analyzes the video data and detects objects and text.

[0222] The server inputs the received video data into the AI ​​model.

[0223] The AI ​​model analyzes the video and detects objects and text within it.

[0224] The detection results (object type, location information, etc.) are extracted and stored in memory.

[0225] Step 4:

[0226] The device uses a microphone to capture the user's voice commands.

[0227] The terminal initializes the microphone device.

[0228] The user issues voice commands such as instructions and questions into the microphone.

[0229] The device captures audio from the microphone and saves it as audio data.

[0230] Step 5:

[0231] The device sends the captured audio data to the server.

[0232] The terminal converts the captured audio data into an appropriate format.

[0233] The converted voice data is transmitted to a server via a network.

[0234] The server receives the audio data.

[0235] Step 6:

[0236] The server converts the audio data into text.

[0237] The server inputs the received speech data into a speech recognition model.

[0238] A speech recognition model analyzes the audio data and converts it into text.

[0239] The converted text data is stored in memory.

[0240] Step 7:

[0241] The server recognizes the user's emotions from the voice commands.

[0242] The server inputs the voice command into an emotion recognition model.

[0243] An emotion recognition model analyzes the voice data to identify the user's emotions.

[0244] Emotion recognition results are stored in memory.

[0245] Step 8:

[0246] The server generates feedback information based on voice commands, video analysis results, and emotion recognition results.

[0247] The server acquires the text data of the voice command, the video analysis results, and the emotion recognition results.

[0248] Based on this data, the AI ​​model generates feedback information.

[0249] The generated feedback information is stored in memory in text format.

[0250] Step 9:

[0251] The server transmits the generated feedback information to the terminal.

[0252] The server converts the generated feedback information into an appropriate format.

[0253] The converted data is transmitted to the terminal via the network.

[0254] The terminal receives the feedback information.

[0255] Step 10:

[0256] The device converts the feedback information into audio and plays it through the speaker.

[0257] The terminal inputs the received feedback information into a text-to-speech engine.

[0258] A text-to-speech engine converts the feedback information into audio.

[0259] The terminal reproduces the generated audio from a speaker and provides it to the user.

[0260] This series of steps allows visually impaired people to understand their surroundings in real time and receive optimal feedback based on their emotions. For example, if a user is nervous at a restaurant and asks for a menu to be read to them, the emotion engine can sense their nervousness and provide more friendly and reassuring feedback.

[0261] Example 2

[0262] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0263] In daily life, visually impaired people have limited means of obtaining real-time information about their surroundings, which can make it difficult for them to act independently. Furthermore, conventional assistance systems lack the ability to optimize feedback based on the user's emotions, and therefore do not provide an environment in which users can use them with confidence.

[0264] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0265] In this invention, the server includes means for converting the voice data into text, means for analyzing the voice command and recognizing the user's emotion, and means for generating feedback information based on the voice command, the analysis result, and emotion information, thereby enabling visually impaired people to obtain information about their surroundings in real time and receive feedback according to the user's emotion.

[0266] A "camera" is an optical device for recording and transmitting visual information as digital data.

[0267] "Video data" is data that represents visual information captured by a camera in digital form.

[0268] A "server" is a computer system that provides various services to clients over a network.

[0269] "Analysis" is the process of extracting information from digital data using specific algorithms or techniques.

[0270] An "object" refers to a specific object that exists within the video data.

[0271] "Text" refers to the text information contained in the video data.

[0272] A "microphone" is an acoustic device for capturing sound as digital data.

[0273] "Voice command" refers to voice data of instructions or questions uttered by a user.

[0274] "Convert to text" is the process of converting audio data into text using natural language processing techniques.

[0275] "Emotion recognition" is the process of analyzing and identifying a user's emotional state from voice and text data.

[0276] "Feedback information" refers to the response content generated in response to information or instructions requested by the user.

[0277] "Providing by voice" refers to the process of conveying the generated feedback information to the user using voice synthesis technology.

[0278] A "system" refers to a collection of multiple interrelated components that work together to perform a function.

[0279] A "restaurant menu" is a document that lists the dishes and drinks served at a restaurant.

[0280] "Directions" are instructions that show the route and direction for the user to reach the destination.

[0281] MODE FOR CARRYING OUT THE INVENTION

[0282] This invention is a support system for visually impaired people to obtain real-time information about their surroundings in daily life, recognize the user's emotions, and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[0283] First, the device is started up and the camera, microphone, and speaker are initialized. The camera captures visual information and generates video data. The microphone captures the user's voice commands and generates audio data. The speaker plays back feedback information from the server as audio.

[0284] The video and audio data captured by the device is sent to a server via the network. The server then uses software such as OpenCV and Tesseract to analyze the video data and extract object and text information. For example, it can recognize objects and text such as "traffic lights" and "menus" in the video.

[0285] Meanwhile, the voice data is converted to text data using the Google Speech-to-Text API, which is then understood using natural language processing (NLP) to analyze the user's intent, and an emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's emotions from the voice data.

[0286] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback. The generated feedback is adjusted to take the user's emotions into account. For example, if the user shows anxiety, the server generates more polite and reassuring feedback.

[0287] The generated feedback information is sent from the server to the device, which then provides it to the user through a speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[0288] Specific examples

[0289] Example 1: Explaining the location of traffic lights

[0290] 1. The user asks, "Where is the next traffic light?"

[0291] 2. The device's microphone captures the audio and sends it to the server.

[0292] 3. The server converts the voice into text and analyzes the user's emotions using an emotion engine.

[0293] 4. The server analyzes the camera footage and identifies the location of the traffic light.

[0294] 5. The server generates feedback such as "The next traffic light is 50 meters ahead on your right."

[0295] 6. The device relays this feedback to the user through the speaker.

[0296] Prompt Sentence Examples

[0297] "If the user asks where the next traffic light is, identify the traffic light in the camera footage and provide instructions taking into account the user's emotions."

[0298] Example 2: Reading a menu at a restaurant

[0299] 1. The user requests, "Please read the menu."

[0300] 2. The device captures the menu image with its camera and sends it to the server.

[0301] 3. The server analyzes the video and extracts the menu text.

[0302] 4. The server recognizes emotions from the user's voice and generates friendly feedback.

[0303] 5. The device tells the user through the speaker, "Sorry to keep you waiting. I'll read it out in order."

[0304] Prompt Sentence Examples

[0305] "If a user asks to have a menu read aloud at a restaurant, capture the menu with the camera, extract the text, and provide helpful audio feedback."

[0306] In this way, visually impaired people can obtain the information they need in their daily lives in real time and receive optimal feedback based on the user's emotions.

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] Step 1:

[0309] When the device is started, the camera, microphone, and speaker are initialized. The camera resolution, microphone sensitivity, and speaker volume are set. This creates an environment for accurate capture of visual and audio information. The input is the device startup signal, and the output is the camera, microphone, and speaker ready state.

[0310] Step 2:

[0311] The user inputs a voice command. For example, "Where is the next traffic light?" The input is the user's voice command, and the output is voice data. The device's microphone captures this voice and sends it to the server as digital data. Specifically, the voice waveform is converted into a digital signal and sent to the server.

[0312] Step 3:

[0313] The server converts the received voice data into text data using the Google Speech-to-Text API. The input is voice data and the output is text data. This allows the information entered by voice to be handled as a string of characters. Specifically, the voice data is sent to the API and a response in text format is received.

[0314] Step 4:

[0315] The server analyzes the converted text data to understand the user's intent. It uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The input is text data, and the output is the user's intent and emotional information. Specifically, it performs text analysis processing to identify the user's requests and emotions.

[0316] Step 5:

[0317] The device activates the camera and captures video data of the surroundings. The input is the camera image and the output is the video data. The captured video data is sent to a server via a network. Specifically, the camera shutter opens and the video is recorded as digital data.

[0318] Step 6:

[0319] The server receives the video data and analyzes it using software such as OpenCV and Tesseract to detect objects and text. The input is video data, and the output is object information and text information. Specifically, the video data is processed using an algorithm to recognize traffic lights and text.

[0320] Step 7:

[0321] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback information. The inputs are text data, object information, text information, and emotion information. The output is feedback information. Specifically, a feedback generation algorithm is used to create an appropriate answer to the user's question.

[0322] Step 8:

[0323] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the completion status of the transmission to the terminal. Specifically, the feedback information is sent to the terminal via the network.

[0324] Step 9:

[0325] The device provides feedback information to the user through the speaker. The input is feedback information and the output is voice feedback. Specifically, the feedback information is converted into voice data by a voice synthesis engine and played back from the speaker.

[0326] (Application example 2)

[0327] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0328] When visually impaired people shop in brick-and-mortar stores, they face challenges in obtaining real-time information about their surroundings and receiving feedback based on their emotional state. This can hinder safe and efficient movement and product exploration. Furthermore, the lack of appropriate guidance and feedback significantly limits the shopping experience for visually impaired people.

[0329] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing surrounding video data using a camera, means for transmitting the captured video data to the server, and means for the server to analyze the video data and detect objects and text. This enables a function to provide product information and location guidance within a physical store. The server also includes means for receiving voice commands using a microphone, means for converting the voice commands into text, means for the server to generate feedback information based on the voice commands and the analysis results, means for providing the feedback information to the user by voice, means for recognizing emotions from the voice commands using an emotion recognition engine, and means for reflecting the emotion recognition results in the feedback information. This allows visually impaired people to obtain information about their surroundings in real time and receive optimal feedback based on their emotions, resulting in a safe and efficient shopping experience.

[0330] A "camera" is a device for capturing video data of the surroundings.

[0331] "Video Data" refers to visual information of the surroundings captured by a camera.

[0332] A "server" is a computer system that analyzes captured video data and voice commands and generates feedback information.

[0333] "Object" refers to a specific thing or entity that the server detects from the video data.

[0334] "Text" refers to information expressed as characters or strings of characters.

[0335] A "microphone" is a device for capturing voice commands.

[0336] "Voice command" refers to instructions or questions entered by a user through speech.

[0337] "Text conversion means" refers to the process or technology that converts voice commands into written information.

[0338] "Feedback information" refers to information or instructions provided to the user that are generated by the server based on the analysis results or voice commands.

[0339] "Means for providing to the user by voice" refers to the process or technology for conveying the generated feedback information to the user by voice.

[0340] An "emotion recognition engine" refers to a technology or system for recognizing and extracting a user's emotions from voice commands.

[0341] "Emotion recognition result" refers to the user's emotion information obtained by the emotion recognition engine.

[0342] "Brick and mortar store" refers to a retail store or commercial establishment that exists in a physical location.

[0343] "Product information" refers to information such as the name, location, and description of the product that the user is looking for in the store.

[0344] "Location navigation" refers to the process or technology that generates feedback to direct users to the specific location of the product they are looking for.

[0345] This system allows visually impaired people to obtain product information in real time in a physical store, and also recognizes the user's emotions and provides optimal feedback. This system is composed of a camera, a microphone, a speaker, an emotion recognition engine, and a server.

[0346] First, the device (smartphone or smart glasses) activates its camera and captures video data of the surroundings. This video data is then sent over the network to a server, which then analyzes the video data and uses the Google Cloud Vision API to detect objects and text.

[0347] The device then uses a microphone to capture the user's voice commands, which are then sent to a server where they are converted to text using SpeechRecognition. For example, a user can ask a question like "Where's the milk?" and the speech is converted to text.

[0348] Furthermore, when analyzing voice commands, the server uses an emotion recognition engine to recognize the user's emotions. Here, the emotion_recognition module is used. The recognized emotion information is taken into account when generating feedback information. If the user is confused, the feedback will be adjusted to provide more detailed and gentler expressions.

[0349] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. The generated feedback information is converted into audio using the Google Cloud Text-to-Speech API. For example, if "milk" is identified through video analysis and its location becomes clear, the server generates feedback such as "The milk is in the refrigerated shelf in the front right." If the user is confused, the server also provides additional reassuring feedback such as "Don't worry, I'll show you the way."

[0350] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[0351] As a specific use case, consider a user searching for a specific product in a supermarket. The user speaks to their smart glasses or smartphone, asking, "Where is the milk?" The device's camera captures video of the surroundings and sends it to the server. The server then analyzes the video to determine the location of the milk and recognizes the user's confusion from the voice command. Finally, it provides feedback such as, "The milk is in the refrigerated shelf in front of you on the right. Don't worry, I'll show you the way."

[0352] Example prompt sentence:

[0353] 1. Video capture: "A user wearing smart glasses captures an image of a scene in a supermarket."

[0354] 2. Voice command: "The user speaks to the smart glasses, 'Where is the milk?'"

[0355] 3. Emotion Recognition: "The AI ​​receives voice commands and detects confusion in the user's voice."

[0356] 4. Image analysis: "Identify the location of refrigerated shelves in captured footage."

[0357] 5. Feedback generation: "When the user asks where the milk is, the AI ​​will respond by saying, 'The milk is in the refrigerator, in the front right.'"

[0358] 6. Emotional feedback: "If the user is confused, generate additional reassuring feedback."

[0359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0360] Step 1:

[0361] The device activates its camera and captures video data of the surroundings. As input, it provides visual information of the surroundings. Here, the device (smartphone or smart glasses) uses its camera hardware to obtain the captured video data. As output, it obtains the captured video data.

[0362] Step 2:

[0363] The device sends the captured video data to the server. The input is the video data obtained in step 1. The data is sent to the server via the network. The output is the video data sent to the server. Specifically, the device establishes a network connection, divides the data into packets, and sends them.

[0364] Step 3:

[0365] The server analyzes the received video data and detects objects and text. The input is the video data sent in step 2. The server analyzes the video data using the Google Cloud Vision API and extracts object positions and text information. The output is the object and text detection data as the analysis result. Specifically, the server sends video data to the API and analyzes the response.

[0366] Step 4:

[0367] The device uses a microphone to capture the user's voice commands. The input is the user's voice. Here, the device's microphone hardware is used to capture voice data. The output is the captured voice command data. Specifically, the microphone converts the user's voice into a digital signal.

[0368] Step 5:

[0369] The device sends the captured voice data to the server. The input is the voice command data obtained in step 4. The data is sent to the server via the network. The output is the voice data sent to the server. Specifically, the device establishes a network connection, divides the voice data into packets, and sends them.

[0370] Step 6:

[0371] The server converts the received voice data into text data using speech recognition technology. The input is the voice data sent in step 5. The server uses SpeechRecognition to analyze the voice data and convert it into text. The output is the converted text data. Specifically, the speech recognition model analyzes the voice signal and generates the corresponding text.

[0372] Step 7:

[0373] The server analyzes the voice command and recognizes the user's emotion using the emotion recognition engine. The input is the text data obtained in step 6. The server recognizes the emotion using the emotion_recognition module. The output is the recognized emotion data. Specifically, the emotion recognition model analyzes the text and generates emotion labels.

[0374] Step 8:

[0375] The server generates feedback information based on the voice command, video analysis results, and emotion recognition results. The inputs are the object and text detection data from step 3, the text data from step 6, and the emotion recognition data from step 7. The server combines these data to generate optimal feedback information. The output is feedback information data. Specifically, the AI ​​model analyzes various data and creates a feedback message.

[0376] Step 9:

[0377] The server converts the generated feedback information into audio data. The input is the feedback information data generated in step 8. The server converts the text into audio data using the Google Cloud Text-to-Speech API. The output is audio feedback data. Specifically, the server sends text data to the API and receives audio data.

[0378] Step 10:

[0379] The terminal receives the audio feedback and provides the feedback information to the user via a speaker. The input is the audio feedback data sent in step 9. The terminal plays back this data and provides it to the user. The output is the audio feedback that the user hears. Specifically, the terminal's speaker plays back the digital audio signal as analog audio.

[0380] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0381] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0382] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0383] [Second embodiment]

[0384] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0385] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0386] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0387] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0388] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0389] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0390] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0391] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0392] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0393] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0394] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0395] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0396] The present invention provides a support system that makes it easy for visually impaired people to obtain real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[0397] First, the device activates the camera and captures video data of the surrounding area. The captured video data is then sent over the network to a server. Once the server receives the video data, it analyzes it using an AI model to detect objects and text within the video.

[0398] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server and converted into text data using voice recognition technology. For example, if a user asks a question such as "Where is the next traffic light?", the voice is converted into text.

[0399] The server generates the necessary feedback information for the user based on the converted text data and the results of video analysis. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[0400] The generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to understand the surrounding situation in real time and take appropriate action.

[0401] As a specific example, if a user wants a menu to be read aloud at a restaurant, the user would say into the microphone, "Please read the menu to me." The device would then capture a video of the menu with its camera and send it to the server. The server would then analyze the video and extract the text information written on the menu. This text information would then be generated as voice feedback and read aloud from the device's speaker. This would allow the user to accurately understand the menu contents and place their order smoothly.

[0402] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[0403] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[0404] The processing flow will be explained below.

[0405] Step 1:

[0406] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[0407] The terminal initializes the camera device.

[0408] It captures a single frame from the camera and stores the data in memory.

[0409] Releases the camera device and ends the capture process.

[0410] Step 2:

[0411] The device transmits the captured video data to the server.

[0412] The terminal converts the captured video data into an appropriate format.

[0413] The converted data is transmitted to a server via a network.

[0414] The server receives the video data.

[0415] Step 3:

[0416] The server analyzes the video data and detects objects and text.

[0417] The server inputs the received video data into the AI ​​model.

[0418] The AI ​​model analyzes the video and detects objects and text within it.

[0419] The detection results (object type, location information, etc.) are extracted and stored in memory.

[0420] Step 4:

[0421] The device uses a microphone to capture the user's voice commands.

[0422] The terminal initializes the microphone device.

[0423] The user issues voice commands such as instructions and questions into the microphone.

[0424] The device captures audio from the microphone and saves it as audio data.

[0425] Step 5:

[0426] The device sends the captured audio data to the server.

[0427] The terminal converts the captured audio data into an appropriate format.

[0428] The converted voice data is transmitted to a server via a network.

[0429] The server receives the audio data.

[0430] Step 6:

[0431] The server converts the audio data into text.

[0432] The server inputs the received speech data into a speech recognition model.

[0433] A speech recognition model analyzes the audio data and converts it into text.

[0434] The converted text data is stored in memory.

[0435] Step 7:

[0436] The server generates feedback information based on voice commands and video analysis results.

[0437] The server acquires the text data of the voice command and the video analysis results.

[0438] Based on this data, the AI ​​model generates feedback.

[0439] Save the generated feedback information in text format.

[0440] Step 8:

[0441] The server transmits the generated feedback information to the terminal.

[0442] The server converts the generated feedback information into an appropriate format.

[0443] The converted data is transmitted to the terminal via the network.

[0444] The terminal receives the feedback information.

[0445] Step 9:

[0446] The device converts the feedback information into audio and plays it through the speaker.

[0447] The terminal inputs the received feedback information into a text-to-speech engine.

[0448] A text-to-speech engine converts the feedback information into audio.

[0449] The terminal reproduces the generated audio from a speaker and provides it to the user.

[0450] This series of steps allows visually impaired people to receive real-time information about their surroundings, improving their quality of life.

[0451] Example 1

[0452] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0453] It is difficult for visually impaired people to obtain real-time information about their surroundings in their daily lives. Particularly, locating objects outdoors or indoors, reading restaurant menus, and getting directions are problematic. Systems that solve these problems and support the visually impaired are needed to enable them to live independently.

[0454] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0455] In this invention, the server includes means for compressing and transferring received video data in real time, means for analyzing objects and text in the video using an AI model through deep learning, means for processing voice commands using voice recognition technology and converting them into text data, means for generating feedback appropriate for the user in natural language using a generative AI model, and means for transmitting feedback information with low latency using a communication protocol, thereby enabling visually impaired people to grasp their surroundings in real time and receive appropriate feedback.

[0456] A "camera" is a device that captures optical images and converts them into digital data.

[0457] "Video data" refers to image information captured by a camera expressed in digital format.

[0458] A "server" is a high-performance computer system that processes and stores data over a network.

[0459] A "microphone" is a device that captures sound as an acoustic signal and converts it into digital data.

[0460] A "voice command" is a voice instruction given by a user, which is an input that the system recognizes and processes.

[0461] "Text data" is a voice command expressed as text information.

[0462] "Feedback information" refers to instructions and guidance information provided by the system based on the analysis results and user requests.

[0463] "Real-time" refers to a state in which processing and response are carried out immediately without delay.

[0464] An "AI model" is an algorithm trained based on machine learning that is used to analyze data and make predictions.

[0465] "Deep learning" is a technology that uses multi-layer neural networks to extract and learn from data features.

[0466] "Speech recognition technology" is a technology that analyzes voice as digital data and converts it into text.

[0467] A "generative AI model" is an AI algorithm that generates output in natural language based on input data.

[0468] A "communication protocol" is a set of rules and procedures for sending and receiving data over a network.

[0469] "Low latency" refers to minimizing the time it takes to send, receive, and process data.

[0470] This invention is a system that supports visually impaired people in obtaining real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[0471] First, the device is equipped with a camera and microphone. The device activates the camera and captures video data of the surrounding area. This video data is then sent to a server via a network. Specifically, technology is used to compress the video data in real time and transfer it with low latency.

[0472] The server analyzes the received video data using an AI model, which uses deep learning object detection algorithms, such as the YOLO (You Only Look Once) model, to quickly and accurately detect objects and text in the video.

[0473] The device then uses a microphone to capture the user's voice commands. For example, when the user asks, "Where is the next traffic light?", the device sends the voice data to a server. The server then uses voice recognition technology (e.g., Google Speech-to-Text API) to convert the voice data into text data.

[0474] The server generates the necessary feedback information for the user based on the converted text data and the video analysis results. To generate the feedback, a generative AI model (such as GPT-3) is used to create feedback in natural language. For example, if a traffic light is detected through video analysis and its location is identified, the server generates feedback such as, "The next traffic light is 50 meters ahead on the right."

[0475] The generated feedback is sent to the device with low latency using a communication protocol, and the device's speaker provides this feedback information to the user via audio, allowing the user to understand the surrounding situation in real time and take appropriate action.

[0476] As a specific example of use, consider the case where a user wants to have a menu read aloud at a restaurant. In this case, the user requests, "Please read the menu aloud," into the microphone. The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video, extracts the text information written on the menu, generates it as voice feedback, and reads it aloud from the device's speaker. This allows the user to accurately understand the menu contents and place their order smoothly.

[0477] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[0478] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[0479] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0480] Step 1:

[0481] The device activates the camera. The user operates the device to point the camera at the surroundings and capture video data. The captured video data is temporarily stored inside the device. The input is the camera, and the output is the captured video data. Specifically, the camera continuously captures frames and converts them into digital data.

[0482] Step 2:

[0483] The device compresses the video data captured by the device and sends it to the server via the network. The input is the captured video data, and the output is the compressed video data. Specifically, the device uses a video data compression algorithm to reduce the data volume and improve the transmission speed.

[0484] Step 3:

[0485] The server analyzes the received video data using an AI model. The input is compressed video data, and the output is the analysis results (location information of objects and text). Specifically, the server uses an AI model (for example, YOLO) to detect objects and text in the video, and obtains location information as a result.

[0486] Step 4:

[0487] The device activates the microphone and captures the user's voice command. The input is the user's speech, and the output is the captured voice data. Specifically, the microphone converts the acoustic signal into digital data and temporarily stores it.

[0488] Step 5:

[0489] The terminal transmits the captured audio data to the server. The input is the audio data, and the output is the audio data transmitted to the server. Specifically, the data is transmitted in real time via the network.

[0490] Step 6:

[0491] The server receives the voice data and converts it into text data using speech recognition technology. The input is the transmitted voice data, and the output is the converted text data. Specifically, speech recognition technology such as the Google Speech-to-Text API is used to convert the voice into text information.

[0492] Step 7:

[0493] The server generates feedback information based on the text data and video analysis results. The input is the converted text data and video analysis results, and the output is the generated feedback information. Specifically, it uses a generative AI model (e.g., GPT-3) to generate natural language feedback for the user.

[0494] Step 8:

[0495] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the feedback information sent to the terminal. Specifically, the data is sent with low latency using a communication protocol.

[0496] Step 9:

[0497] The device's speaker provides the user with audible feedback. The input is the transmitted feedback information, and the output is the feedback information provided as audio. Specifically, text is converted into audio using speech synthesis technology and output from the speaker.

[0498] Through the above processing steps, this system enables visually impaired people to understand their surroundings in real time and receive appropriate feedback.

[0499] (Application example 1)

[0500] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0501] When visually impaired people use food delivery services, it is extremely difficult for them to understand the menu contents and delivery status. The lack of an appropriate means to confirm order details and track delivery locations without relying on visual information makes it difficult for them to order and receive meals autonomously. To solve this problem, a system is needed that allows visually impaired people to obtain real-time information about food delivery using voice commands.

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

[0503] In this invention, the server includes a means for a visually impaired person to obtain information about food delivery services using voice commands, a means including a function to read out restaurant menus, and a means for notifying the delivery location and time by voice, thereby enabling a visually impaired person to check menu contents, confirm an order, and track the delivery location when using a food delivery service using voice commands.

[0504] A "camera" is a device for capturing video data of the surroundings.

[0505] A "server" is a device that has the computational resources to receive and analyze captured video data.

[0506] A "microphone" is a device for receiving voice commands.

[0507] A "voice command" is a voice instruction given by the user through a microphone.

[0508] "Video data" is data that includes visual information captured by a camera.

[0509] "Text data" is data obtained by converting a voice command into text format.

[0510] "Object detection" is a process of recognizing and identifying objects present in video data.

[0511] "Feedback information" is information for the user that is generated by the server based on the analysis results and voice commands.

[0512] "Blind people" refers to people who have visual impairments.

[0513] A "food delivery service" is a service that allows users to order food online and receive it via delivery.

[0514] "Menu" means the list of food offered by a restaurant or food delivery page.

[0515] "Voice notification" refers to the act of providing the generated feedback information to the user as voice.

[0516] "Delivery location tracking" is the process of confirming and notifying the current location of a food delivery person.

[0517] This invention is a system to support visually impaired people to use food delivery services safely and smoothly. This system is mainly composed of a camera, a microphone, a server, and a speaker. These elements work together to provide necessary information to visually impaired people in real time.

[0518] First, when a user speaks a voice command into the microphone, the microphone captures the voice data and sends it to the server. Voice commands include "read me the menu," "tell me the status of my order," "check delivery location," etc. The server then uses voice recognition technology to convert the voice data into text data.

[0519] Next, if a user wants to check the menu of a food delivery service, they use the device's camera to capture a video of the menu. This video data is sent to the server, which then analyzes the video data using a generative AI model to extract the text information of the menu. The extracted text information is converted into audio data and provided to the user through a speaker.

[0520] Specifically, the following scenarios are possible:

[0521] For example, if a visually impaired person issues the voice command "Read me the menu," the camera will activate, capture a video of the menu, and send it to the server. The server will analyze the video, convert the acquired text information into audio data, and provide feedback from the speaker, such as "Today's menu is hamburger, french fries, and salad."

[0522] Furthermore, if a user wants to know the status of their delivery, they can use the voice command "Tell me the delivery status." The server generates voice feedback based on the current delivery location and estimated delivery time, and provides information through the speaker, such as "The delivery person has left the store and is expected to arrive within 5 minutes."

[0523] The main hardware used is as follows:

[0524] Camera: a device that captures visual data of the surroundings

[0525] Microphone: A device that receives voice commands

[0526] Server: A device with the computational resources to analyze video and audio data

[0527] speaker: a device that provides audio feedback

[0528] The main software used is as follows:

[0529] Speech recognition system: Technology that converts voice data into text data

[0530] Generative AI model: Technology that analyzes video data and detects objects and text

[0531] Text-to-speech system: Technology that converts text data into voice data

[0532] Examples of prompt sentences include:

[0533] "Analyze the latest menu image and output the menu contents as text."

[0534] The above is a specific embodiment for carrying out the present invention. The system of the present invention enables visually impaired people to use food delivery services safely and efficiently.

[0535] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0536] Step 1:

[0537] When a user speaks a voice command into a microphone, for example, "read me the menu," the microphone captures the voice data, which becomes the input.

[0538] Step 2:

[0539] The device sends the captured voice data to the server. The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, the voice data is analyzed to understand the user's intent.

[0540] Step 3:

[0541] A user uses a camera to capture a menu from a food delivery service. This video data becomes the input. The camera then performs specific operations to capture an image of the menu.

[0542] Step 4:

[0543] The video data captured by the device is sent to the server. The server uses a generative AI model to analyze the received video data and extract the text information for the menu. The input is video data and the output is text information. Specifically, the video data is analyzed and character recognition is performed.

[0544] Step 5:

[0545] The server converts the extracted text information into voice data. This text information is the input and the voice data is the output. The specific operation is the process of converting text into voice.

[0546] Step 6:

[0547] The terminal plays the converted voice data on the speaker and provides it to the user. The input is voice data and the output is voice feedback. Specifically, the speaker plays the voice.

[0548] Step 7:

[0549] If a user wants to know the status of their delivery, they can say "Tell me the status of my delivery" into the microphone. The microphone captures the voice data and sends it to the server. This voice data becomes the input.

[0550] Step 8:

[0551] The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, it analyzes the voice and converts the user's request into text.

[0552] Step 9:

[0553] The server generates voice feedback based on the current delivery location and estimated delivery time. This location data and time data are input, and the output is voice feedback. Specifically, the server obtains data from the location information system and generates voice notification of the delivery status.

[0554] Step 10:

[0555] The device plays the generated audio feedback on a speaker and provides it to the user. The input is audio data and the output is audio feedback. Specifically, the speaker plays the audio.

[0556] This will enable visually impaired people to check the menu contents and quickly find out the delivery status via voice.

[0557] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0558] This invention provides a support system for visually impaired people to obtain real-time information about their surroundings in daily life, and to recognize the user's emotions and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[0559] First, the device activates the camera to capture video data of the surrounding area, which is then sent to the server via the network. The server then analyzes the video data and detects objects and text.

[0560] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server, where it is converted into text using voice recognition technology. For example, if a user asks a question like, "Where is the next traffic light?", the voice is converted into text.

[0561] Furthermore, the server uses an emotion engine to recognize the user's emotions when analyzing the voice command. The recognized emotion information is taken into consideration when generating feedback information. For example, if the user expresses anxiety, the feedback will be adjusted to be more polite and detailed.

[0562] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[0563] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[0564] As a specific example, consider the case where a user wants a menu read out loud at a restaurant. The user turns to the microphone and requests, "Please read the menu out loud." The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video and extracts the text information written on the menu. Next, it uses an emotion engine to recognize emotions from the user's voice and reflects this in the feedback provided. For example, if the user is nervous, it provides friendly voice feedback such as, "Sorry to keep you waiting. I'll read it out in order."

[0565] It can also be applied to locating objects within the home. When a user asks, "Where are my keys?", the device captures the entire room with its camera and sends the video data to a server. The server then identifies the "keys" in the video and generates feedback such as "The keys are on the table" based on that location information. Furthermore, an emotion engine is used to recognize emotions from the user's voice, and if the user appears anxious, it provides reassuring feedback such as "Your keys are in a place where you can easily find them."

[0566] As described above, the assistance system of the present invention not only enables visually impaired people to obtain the information they need in their daily lives in real time, but also provides more optimal feedback through emotion recognition, thereby further improving their quality of life.

[0567] The processing flow will be explained below.

[0568] Step 1:

[0569] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[0570] The terminal initializes the camera device.

[0571] It captures a single frame from the camera and stores the data in memory.

[0572] Releases the camera device and ends the capture process.

[0573] Step 2:

[0574] The device transmits the captured video data to the server.

[0575] The terminal converts the captured video data into an appropriate format.

[0576] The converted data is transmitted to a server via a network.

[0577] The server receives the video data.

[0578] Step 3:

[0579] The server analyzes the video data and detects objects and text.

[0580] The server inputs the received video data into the AI ​​model.

[0581] The AI ​​model analyzes the video and detects objects and text within it.

[0582] The detection results (object type, location information, etc.) are extracted and stored in memory.

[0583] Step 4:

[0584] The device uses a microphone to capture the user's voice commands.

[0585] The terminal initializes the microphone device.

[0586] The user issues voice commands such as instructions and questions into the microphone.

[0587] The device captures audio from the microphone and saves it as audio data.

[0588] Step 5:

[0589] The device sends the captured audio data to the server.

[0590] The terminal converts the captured audio data into an appropriate format.

[0591] The converted voice data is transmitted to a server via a network.

[0592] The server receives the audio data.

[0593] Step 6:

[0594] The server converts the audio data into text.

[0595] The server inputs the received speech data into a speech recognition model.

[0596] A speech recognition model analyzes the audio data and converts it into text.

[0597] The converted text data is stored in memory.

[0598] Step 7:

[0599] The server recognizes the user's emotions from the voice commands.

[0600] The server inputs the voice command into an emotion recognition model.

[0601] An emotion recognition model analyzes the voice data to identify the user's emotions.

[0602] Emotion recognition results are stored in memory.

[0603] Step 8:

[0604] The server generates feedback information based on voice commands, video analysis results, and emotion recognition results.

[0605] The server acquires the text data of the voice command, the video analysis results, and the emotion recognition results.

[0606] Based on this data, the AI ​​model generates feedback information.

[0607] The generated feedback information is stored in memory in text format.

[0608] Step 9:

[0609] The server transmits the generated feedback information to the terminal.

[0610] The server converts the generated feedback information into an appropriate format.

[0611] The converted data is transmitted to the terminal via the network.

[0612] The terminal receives the feedback information.

[0613] Step 10:

[0614] The device converts the feedback information into audio and plays it through the speaker.

[0615] The terminal inputs the received feedback information into a text-to-speech engine.

[0616] A text-to-speech engine converts the feedback information into audio.

[0617] The terminal reproduces the generated audio from a speaker and provides it to the user.

[0618] This series of steps allows visually impaired people to understand their surroundings in real time and receive optimal feedback based on their emotions. For example, if a user is nervous at a restaurant and asks for a menu to be read to them, the emotion engine can sense their nervousness and provide more friendly and reassuring feedback.

[0619] Example 2

[0620] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0621] In daily life, visually impaired people have limited means of obtaining real-time information about their surroundings, which can make it difficult for them to act independently. Furthermore, conventional assistance systems lack the ability to optimize feedback based on the user's emotions, and therefore do not provide an environment in which users can use them with confidence.

[0622] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0623] In this invention, the server includes means for converting the voice data into text, means for analyzing the voice command and recognizing the user's emotion, and means for generating feedback information based on the voice command, the analysis result, and emotion information, thereby enabling visually impaired people to obtain information about their surroundings in real time and receive feedback according to the user's emotion.

[0624] A "camera" is an optical device for recording and transmitting visual information as digital data.

[0625] "Video data" is data that represents visual information captured by a camera in digital form.

[0626] A "server" is a computer system that provides various services to clients over a network.

[0627] "Analysis" is the process of extracting information from digital data using specific algorithms or techniques.

[0628] An "object" refers to a specific object that exists within the video data.

[0629] "Text" refers to the text information contained in the video data.

[0630] A "microphone" is an acoustic device for capturing sound as digital data.

[0631] "Voice command" refers to voice data of instructions or questions uttered by a user.

[0632] "Convert to text" is the process of converting audio data into text using natural language processing techniques.

[0633] "Emotion recognition" is the process of analyzing and identifying a user's emotional state from voice and text data.

[0634] "Feedback information" refers to the response content generated in response to information or instructions requested by the user.

[0635] "Providing by voice" refers to the process of conveying the generated feedback information to the user using voice synthesis technology.

[0636] A "system" refers to a collection of multiple interrelated components that work together to perform a function.

[0637] A "restaurant menu" is a document that lists the dishes and drinks served at a restaurant.

[0638] "Directions" are instructions that show the route and direction for the user to reach the destination.

[0639] MODE FOR CARRYING OUT THE INVENTION

[0640] This invention is a support system for visually impaired people to obtain real-time information about their surroundings in daily life, recognize the user's emotions, and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[0641] First, the device is started up and the camera, microphone, and speaker are initialized. The camera captures visual information and generates video data. The microphone captures the user's voice commands and generates audio data. The speaker plays back feedback information from the server as audio.

[0642] The video and audio data captured by the device is sent to a server via the network. The server then uses software such as OpenCV and Tesseract to analyze the video data and extract object and text information. For example, it can recognize objects and text such as "traffic lights" and "menus" in the video.

[0643] Meanwhile, the voice data is converted to text data using the Google Speech-to-Text API, which is then understood using natural language processing (NLP) to analyze the user's intent, and an emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's emotions from the voice data.

[0644] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback. The generated feedback is adjusted to take the user's emotions into account. For example, if the user shows anxiety, the server generates more polite and reassuring feedback.

[0645] The generated feedback information is sent from the server to the device, which then provides it to the user through a speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[0646] Specific examples

[0647] Example 1: Explaining the location of traffic lights

[0648] 1. The user asks, "Where is the next traffic light?"

[0649] 2. The device's microphone captures the audio and sends it to the server.

[0650] 3. The server converts the voice into text and analyzes the user's emotions using an emotion engine.

[0651] 4. The server analyzes the camera footage and identifies the location of the traffic light.

[0652] 5. The server generates feedback such as "The next traffic light is 50 meters ahead on your right."

[0653] 6. The device relays this feedback to the user through the speaker.

[0654] Prompt Sentence Examples

[0655] "If the user asks where the next traffic light is, identify the traffic light in the camera footage and provide instructions taking into account the user's emotions."

[0656] Example 2: Reading a menu at a restaurant

[0657] 1. The user requests, "Please read the menu."

[0658] 2. The device captures the menu image with its camera and sends it to the server.

[0659] 3. The server analyzes the video and extracts the menu text.

[0660] 4. The server recognizes emotions from the user's voice and generates friendly feedback.

[0661] 5. The device tells the user through the speaker, "Sorry to keep you waiting. I'll read it out in order."

[0662] Prompt Sentence Examples

[0663] "If a user asks to have a menu read aloud at a restaurant, capture the menu with the camera, extract the text, and provide helpful audio feedback."

[0664] In this way, visually impaired people can obtain the information they need in their daily lives in real time and receive optimal feedback based on the user's emotions.

[0665] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0666] Step 1:

[0667] When the device is started, the camera, microphone, and speaker are initialized. The camera resolution, microphone sensitivity, and speaker volume are set. This creates an environment for accurate capture of visual and audio information. The input is the device startup signal, and the output is the camera, microphone, and speaker ready state.

[0668] Step 2:

[0669] The user inputs a voice command. For example, "Where is the next traffic light?" The input is the user's voice command, and the output is voice data. The device's microphone captures this voice and sends it to the server as digital data. Specifically, the voice waveform is converted into a digital signal and sent to the server.

[0670] Step 3:

[0671] The server converts the received voice data into text data using the Google Speech-to-Text API. The input is voice data and the output is text data. This allows the information entered by voice to be handled as a string of characters. Specifically, the voice data is sent to the API and a response in text format is received.

[0672] Step 4:

[0673] The server analyzes the converted text data to understand the user's intent. It uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The input is text data, and the output is the user's intent and emotional information. Specifically, it performs text analysis processing to identify the user's requests and emotions.

[0674] Step 5:

[0675] The device activates the camera and captures video data of the surroundings. The input is the camera image and the output is the video data. The captured video data is sent to a server via a network. Specifically, the camera shutter opens and the video is recorded as digital data.

[0676] Step 6:

[0677] The server receives the video data and analyzes it using software such as OpenCV and Tesseract to detect objects and text. The input is video data, and the output is object information and text information. Specifically, the video data is processed using an algorithm to recognize traffic lights and text.

[0678] Step 7:

[0679] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback information. The inputs are text data, object information, text information, and emotion information. The output is feedback information. Specifically, a feedback generation algorithm is used to create an appropriate answer to the user's question.

[0680] Step 8:

[0681] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the completion status of the transmission to the terminal. Specifically, the feedback information is sent to the terminal via the network.

[0682] Step 9:

[0683] The device provides feedback information to the user through the speaker. The input is feedback information and the output is voice feedback. Specifically, the feedback information is converted into voice data by a voice synthesis engine and played back from the speaker.

[0684] (Application example 2)

[0685] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0686] When visually impaired people shop in brick-and-mortar stores, they face challenges in obtaining real-time information about their surroundings and receiving feedback based on their emotional state. This can hinder safe and efficient movement and product exploration. Furthermore, the lack of appropriate guidance and feedback significantly limits the shopping experience for visually impaired people.

[0687] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing surrounding video data using a camera, means for transmitting the captured video data to the server, and means for the server to analyze the video data and detect objects and text. This enables a function to provide product information and location guidance within a physical store. The server also includes means for receiving voice commands using a microphone, means for converting the voice commands into text, means for the server to generate feedback information based on the voice commands and the analysis results, means for providing the feedback information to the user by voice, means for recognizing emotions from the voice commands using an emotion recognition engine, and means for reflecting the emotion recognition results in the feedback information. This allows visually impaired people to obtain information about their surroundings in real time and receive optimal feedback based on their emotions, resulting in a safe and efficient shopping experience.

[0688] A "camera" is a device for capturing video data of the surroundings.

[0689] "Video Data" refers to visual information of the surroundings captured by a camera.

[0690] A "server" is a computer system that analyzes captured video data and voice commands and generates feedback information.

[0691] "Object" refers to a specific thing or entity that the server detects from the video data.

[0692] "Text" refers to information expressed as characters or strings of characters.

[0693] A "microphone" is a device for capturing voice commands.

[0694] "Voice command" refers to instructions or questions entered by a user through speech.

[0695] "Text conversion means" refers to the process or technology that converts voice commands into written information.

[0696] "Feedback information" refers to information or instructions provided to the user that are generated by the server based on the analysis results or voice commands.

[0697] "Means for providing to the user by voice" refers to the process or technology for conveying the generated feedback information to the user by voice.

[0698] An "emotion recognition engine" refers to a technology or system for recognizing and extracting a user's emotions from voice commands.

[0699] "Emotion recognition result" refers to the user's emotion information obtained by the emotion recognition engine.

[0700] "Brick and mortar store" refers to a retail store or commercial establishment that exists in a physical location.

[0701] "Product information" refers to information such as the name, location, and description of the product that the user is looking for in the store.

[0702] "Location navigation" refers to the process or technology that generates feedback to direct users to the specific location of the product they are looking for.

[0703] This system allows visually impaired people to obtain product information in real time in a physical store, and also recognizes the user's emotions and provides optimal feedback. This system is composed of a camera, a microphone, a speaker, an emotion recognition engine, and a server.

[0704] First, the device (smartphone or smart glasses) activates its camera and captures video data of the surroundings. This video data is then sent over the network to a server, which then analyzes the video data and uses the Google Cloud Vision API to detect objects and text.

[0705] The device then uses a microphone to capture the user's voice commands, which are then sent to a server where they are converted to text using SpeechRecognition. For example, a user can ask a question like "Where's the milk?" and the speech is converted to text.

[0706] Furthermore, when analyzing voice commands, the server uses an emotion recognition engine to recognize the user's emotions. Here, the emotion_recognition module is used. The recognized emotion information is taken into account when generating feedback information. If the user is confused, the feedback will be adjusted to provide more detailed and gentler expressions.

[0707] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. The generated feedback information is converted into audio using the Google Cloud Text-to-Speech API. For example, if "milk" is identified through video analysis and its location becomes clear, the server generates feedback such as "The milk is in the refrigerated shelf in the front right." If the user is confused, the server also provides additional reassuring feedback such as "Don't worry, I'll show you the way."

[0708] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[0709] As a specific use case, consider a user searching for a specific product in a supermarket. The user speaks to their smart glasses or smartphone, asking, "Where is the milk?" The device's camera captures video of the surroundings and sends it to the server. The server then analyzes the video to determine the location of the milk and recognizes the user's confusion from the voice command. Finally, it provides feedback such as, "The milk is in the refrigerated shelf in front of you on the right. Don't worry, I'll show you the way."

[0710] Example prompt sentence:

[0711] 1. Video capture: "A user wearing smart glasses captures an image of a scene in a supermarket."

[0712] 2. Voice command: "The user speaks to the smart glasses, 'Where is the milk?'"

[0713] 3. Emotion Recognition: "The AI ​​receives voice commands and detects confusion in the user's voice."

[0714] 4. Image analysis: "Identify the location of refrigerated shelves in captured footage."

[0715] 5. Feedback generation: "When the user asks where the milk is, the AI ​​will respond by saying, 'The milk is in the refrigerator, in the front right.'"

[0716] 6. Emotional feedback: "If the user is confused, generate additional reassuring feedback."

[0717] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0718] Step 1:

[0719] The device activates its camera and captures video data of the surroundings. As input, it provides visual information of the surroundings. Here, the device (smartphone or smart glasses) uses its camera hardware to obtain the captured video data. As output, it obtains the captured video data.

[0720] Step 2:

[0721] The device sends the captured video data to the server. The input is the video data obtained in step 1. The data is sent to the server via the network. The output is the video data sent to the server. Specifically, the device establishes a network connection, divides the data into packets, and sends them.

[0722] Step 3:

[0723] The server analyzes the received video data and detects objects and text. The input is the video data sent in step 2. The server analyzes the video data using the Google Cloud Vision API and extracts object positions and text information. The output is the object and text detection data as the analysis result. Specifically, the server sends video data to the API and analyzes the response.

[0724] Step 4:

[0725] The device uses a microphone to capture the user's voice commands. The input is the user's voice. Here, the device's microphone hardware is used to capture voice data. The output is the captured voice command data. Specifically, the microphone converts the user's voice into a digital signal.

[0726] Step 5:

[0727] The device sends the captured voice data to the server. The input is the voice command data obtained in step 4. The data is sent to the server via the network. The output is the voice data sent to the server. Specifically, the device establishes a network connection, divides the voice data into packets, and sends them.

[0728] Step 6:

[0729] The server converts the received voice data into text data using speech recognition technology. The input is the voice data sent in step 5. The server uses SpeechRecognition to analyze the voice data and convert it into text. The output is the converted text data. Specifically, the speech recognition model analyzes the voice signal and generates the corresponding text.

[0730] Step 7:

[0731] The server analyzes the voice command and recognizes the user's emotion using the emotion recognition engine. The input is the text data obtained in step 6. The server recognizes the emotion using the emotion_recognition module. The output is the recognized emotion data. Specifically, the emotion recognition model analyzes the text and generates emotion labels.

[0732] Step 8:

[0733] The server generates feedback information based on the voice command, video analysis results, and emotion recognition results. The inputs are the object and text detection data from step 3, the text data from step 6, and the emotion recognition data from step 7. The server combines these data to generate optimal feedback information. The output is feedback information data. Specifically, the AI ​​model analyzes various data and creates a feedback message.

[0734] Step 9:

[0735] The server converts the generated feedback information into audio data. The input is the feedback information data generated in step 8. The server converts the text into audio data using the Google Cloud Text-to-Speech API. The output is audio feedback data. Specifically, the server sends text data to the API and receives audio data.

[0736] Step 10:

[0737] The terminal receives the audio feedback and provides the feedback information to the user via a speaker. The input is the audio feedback data sent in step 9. The terminal plays back this data and provides it to the user. The output is the audio feedback that the user hears. Specifically, the terminal's speaker plays back the digital audio signal as analog audio.

[0738] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0739] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0740] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0741] [Third embodiment]

[0742] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0743] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0744] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0745] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0746] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0747] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0748] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0749] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0750] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0751] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0752] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0753] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0754] The present invention provides a support system that makes it easy for visually impaired people to obtain real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[0755] First, the device activates the camera and captures video data of the surrounding area. The captured video data is then sent over the network to a server. Once the server receives the video data, it analyzes it using an AI model to detect objects and text within the video.

[0756] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server and converted into text data using voice recognition technology. For example, if a user asks a question such as "Where is the next traffic light?", the voice is converted into text.

[0757] The server generates the necessary feedback information for the user based on the converted text data and the results of video analysis. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[0758] The generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to understand the surrounding situation in real time and take appropriate action.

[0759] As a specific example, if a user wants a menu to be read aloud at a restaurant, the user would say into the microphone, "Please read the menu to me." The device would then capture a video of the menu with its camera and send it to the server. The server would then analyze the video and extract the text information written on the menu. This text information would then be generated as voice feedback and read aloud from the device's speaker. This would allow the user to accurately understand the menu contents and place their order smoothly.

[0760] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[0761] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[0762] The processing flow will be explained below.

[0763] Step 1:

[0764] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[0765] The terminal initializes the camera device.

[0766] It captures a single frame from the camera and stores the data in memory.

[0767] Releases the camera device and ends the capture process.

[0768] Step 2:

[0769] The device transmits the captured video data to the server.

[0770] The terminal converts the captured video data into an appropriate format.

[0771] The converted data is transmitted to a server via a network.

[0772] The server receives the video data.

[0773] Step 3:

[0774] The server analyzes the video data and detects objects and text.

[0775] The server inputs the received video data into the AI ​​model.

[0776] The AI ​​model analyzes the video and detects objects and text within it.

[0777] The detection results (object type, location information, etc.) are extracted and stored in memory.

[0778] Step 4:

[0779] The device uses a microphone to capture the user's voice commands.

[0780] The terminal initializes the microphone device.

[0781] The user issues voice commands such as instructions and questions into the microphone.

[0782] The device captures audio from the microphone and saves it as audio data.

[0783] Step 5:

[0784] The device sends the captured audio data to the server.

[0785] The terminal converts the captured audio data into an appropriate format.

[0786] The converted voice data is transmitted to a server via a network.

[0787] The server receives the audio data.

[0788] Step 6:

[0789] The server converts the audio data into text.

[0790] The server inputs the received speech data into a speech recognition model.

[0791] A speech recognition model analyzes the audio data and converts it into text.

[0792] The converted text data is stored in memory.

[0793] Step 7:

[0794] The server generates feedback information based on voice commands and video analysis results.

[0795] The server acquires the text data of the voice command and the video analysis results.

[0796] Based on this data, the AI ​​model generates feedback.

[0797] Save the generated feedback information in text format.

[0798] Step 8:

[0799] The server transmits the generated feedback information to the terminal.

[0800] The server converts the generated feedback information into an appropriate format.

[0801] The converted data is transmitted to the terminal via the network.

[0802] The terminal receives the feedback information.

[0803] Step 9:

[0804] The device converts the feedback information into audio and plays it through the speaker.

[0805] The terminal inputs the received feedback information into a text-to-speech engine.

[0806] A text-to-speech engine converts the feedback information into audio.

[0807] The terminal reproduces the generated audio from a speaker and provides it to the user.

[0808] This series of steps allows visually impaired people to receive real-time information about their surroundings, improving their quality of life.

[0809] Example 1

[0810] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0811] It is difficult for visually impaired people to obtain real-time information about their surroundings in their daily lives. Particularly, locating objects outdoors or indoors, reading restaurant menus, and getting directions are problematic. Systems that solve these problems and support the visually impaired are needed to enable them to live independently.

[0812] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0813] In this invention, the server includes means for compressing and transferring received video data in real time, means for analyzing objects and text in the video using an AI model through deep learning, means for processing voice commands using voice recognition technology and converting them into text data, means for generating feedback appropriate for the user in natural language using a generative AI model, and means for transmitting feedback information with low latency using a communication protocol, thereby enabling visually impaired people to grasp their surroundings in real time and receive appropriate feedback.

[0814] A "camera" is a device that captures optical images and converts them into digital data.

[0815] "Video data" refers to image information captured by a camera expressed in digital format.

[0816] A "server" is a high-performance computer system that processes and stores data over a network.

[0817] A "microphone" is a device that captures sound as an acoustic signal and converts it into digital data.

[0818] A "voice command" is a voice instruction given by a user, which is an input that the system recognizes and processes.

[0819] "Text data" is a voice command expressed as text information.

[0820] "Feedback information" refers to instructions and guidance information provided by the system based on the analysis results and user requests.

[0821] "Real-time" refers to a state in which processing and response are carried out immediately without delay.

[0822] An "AI model" is an algorithm trained based on machine learning that is used to analyze data and make predictions.

[0823] "Deep learning" is a technology that uses multi-layer neural networks to extract and learn from data features.

[0824] "Speech recognition technology" is a technology that analyzes voice as digital data and converts it into text.

[0825] A "generative AI model" is an AI algorithm that generates output in natural language based on input data.

[0826] A "communication protocol" is a set of rules and procedures for sending and receiving data over a network.

[0827] "Low latency" refers to minimizing the time it takes to send, receive, and process data.

[0828] This invention is a system that supports visually impaired people in obtaining real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[0829] First, the device is equipped with a camera and microphone. The device activates the camera and captures video data of the surrounding area. This video data is then sent to a server via a network. Specifically, technology is used to compress the video data in real time and transfer it with low latency.

[0830] The server analyzes the received video data using an AI model, which uses deep learning object detection algorithms, such as the YOLO (You Only Look Once) model, to quickly and accurately detect objects and text in the video.

[0831] The device then uses a microphone to capture the user's voice commands. For example, when the user asks, "Where is the next traffic light?", the device sends the voice data to a server. The server then uses voice recognition technology (e.g., Google Speech-to-Text API) to convert the voice data into text data.

[0832] The server generates the necessary feedback information for the user based on the converted text data and the video analysis results. To generate the feedback, a generative AI model (such as GPT-3) is used to create feedback in natural language. For example, if a traffic light is detected through video analysis and its location is identified, the server generates feedback such as, "The next traffic light is 50 meters ahead on the right."

[0833] The generated feedback is sent to the device with low latency using a communication protocol, and the device's speaker provides this feedback information to the user via audio, allowing the user to understand the surrounding situation in real time and take appropriate action.

[0834] As a specific example of use, consider the case where a user wants to have a menu read aloud at a restaurant. In this case, the user requests, "Please read the menu aloud," into the microphone. The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video, extracts the text information written on the menu, generates it as voice feedback, and reads it aloud from the device's speaker. This allows the user to accurately understand the menu contents and place their order smoothly.

[0835] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[0836] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[0837] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0838] Step 1:

[0839] The device activates the camera. The user operates the device to point the camera at the surroundings and capture video data. The captured video data is temporarily stored inside the device. The input is the camera, and the output is the captured video data. Specifically, the camera continuously captures frames and converts them into digital data.

[0840] Step 2:

[0841] The device compresses the video data captured by the device and sends it to the server via the network. The input is the captured video data, and the output is the compressed video data. Specifically, the device uses a video data compression algorithm to reduce the data volume and improve the transmission speed.

[0842] Step 3:

[0843] The server analyzes the received video data using an AI model. The input is compressed video data, and the output is the analysis results (location information of objects and text). Specifically, the server uses an AI model (for example, YOLO) to detect objects and text in the video, and obtains location information as a result.

[0844] Step 4:

[0845] The device activates the microphone and captures the user's voice command. The input is the user's speech, and the output is the captured voice data. Specifically, the microphone converts the acoustic signal into digital data and temporarily stores it.

[0846] Step 5:

[0847] The terminal transmits the captured audio data to the server. The input is the audio data, and the output is the audio data transmitted to the server. Specifically, the data is transmitted in real time via the network.

[0848] Step 6:

[0849] The server receives the voice data and converts it into text data using speech recognition technology. The input is the transmitted voice data, and the output is the converted text data. Specifically, speech recognition technology such as the Google Speech-to-Text API is used to convert the voice into text information.

[0850] Step 7:

[0851] The server generates feedback information based on the text data and video analysis results. The input is the converted text data and video analysis results, and the output is the generated feedback information. Specifically, it uses a generative AI model (e.g., GPT-3) to generate natural language feedback for the user.

[0852] Step 8:

[0853] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the feedback information sent to the terminal. Specifically, the data is sent with low latency using a communication protocol.

[0854] Step 9:

[0855] The device's speaker provides the user with audible feedback. The input is the transmitted feedback information, and the output is the feedback information provided as audio. Specifically, text is converted into audio using speech synthesis technology and output from the speaker.

[0856] Through the above processing steps, this system enables visually impaired people to understand their surroundings in real time and receive appropriate feedback.

[0857] (Application example 1)

[0858] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0859] When visually impaired people use food delivery services, it is extremely difficult for them to understand the menu contents and delivery status. The lack of an appropriate means to confirm order details and track delivery locations without relying on visual information makes it difficult for them to order and receive meals autonomously. To solve this problem, a system is needed that allows visually impaired people to obtain real-time information about food delivery using voice commands.

[0860] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0861] In this invention, the server includes a means for a visually impaired person to obtain information about food delivery services using voice commands, a means including a function to read out restaurant menus, and a means for notifying the delivery location and time by voice, thereby enabling a visually impaired person to check menu contents, confirm an order, and track the delivery location when using a food delivery service using voice commands.

[0862] A "camera" is a device for capturing video data of the surroundings.

[0863] A "server" is a device that has the computational resources to receive and analyze captured video data.

[0864] A "microphone" is a device for receiving voice commands.

[0865] A "voice command" is a voice instruction given by the user through a microphone.

[0866] "Video data" is data that includes visual information captured by a camera.

[0867] "Text data" is data obtained by converting a voice command into text format.

[0868] "Object detection" is a process of recognizing and identifying objects present in video data.

[0869] "Feedback information" is information for the user that is generated by the server based on the analysis results and voice commands.

[0870] "Blind people" refers to people who have visual impairments.

[0871] A "food delivery service" is a service that allows users to order food online and receive it via delivery.

[0872] "Menu" means the list of food offered by a restaurant or food delivery page.

[0873] "Voice notification" refers to the act of providing the generated feedback information to the user as voice.

[0874] "Delivery location tracking" is the process of confirming and notifying the current location of a food delivery person.

[0875] This invention is a system to support visually impaired people to use food delivery services safely and smoothly. This system is mainly composed of a camera, a microphone, a server, and a speaker. These elements work together to provide necessary information to visually impaired people in real time.

[0876] First, when a user speaks a voice command into the microphone, the microphone captures the voice data and sends it to the server. Voice commands include "read me the menu," "tell me the status of my order," "check delivery location," etc. The server then uses voice recognition technology to convert the voice data into text data.

[0877] Next, if a user wants to check the menu of a food delivery service, they use the device's camera to capture a video of the menu. This video data is sent to the server, which then analyzes the video data using a generative AI model to extract the text information of the menu. The extracted text information is converted into audio data and provided to the user through a speaker.

[0878] Specifically, the following scenarios are possible:

[0879] For example, if a visually impaired person issues the voice command "Read me the menu," the camera will activate, capture a video of the menu, and send it to the server. The server will analyze the video, convert the acquired text information into audio data, and provide feedback from the speaker, such as "Today's menu is hamburger, french fries, and salad."

[0880] Furthermore, if a user wants to know the status of their delivery, they can use the voice command "Tell me the delivery status." The server generates voice feedback based on the current delivery location and estimated delivery time, and provides information through the speaker, such as "The delivery person has left the store and is expected to arrive within 5 minutes."

[0881] The main hardware used is as follows:

[0882] Camera: a device that captures visual data of the surroundings

[0883] Microphone: A device that receives voice commands

[0884] Server: A device with the computational resources to analyze video and audio data

[0885] speaker: a device that provides audio feedback

[0886] The main software used is as follows:

[0887] Speech recognition system: Technology that converts voice data into text data

[0888] Generative AI model: Technology that analyzes video data and detects objects and text

[0889] Text-to-speech system: Technology that converts text data into voice data

[0890] Examples of prompt sentences include:

[0891] "Analyze the latest menu image and output the menu contents as text."

[0892] The above is a specific embodiment for carrying out the present invention. The system of the present invention enables visually impaired people to use food delivery services safely and efficiently.

[0893] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0894] Step 1:

[0895] When a user speaks a voice command into a microphone, for example, "read me the menu," the microphone captures the voice data, which becomes the input.

[0896] Step 2:

[0897] The device sends the captured voice data to the server. The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, the voice data is analyzed to understand the user's intent.

[0898] Step 3:

[0899] A user uses a camera to capture a menu from a food delivery service. This video data becomes the input. The camera then performs specific operations to capture an image of the menu.

[0900] Step 4:

[0901] The video data captured by the device is sent to the server. The server uses a generative AI model to analyze the received video data and extract the text information for the menu. The input is video data and the output is text information. Specifically, the video data is analyzed and character recognition is performed.

[0902] Step 5:

[0903] The server converts the extracted text information into voice data. This text information is the input and the voice data is the output. The specific operation is the process of converting text into voice.

[0904] Step 6:

[0905] The terminal plays the converted voice data on the speaker and provides it to the user. The input is voice data and the output is voice feedback. Specifically, the speaker plays the voice.

[0906] Step 7:

[0907] If a user wants to know the status of their delivery, they can say "Tell me the status of my delivery" into the microphone. The microphone captures the voice data and sends it to the server. This voice data becomes the input.

[0908] Step 8:

[0909] The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, it analyzes the voice and converts the user's request into text.

[0910] Step 9:

[0911] The server generates voice feedback based on the current delivery location and estimated delivery time. This location data and time data are input, and the output is voice feedback. Specifically, the server obtains data from the location information system and generates voice notification of the delivery status.

[0912] Step 10:

[0913] The device plays the generated audio feedback on a speaker and provides it to the user. The input is audio data and the output is audio feedback. Specifically, the speaker plays the audio.

[0914] This will enable visually impaired people to check the menu contents and quickly find out the delivery status via voice.

[0915] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0916] This invention provides a support system for visually impaired people to obtain real-time information about their surroundings in daily life, and to recognize the user's emotions and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[0917] First, the device activates the camera to capture video data of the surrounding area, which is then sent to the server via the network. The server then analyzes the video data and detects objects and text.

[0918] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server, where it is converted into text using voice recognition technology. For example, if a user asks a question like, "Where is the next traffic light?", the voice is converted into text.

[0919] Furthermore, the server uses an emotion engine to recognize the user's emotions when analyzing the voice command. The recognized emotion information is taken into consideration when generating feedback information. For example, if the user expresses anxiety, the feedback will be adjusted to be more polite and detailed.

[0920] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[0921] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[0922] As a specific example, consider the case where a user wants a menu read out loud at a restaurant. The user turns to the microphone and requests, "Please read the menu out loud." The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video and extracts the text information written on the menu. Next, it uses an emotion engine to recognize emotions from the user's voice and reflects this in the feedback provided. For example, if the user is nervous, it provides friendly voice feedback such as, "Sorry to keep you waiting. I'll read it out in order."

[0923] It can also be applied to locating objects within the home. When a user asks, "Where are my keys?", the device captures the entire room with its camera and sends the video data to a server. The server then identifies the "keys" in the video and generates feedback such as "The keys are on the table" based on that location information. Furthermore, an emotion engine is used to recognize emotions from the user's voice, and if the user appears anxious, it provides reassuring feedback such as "Your keys are in a place where you can easily find them."

[0924] As described above, the assistance system of the present invention not only enables visually impaired people to obtain the information they need in their daily lives in real time, but also provides more optimal feedback through emotion recognition, thereby further improving their quality of life.

[0925] The processing flow will be explained below.

[0926] Step 1:

[0927] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[0928] The terminal initializes the camera device.

[0929] It captures a single frame from the camera and stores the data in memory.

[0930] Releases the camera device and ends the capture process.

[0931] Step 2:

[0932] The device transmits the captured video data to the server.

[0933] The terminal converts the captured video data into an appropriate format.

[0934] The converted data is transmitted to a server via a network.

[0935] The server receives the video data.

[0936] Step 3:

[0937] The server analyzes the video data and detects objects and text.

[0938] The server inputs the received video data into the AI ​​model.

[0939] The AI ​​model analyzes the video and detects objects and text within it.

[0940] The detection results (object type, location information, etc.) are extracted and stored in memory.

[0941] Step 4:

[0942] The device uses a microphone to capture the user's voice commands.

[0943] The terminal initializes the microphone device.

[0944] The user issues voice commands such as instructions and questions into the microphone.

[0945] The device captures audio from the microphone and saves it as audio data.

[0946] Step 5:

[0947] The device sends the captured audio data to the server.

[0948] The terminal converts the captured audio data into an appropriate format.

[0949] The converted voice data is transmitted to a server via a network.

[0950] The server receives the audio data.

[0951] Step 6:

[0952] The server converts the audio data into text.

[0953] The server inputs the received speech data into a speech recognition model.

[0954] A speech recognition model analyzes the audio data and converts it into text.

[0955] The converted text data is stored in memory.

[0956] Step 7:

[0957] The server recognizes the user's emotions from the voice commands.

[0958] The server inputs the voice command into an emotion recognition model.

[0959] An emotion recognition model analyzes the voice data to identify the user's emotions.

[0960] Emotion recognition results are stored in memory.

[0961] Step 8:

[0962] The server generates feedback information based on voice commands, video analysis results, and emotion recognition results.

[0963] The server acquires the text data of the voice command, the video analysis results, and the emotion recognition results.

[0964] Based on this data, the AI ​​model generates feedback information.

[0965] The generated feedback information is stored in memory in text format.

[0966] Step 9:

[0967] The server transmits the generated feedback information to the terminal.

[0968] The server converts the generated feedback information into an appropriate format.

[0969] The converted data is transmitted to the terminal via the network.

[0970] The terminal receives the feedback information.

[0971] Step 10:

[0972] The device converts the feedback information into audio and plays it through the speaker.

[0973] The terminal inputs the received feedback information into a text-to-speech engine.

[0974] A text-to-speech engine converts the feedback information into audio.

[0975] The terminal reproduces the generated audio from a speaker and provides it to the user.

[0976] This series of steps allows visually impaired people to understand their surroundings in real time and receive optimal feedback based on their emotions. For example, if a user is nervous at a restaurant and asks for a menu to be read to them, the emotion engine can sense their nervousness and provide more friendly and reassuring feedback.

[0977] Example 2

[0978] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0979] In daily life, visually impaired people have limited means of obtaining real-time information about their surroundings, which can make it difficult for them to act independently. Furthermore, conventional assistance systems lack the ability to optimize feedback based on the user's emotions, and therefore do not provide an environment in which users can use them with confidence.

[0980] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0981] In this invention, the server includes means for converting the voice data into text, means for analyzing the voice command and recognizing the user's emotion, and means for generating feedback information based on the voice command, the analysis result, and emotion information, thereby enabling visually impaired people to obtain information about their surroundings in real time and receive feedback according to the user's emotion.

[0982] A "camera" is an optical device for recording and transmitting visual information as digital data.

[0983] "Video data" is data that represents visual information captured by a camera in digital form.

[0984] A "server" is a computer system that provides various services to clients over a network.

[0985] "Analysis" is the process of extracting information from digital data using specific algorithms or techniques.

[0986] An "object" refers to a specific object that exists within the video data.

[0987] "Text" refers to the text information contained in the video data.

[0988] A "microphone" is an acoustic device for capturing sound as digital data.

[0989] "Voice command" refers to voice data of instructions or questions uttered by a user.

[0990] "Convert to text" is the process of converting audio data into text using natural language processing techniques.

[0991] "Emotion recognition" is the process of analyzing and identifying a user's emotional state from voice and text data.

[0992] "Feedback information" refers to the response content generated in response to information or instructions requested by the user.

[0993] "Providing by voice" refers to the process of conveying the generated feedback information to the user using voice synthesis technology.

[0994] A "system" refers to a collection of multiple interrelated components that work together to perform a function.

[0995] A "restaurant menu" is a document that lists the dishes and drinks served at a restaurant.

[0996] "Directions" are instructions that show the route and direction for the user to reach the destination.

[0997] MODE FOR CARRYING OUT THE INVENTION

[0998] This invention is a support system for visually impaired people to obtain real-time information about their surroundings in daily life, recognize the user's emotions, and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[0999] First, the device is started up and the camera, microphone, and speaker are initialized. The camera captures visual information and generates video data. The microphone captures the user's voice commands and generates audio data. The speaker plays back feedback information from the server as audio.

[1000] The video and audio data captured by the device is sent to a server via the network. The server then uses software such as OpenCV and Tesseract to analyze the video data and extract object and text information. For example, it can recognize objects and text such as "traffic lights" and "menus" in the video.

[1001] Meanwhile, the voice data is converted to text data using the Google Speech-to-Text API, which is then understood using natural language processing (NLP) to analyze the user's intent, and an emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's emotions from the voice data.

[1002] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback. The generated feedback is adjusted to take the user's emotions into account. For example, if the user shows anxiety, the server generates more polite and reassuring feedback.

[1003] The generated feedback information is sent from the server to the device, which then provides it to the user through a speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[1004] Specific examples

[1005] Example 1: Explaining the location of traffic lights

[1006] 1. The user asks, "Where is the next traffic light?"

[1007] 2. The device's microphone captures the audio and sends it to the server.

[1008] 3. The server converts the voice into text and analyzes the user's emotions using an emotion engine.

[1009] 4. The server analyzes the camera footage and identifies the location of the traffic light.

[1010] 5. The server generates feedback such as "The next traffic light is 50 meters ahead on your right."

[1011] 6. The device relays this feedback to the user through the speaker.

[1012] Prompt Sentence Examples

[1013] "If the user asks where the next traffic light is, identify the traffic light in the camera footage and provide instructions taking into account the user's emotions."

[1014] Example 2: Reading a menu at a restaurant

[1015] 1. The user requests, "Please read the menu."

[1016] 2. The device captures the menu image with its camera and sends it to the server.

[1017] 3. The server analyzes the video and extracts the menu text.

[1018] 4. The server recognizes emotions from the user's voice and generates friendly feedback.

[1019] 5. The device tells the user through the speaker, "Sorry to keep you waiting. I'll read it out in order."

[1020] Prompt Sentence Examples

[1021] "If a user asks to have a menu read aloud at a restaurant, capture the menu with the camera, extract the text, and provide helpful audio feedback."

[1022] In this way, visually impaired people can obtain the information they need in their daily lives in real time and receive optimal feedback based on the user's emotions.

[1023] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] When the device is started, the camera, microphone, and speaker are initialized. The camera resolution, microphone sensitivity, and speaker volume are set. This creates an environment for accurate capture of visual and audio information. The input is the device startup signal, and the output is the camera, microphone, and speaker ready state.

[1026] Step 2:

[1027] The user inputs a voice command. For example, "Where is the next traffic light?" The input is the user's voice command, and the output is voice data. The device's microphone captures this voice and sends it to the server as digital data. Specifically, the voice waveform is converted into a digital signal and sent to the server.

[1028] Step 3:

[1029] The server converts the received voice data into text data using the Google Speech-to-Text API. The input is voice data and the output is text data. This allows the information entered by voice to be handled as a string of characters. Specifically, the voice data is sent to the API and a response in text format is received.

[1030] Step 4:

[1031] The server analyzes the converted text data to understand the user's intent. It uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The input is text data, and the output is the user's intent and emotional information. Specifically, it performs text analysis processing to identify the user's requests and emotions.

[1032] Step 5:

[1033] The device activates the camera and captures video data of the surroundings. The input is the camera image and the output is the video data. The captured video data is sent to a server via a network. Specifically, the camera shutter opens and the video is recorded as digital data.

[1034] Step 6:

[1035] The server receives the video data and analyzes it using software such as OpenCV and Tesseract to detect objects and text. The input is video data, and the output is object information and text information. Specifically, the video data is processed using an algorithm to recognize traffic lights and text.

[1036] Step 7:

[1037] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback information. The inputs are text data, object information, text information, and emotion information. The output is feedback information. Specifically, a feedback generation algorithm is used to create an appropriate answer to the user's question.

[1038] Step 8:

[1039] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the completion status of the transmission to the terminal. Specifically, the feedback information is sent to the terminal via the network.

[1040] Step 9:

[1041] The device provides feedback information to the user through the speaker. The input is feedback information and the output is voice feedback. Specifically, the feedback information is converted into voice data by a voice synthesis engine and played back from the speaker.

[1042] (Application example 2)

[1043] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1044] When visually impaired people shop in brick-and-mortar stores, they face challenges in obtaining real-time information about their surroundings and receiving feedback based on their emotional state. This can hinder safe and efficient movement and product exploration. Furthermore, the lack of appropriate guidance and feedback significantly limits the shopping experience for visually impaired people.

[1045] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing surrounding video data using a camera, means for transmitting the captured video data to the server, and means for the server to analyze the video data and detect objects and text. This enables a function to provide product information and location guidance within a physical store. The server also includes means for receiving voice commands using a microphone, means for converting the voice commands into text, means for the server to generate feedback information based on the voice commands and the analysis results, means for providing the feedback information to the user by voice, means for recognizing emotions from the voice commands using an emotion recognition engine, and means for reflecting the emotion recognition results in the feedback information. This allows visually impaired people to obtain information about their surroundings in real time and receive optimal feedback based on their emotions, resulting in a safe and efficient shopping experience.

[1046] A "camera" is a device for capturing video data of the surroundings.

[1047] "Video Data" refers to visual information of the surroundings captured by a camera.

[1048] A "server" is a computer system that analyzes captured video data and voice commands and generates feedback information.

[1049] "Object" refers to a specific thing or entity that the server detects from the video data.

[1050] "Text" refers to information expressed as characters or strings of characters.

[1051] A "microphone" is a device for capturing voice commands.

[1052] "Voice command" refers to instructions or questions entered by a user through speech.

[1053] "Text conversion means" refers to the process or technology that converts voice commands into written information.

[1054] "Feedback information" refers to information or instructions provided to the user that are generated by the server based on the analysis results or voice commands.

[1055] "Means for providing to the user by voice" refers to the process or technology for conveying the generated feedback information to the user by voice.

[1056] An "emotion recognition engine" refers to a technology or system for recognizing and extracting a user's emotions from voice commands.

[1057] "Emotion recognition result" refers to the user's emotion information obtained by the emotion recognition engine.

[1058] "Brick and mortar store" refers to a retail store or commercial establishment that exists in a physical location.

[1059] "Product information" refers to information such as the name, location, and description of the product that the user is looking for in the store.

[1060] "Location navigation" refers to the process or technology that generates feedback to direct users to the specific location of the product they are looking for.

[1061] This system allows visually impaired people to obtain product information in real time in a physical store, and also recognizes the user's emotions and provides optimal feedback. This system is composed of a camera, a microphone, a speaker, an emotion recognition engine, and a server.

[1062] First, the device (smartphone or smart glasses) activates its camera and captures video data of the surroundings. This video data is then sent over the network to a server, which then analyzes the video data and uses the Google Cloud Vision API to detect objects and text.

[1063] The device then uses a microphone to capture the user's voice commands, which are then sent to a server where they are converted to text using SpeechRecognition. For example, a user can ask a question like "Where's the milk?" and the speech is converted to text.

[1064] Furthermore, when analyzing voice commands, the server uses an emotion recognition engine to recognize the user's emotions. Here, the emotion_recognition module is used. The recognized emotion information is taken into account when generating feedback information. If the user is confused, the feedback will be adjusted to provide more detailed and gentler expressions.

[1065] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. The generated feedback information is converted into audio using the Google Cloud Text-to-Speech API. For example, if "milk" is identified through video analysis and its location becomes clear, the server generates feedback such as "The milk is in the refrigerated shelf in the front right." If the user is confused, the server also provides additional reassuring feedback such as "Don't worry, I'll show you the way."

[1066] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[1067] As a specific use case, consider a user searching for a specific product in a supermarket. The user speaks to their smart glasses or smartphone, asking, "Where is the milk?" The device's camera captures video of the surroundings and sends it to the server. The server then analyzes the video to determine the location of the milk and recognizes the user's confusion from the voice command. Finally, it provides feedback such as, "The milk is in the refrigerated shelf in front of you on the right. Don't worry, I'll show you the way."

[1068] Example prompt sentence:

[1069] 1. Video capture: "A user wearing smart glasses captures an image of a scene in a supermarket."

[1070] 2. Voice command: "The user speaks to the smart glasses, 'Where is the milk?'"

[1071] 3. Emotion Recognition: "The AI ​​receives voice commands and detects confusion in the user's voice."

[1072] 4. Image analysis: "Identify the location of refrigerated shelves in captured footage."

[1073] 5. Feedback generation: "When the user asks where the milk is, the AI ​​will respond by saying, 'The milk is in the refrigerator, in the front right.'"

[1074] 6. Emotional feedback: "If the user is confused, generate additional reassuring feedback."

[1075] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1076] Step 1:

[1077] The device activates its camera and captures video data of the surroundings. As input, it provides visual information of the surroundings. Here, the device (smartphone or smart glasses) uses its camera hardware to obtain the captured video data. As output, it obtains the captured video data.

[1078] Step 2:

[1079] The device sends the captured video data to the server. The input is the video data obtained in step 1. The data is sent to the server via the network. The output is the video data sent to the server. Specifically, the device establishes a network connection, divides the data into packets, and sends them.

[1080] Step 3:

[1081] The server analyzes the received video data and detects objects and text. The input is the video data sent in step 2. The server analyzes the video data using the Google Cloud Vision API and extracts object positions and text information. The output is the object and text detection data as the analysis result. Specifically, the server sends video data to the API and analyzes the response.

[1082] Step 4:

[1083] The device uses a microphone to capture the user's voice commands. The input is the user's voice. Here, the device's microphone hardware is used to capture voice data. The output is the captured voice command data. Specifically, the microphone converts the user's voice into a digital signal.

[1084] Step 5:

[1085] The device sends the captured voice data to the server. The input is the voice command data obtained in step 4. The data is sent to the server via the network. The output is the voice data sent to the server. Specifically, the device establishes a network connection, divides the voice data into packets, and sends them.

[1086] Step 6:

[1087] The server converts the received voice data into text data using speech recognition technology. The input is the voice data sent in step 5. The server uses SpeechRecognition to analyze the voice data and convert it into text. The output is the converted text data. Specifically, the speech recognition model analyzes the voice signal and generates the corresponding text.

[1088] Step 7:

[1089] The server analyzes the voice command and recognizes the user's emotion using the emotion recognition engine. The input is the text data obtained in step 6. The server recognizes the emotion using the emotion_recognition module. The output is the recognized emotion data. Specifically, the emotion recognition model analyzes the text and generates emotion labels.

[1090] Step 8:

[1091] The server generates feedback information based on the voice command, video analysis results, and emotion recognition results. The inputs are the object and text detection data from step 3, the text data from step 6, and the emotion recognition data from step 7. The server combines these data to generate optimal feedback information. The output is feedback information data. Specifically, the AI ​​model analyzes various data and creates a feedback message.

[1092] Step 9:

[1093] The server converts the generated feedback information into audio data. The input is the feedback information data generated in step 8. The server converts the text into audio data using the Google Cloud Text-to-Speech API. The output is audio feedback data. Specifically, the server sends text data to the API and receives audio data.

[1094] Step 10:

[1095] The terminal receives the audio feedback and provides the feedback information to the user via a speaker. The input is the audio feedback data sent in step 9. The terminal plays back this data and provides it to the user. The output is the audio feedback that the user hears. Specifically, the terminal's speaker plays back the digital audio signal as analog audio.

[1096] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1097] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1098] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1099] [Fourth embodiment]

[1100] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1101] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1103] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1104] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1106] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1107] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1108] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1109] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1111] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1112] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1113] The present invention provides a support system that makes it easy for visually impaired people to obtain real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[1114] First, the device activates the camera and captures video data of the surrounding area. The captured video data is then sent over the network to a server. Once the server receives the video data, it analyzes it using an AI model to detect objects and text within the video.

[1115] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server and converted into text data using voice recognition technology. For example, if a user asks a question such as "Where is the next traffic light?", the voice is converted into text.

[1116] The server generates the necessary feedback information for the user based on the converted text data and the results of video analysis. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[1117] The generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to understand the surrounding situation in real time and take appropriate action.

[1118] As a specific example, if a user wants a menu to be read aloud at a restaurant, the user would say into the microphone, "Please read the menu to me." The device would then capture a video of the menu with its camera and send it to the server. The server would then analyze the video and extract the text information written on the menu. This text information would then be generated as voice feedback and read aloud from the device's speaker. This would allow the user to accurately understand the menu contents and place their order smoothly.

[1119] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[1120] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[1121] The processing flow will be explained below.

[1122] Step 1:

[1123] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[1124] The terminal initializes the camera device.

[1125] It captures a single frame from the camera and stores the data in memory.

[1126] Releases the camera device and ends the capture process.

[1127] Step 2:

[1128] The device transmits the captured video data to the server.

[1129] The terminal converts the captured video data into an appropriate format.

[1130] The converted data is transmitted to a server via a network.

[1131] The server receives the video data.

[1132] Step 3:

[1133] The server analyzes the video data and detects objects and text.

[1134] The server inputs the received video data into the AI ​​model.

[1135] The AI ​​model analyzes the video and detects objects and text within it.

[1136] The detection results (object type, location information, etc.) are extracted and stored in memory.

[1137] Step 4:

[1138] The device uses a microphone to capture the user's voice commands.

[1139] The terminal initializes the microphone device.

[1140] The user issues voice commands such as instructions and questions into the microphone.

[1141] The device captures audio from the microphone and saves it as audio data.

[1142] Step 5:

[1143] The device sends the captured audio data to the server.

[1144] The terminal converts the captured audio data into an appropriate format.

[1145] The converted voice data is transmitted to a server via a network.

[1146] The server receives the audio data.

[1147] Step 6:

[1148] The server converts the audio data into text.

[1149] The server inputs the received speech data into a speech recognition model.

[1150] A speech recognition model analyzes the audio data and converts it into text.

[1151] The converted text data is stored in memory.

[1152] Step 7:

[1153] The server generates feedback information based on voice commands and video analysis results.

[1154] The server acquires the text data of the voice command and the video analysis results.

[1155] Based on this data, the AI ​​model generates feedback.

[1156] Save the generated feedback information in text format.

[1157] Step 8:

[1158] The server transmits the generated feedback information to the terminal.

[1159] The server converts the generated feedback information into an appropriate format.

[1160] The converted data is transmitted to the terminal via the network.

[1161] The terminal receives the feedback information.

[1162] Step 9:

[1163] The device converts the feedback information into audio and plays it through the speaker.

[1164] The terminal inputs the received feedback information into a text-to-speech engine.

[1165] A text-to-speech engine converts the feedback information into audio.

[1166] The terminal reproduces the generated audio from a speaker and provides it to the user.

[1167] This series of steps allows visually impaired people to receive real-time information about their surroundings, improving their quality of life.

[1168] Example 1

[1169] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1170] It is difficult for visually impaired people to obtain real-time information about their surroundings in their daily lives. Particularly, locating objects outdoors or indoors, reading restaurant menus, and getting directions are problematic. Systems that solve these problems and support the visually impaired are needed to enable them to live independently.

[1171] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1172] In this invention, the server includes means for compressing and transferring received video data in real time, means for analyzing objects and text in the video using an AI model through deep learning, means for processing voice commands using voice recognition technology and converting them into text data, means for generating feedback appropriate for the user in natural language using a generative AI model, and means for transmitting feedback information with low latency using a communication protocol, thereby enabling visually impaired people to grasp their surroundings in real time and receive appropriate feedback.

[1173] A "camera" is a device that captures optical images and converts them into digital data.

[1174] "Video data" refers to image information captured by a camera expressed in digital format.

[1175] A "server" is a high-performance computer system that processes and stores data over a network.

[1176] A "microphone" is a device that captures sound as an acoustic signal and converts it into digital data.

[1177] A "voice command" is a voice instruction given by a user, which is an input that the system recognizes and processes.

[1178] "Text data" is a voice command expressed as text information.

[1179] "Feedback information" refers to instructions and guidance information provided by the system based on the analysis results and user requests.

[1180] "Real-time" refers to a state in which processing and response are carried out immediately without delay.

[1181] An "AI model" is an algorithm trained based on machine learning that is used to analyze data and make predictions.

[1182] "Deep learning" is a technology that uses multi-layer neural networks to extract and learn from data features.

[1183] "Speech recognition technology" is a technology that analyzes voice as digital data and converts it into text.

[1184] A "generative AI model" is an AI algorithm that generates output in natural language based on input data.

[1185] A "communication protocol" is a set of rules and procedures for sending and receiving data over a network.

[1186] "Low latency" refers to minimizing the time it takes to send, receive, and process data.

[1187] This invention is a system that supports visually impaired people in obtaining real-time information about their surroundings in daily life. The system mainly consists of a camera, a microphone, a speaker, and a server, which work together.

[1188] First, the device is equipped with a camera and microphone. The device activates the camera and captures video data of the surrounding area. This video data is then sent to a server via a network. Specifically, technology is used to compress the video data in real time and transfer it with low latency.

[1189] The server analyzes the received video data using an AI model, which uses deep learning object detection algorithms, such as the YOLO (You Only Look Once) model, to quickly and accurately detect objects and text in the video.

[1190] The device then uses a microphone to capture the user's voice commands. For example, when the user asks, "Where is the next traffic light?", the device sends the voice data to a server. The server then uses voice recognition technology (e.g., Google Speech-to-Text API) to convert the voice data into text data.

[1191] The server generates the necessary feedback information for the user based on the converted text data and the video analysis results. To generate the feedback, a generative AI model (such as GPT-3) is used to create feedback in natural language. For example, if a traffic light is detected through video analysis and its location is identified, the server generates feedback such as, "The next traffic light is 50 meters ahead on the right."

[1192] The generated feedback is sent to the device with low latency using a communication protocol, and the device's speaker provides this feedback information to the user via audio, allowing the user to understand the surrounding situation in real time and take appropriate action.

[1193] As a specific example of use, consider the case where a user wants to have a menu read aloud at a restaurant. In this case, the user requests, "Please read the menu aloud," into the microphone. The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video, extracts the text information written on the menu, generates it as voice feedback, and reads it aloud from the device's speaker. This allows the user to accurately understand the menu contents and place their order smoothly.

[1194] It can also be applied to locating objects in the home. For example, if a user asks, "Where are my keys?", the device will capture the entire room with its camera and send the video data to the server. The server will then identify the "keys" in the video and, based on their location, generate voice feedback such as "The keys are on the table," which will be provided to the user.

[1195] As described above, the support system of the present invention is a groundbreaking technology that enables visually impaired people to obtain necessary information in real time in various situations in daily life, thereby supporting independent living.

[1196] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1197] Step 1:

[1198] The device activates the camera. The user operates the device to point the camera at the surroundings and capture video data. The captured video data is temporarily stored inside the device. The input is the camera, and the output is the captured video data. Specifically, the camera continuously captures frames and converts them into digital data.

[1199] Step 2:

[1200] The device compresses the video data captured by the device and sends it to the server via the network. The input is the captured video data, and the output is the compressed video data. Specifically, the device uses a video data compression algorithm to reduce the data volume and improve the transmission speed.

[1201] Step 3:

[1202] The server analyzes the received video data using an AI model. The input is compressed video data, and the output is the analysis results (location information of objects and text). Specifically, the server uses an AI model (for example, YOLO) to detect objects and text in the video, and obtains location information as a result.

[1203] Step 4:

[1204] The device activates the microphone and captures the user's voice command. The input is the user's speech, and the output is the captured voice data. Specifically, the microphone converts the acoustic signal into digital data and temporarily stores it.

[1205] Step 5:

[1206] The terminal transmits the captured audio data to the server. The input is the audio data, and the output is the audio data transmitted to the server. Specifically, the data is transmitted in real time via the network.

[1207] Step 6:

[1208] The server receives the voice data and converts it into text data using speech recognition technology. The input is the transmitted voice data, and the output is the converted text data. Specifically, speech recognition technology such as the Google Speech-to-Text API is used to convert the voice into text information.

[1209] Step 7:

[1210] The server generates feedback information based on the text data and video analysis results. The input is the converted text data and video analysis results, and the output is the generated feedback information. Specifically, it uses a generative AI model (e.g., GPT-3) to generate natural language feedback for the user.

[1211] Step 8:

[1212] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the feedback information sent to the terminal. Specifically, the data is sent with low latency using a communication protocol.

[1213] Step 9:

[1214] The device's speaker provides the user with audible feedback. The input is the transmitted feedback information, and the output is the feedback information provided as audio. Specifically, text is converted into audio using speech synthesis technology and output from the speaker.

[1215] Through the above processing steps, this system enables visually impaired people to understand their surroundings in real time and receive appropriate feedback.

[1216] (Application example 1)

[1217] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1218] When visually impaired people use food delivery services, it is extremely difficult for them to understand the menu contents and delivery status. The lack of an appropriate means to confirm order details and track delivery locations without relying on visual information makes it difficult for them to order and receive meals autonomously. To solve this problem, a system is needed that allows visually impaired people to obtain real-time information about food delivery using voice commands.

[1219] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1220] In this invention, the server includes a means for a visually impaired person to obtain information about food delivery services using voice commands, a means including a function to read out restaurant menus, and a means for notifying the delivery location and time by voice, thereby enabling a visually impaired person to check menu contents, confirm an order, and track the delivery location when using a food delivery service using voice commands.

[1221] A "camera" is a device for capturing video data of the surroundings.

[1222] A "server" is a device that has the computational resources to receive and analyze captured video data.

[1223] A "microphone" is a device for receiving voice commands.

[1224] A "voice command" is a voice instruction given by the user through a microphone.

[1225] "Video data" is data that includes visual information captured by a camera.

[1226] "Text data" is data obtained by converting a voice command into text format.

[1227] "Object detection" is a process of recognizing and identifying objects present in video data.

[1228] "Feedback information" is information for the user that is generated by the server based on the analysis results and voice commands.

[1229] "Blind people" refers to people who have visual impairments.

[1230] A "food delivery service" is a service that allows users to order food online and receive it via delivery.

[1231] "Menu" means the list of food offered by a restaurant or food delivery page.

[1232] "Voice notification" refers to the act of providing the generated feedback information to the user as voice.

[1233] "Delivery location tracking" is the process of confirming and notifying the current location of a food delivery person.

[1234] This invention is a system to support visually impaired people to use food delivery services safely and smoothly. This system is mainly composed of a camera, a microphone, a server, and a speaker. These elements work together to provide necessary information to visually impaired people in real time.

[1235] First, when a user speaks a voice command into the microphone, the microphone captures the voice data and sends it to the server. Voice commands include "read me the menu," "tell me the status of my order," "check delivery location," etc. The server then uses voice recognition technology to convert the voice data into text data.

[1236] Next, if a user wants to check the menu of a food delivery service, they use the device's camera to capture a video of the menu. This video data is sent to the server, which then analyzes the video data using a generative AI model to extract the text information of the menu. The extracted text information is converted into audio data and provided to the user through a speaker.

[1237] Specifically, the following scenarios are possible:

[1238] For example, if a visually impaired person issues the voice command "Read me the menu," the camera will activate, capture a video of the menu, and send it to the server. The server will analyze the video, convert the acquired text information into audio data, and provide feedback from the speaker, such as "Today's menu is hamburger, french fries, and salad."

[1239] Furthermore, if a user wants to know the status of their delivery, they can use the voice command "Tell me the delivery status." The server generates voice feedback based on the current delivery location and estimated delivery time, and provides information through the speaker, such as "The delivery person has left the store and is expected to arrive within 5 minutes."

[1240] The main hardware used is as follows:

[1241] Camera: a device that captures visual data of the surroundings

[1242] Microphone: A device that receives voice commands

[1243] Server: A device with the computational resources to analyze video and audio data

[1244] speaker: a device that provides audio feedback

[1245] The main software used is as follows:

[1246] Speech recognition system: Technology that converts voice data into text data

[1247] Generative AI model: Technology that analyzes video data and detects objects and text

[1248] Text-to-speech system: Technology that converts text data into voice data

[1249] Examples of prompt sentences include:

[1250] "Analyze the latest menu image and output the menu contents as text."

[1251] The above is a specific embodiment for carrying out the present invention. The system of the present invention enables visually impaired people to use food delivery services safely and efficiently.

[1252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1253] Step 1:

[1254] When a user speaks a voice command into a microphone, for example, "read me the menu," the microphone captures the voice data, which becomes the input.

[1255] Step 2:

[1256] The device sends the captured voice data to the server. The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, the voice data is analyzed to understand the user's intent.

[1257] Step 3:

[1258] A user uses a camera to capture a menu from a food delivery service. This video data becomes the input. The camera then performs specific operations to capture an image of the menu.

[1259] Step 4:

[1260] The video data captured by the device is sent to the server. The server uses a generative AI model to analyze the received video data and extract the text information for the menu. The input is video data and the output is text information. Specifically, the video data is analyzed and character recognition is performed.

[1261] Step 5:

[1262] The server converts the extracted text information into voice data. This text information is the input and the voice data is the output. The specific operation is the process of converting text into voice.

[1263] Step 6:

[1264] The terminal plays the converted voice data on the speaker and provides it to the user. The input is voice data and the output is voice feedback. Specifically, the speaker plays the voice.

[1265] Step 7:

[1266] If a user wants to know the status of their delivery, they can say "Tell me the status of my delivery" into the microphone. The microphone captures the voice data and sends it to the server. This voice data becomes the input.

[1267] Step 8:

[1268] The server uses voice recognition technology to convert the received voice data into text data. The input is voice data and the output is text data. Specifically, it analyzes the voice and converts the user's request into text.

[1269] Step 9:

[1270] The server generates voice feedback based on the current delivery location and estimated delivery time. This location data and time data are input, and the output is voice feedback. Specifically, the server obtains data from the location information system and generates voice notification of the delivery status.

[1271] Step 10:

[1272] The device plays the generated audio feedback on a speaker and provides it to the user. The input is audio data and the output is audio feedback. Specifically, the speaker plays the audio.

[1273] This will enable visually impaired people to check the menu contents and quickly find out the delivery status via voice.

[1274] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1275] This invention provides a support system for visually impaired people to obtain real-time information about their surroundings in daily life, and to recognize the user's emotions and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[1276] First, the device activates the camera to capture video data of the surrounding area, which is then sent to the server via the network. The server then analyzes the video data and detects objects and text.

[1277] The device then uses a microphone to capture the user's voice commands. The captured voice data is sent to a server, where it is converted into text using voice recognition technology. For example, if a user asks a question like, "Where is the next traffic light?", the voice is converted into text.

[1278] Furthermore, the server uses an emotion engine to recognize the user's emotions when analyzing the voice command. The recognized emotion information is taken into consideration when generating feedback information. For example, if the user expresses anxiety, the feedback will be adjusted to be more polite and detailed.

[1279] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. For example, if a traffic light is detected through video analysis and its location is identified, the AI ​​will generate feedback such as, "The next traffic light is 50 meters ahead to the right."

[1280] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[1281] As a specific example, consider the case where a user wants a menu read out loud at a restaurant. The user turns to the microphone and requests, "Please read the menu out loud." The device captures a video of the menu with its camera and sends it to the server. The server analyzes the video and extracts the text information written on the menu. Next, it uses an emotion engine to recognize emotions from the user's voice and reflects this in the feedback provided. For example, if the user is nervous, it provides friendly voice feedback such as, "Sorry to keep you waiting. I'll read it out in order."

[1282] It can also be applied to locating objects within the home. When a user asks, "Where are my keys?", the device captures the entire room with its camera and sends the video data to a server. The server then identifies the "keys" in the video and generates feedback such as "The keys are on the table" based on that location information. Furthermore, an emotion engine is used to recognize emotions from the user's voice, and if the user appears anxious, it provides reassuring feedback such as "Your keys are in a place where you can easily find them."

[1283] As described above, the assistance system of the present invention not only enables visually impaired people to obtain the information they need in their daily lives in real time, but also provides more optimal feedback through emotion recognition, thereby further improving their quality of life.

[1284] The processing flow will be explained below.

[1285] Step 1:

[1286] The device activates the camera and captures the current surroundings, thereby obtaining video data (frames).

[1287] The terminal initializes the camera device.

[1288] It captures a single frame from the camera and stores the data in memory.

[1289] Releases the camera device and ends the capture process.

[1290] Step 2:

[1291] The device transmits the captured video data to the server.

[1292] The terminal converts the captured video data into an appropriate format.

[1293] The converted data is transmitted to a server via a network.

[1294] The server receives the video data.

[1295] Step 3:

[1296] The server analyzes the video data and detects objects and text.

[1297] The server inputs the received video data into the AI ​​model.

[1298] The AI ​​model analyzes the video and detects objects and text within it.

[1299] The detection results (object type, location information, etc.) are extracted and stored in memory.

[1300] Step 4:

[1301] The device uses a microphone to capture the user's voice commands.

[1302] The terminal initializes the microphone device.

[1303] The user issues voice commands such as instructions and questions into the microphone.

[1304] The device captures audio from the microphone and saves it as audio data.

[1305] Step 5:

[1306] The device sends the captured audio data to the server.

[1307] The terminal converts the captured audio data into an appropriate format.

[1308] The converted voice data is transmitted to a server via a network.

[1309] The server receives the audio data.

[1310] Step 6:

[1311] The server converts the audio data into text.

[1312] The server inputs the received speech data into a speech recognition model.

[1313] A speech recognition model analyzes the audio data and converts it into text.

[1314] The converted text data is stored in memory.

[1315] Step 7:

[1316] The server recognizes the user's emotions from the voice commands.

[1317] The server inputs the voice command into an emotion recognition model.

[1318] An emotion recognition model analyzes the voice data to identify the user's emotions.

[1319] Emotion recognition results are stored in memory.

[1320] Step 8:

[1321] The server generates feedback information based on voice commands, video analysis results, and emotion recognition results.

[1322] The server acquires the text data of the voice command, the video analysis results, and the emotion recognition results.

[1323] Based on this data, the AI ​​model generates feedback information.

[1324] The generated feedback information is stored in memory in text format.

[1325] Step 9:

[1326] The server transmits the generated feedback information to the terminal.

[1327] The server converts the generated feedback information into an appropriate format.

[1328] The converted data is transmitted to the terminal via the network.

[1329] The terminal receives the feedback information.

[1330] Step 10:

[1331] The device converts the feedback information into audio and plays it through the speaker.

[1332] The terminal inputs the received feedback information into a text-to-speech engine.

[1333] A text-to-speech engine converts the feedback information into audio.

[1334] The terminal reproduces the generated audio from a speaker and provides it to the user.

[1335] This series of steps allows visually impaired people to understand their surroundings in real time and receive optimal feedback based on their emotions. For example, if a user is nervous at a restaurant and asks for a menu to be read to them, the emotion engine can sense their nervousness and provide more friendly and reassuring feedback.

[1336] Example 2

[1337] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1338] In daily life, visually impaired people have limited means of obtaining real-time information about their surroundings, which can make it difficult for them to act independently. Furthermore, conventional assistance systems lack the ability to optimize feedback based on the user's emotions, and therefore do not provide an environment in which users can use them with confidence.

[1339] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1340] In this invention, the server includes means for converting the voice data into text, means for analyzing the voice command and recognizing the user's emotion, and means for generating feedback information based on the voice command, the analysis result, and emotion information, thereby enabling visually impaired people to obtain information about their surroundings in real time and receive feedback according to the user's emotion.

[1341] A "camera" is an optical device for recording and transmitting visual information as digital data.

[1342] "Video data" is data that represents visual information captured by a camera in digital form.

[1343] A "server" is a computer system that provides various services to clients over a network.

[1344] "Analysis" is the process of extracting information from digital data using specific algorithms or techniques.

[1345] An "object" refers to a specific object that exists within the video data.

[1346] "Text" refers to the text information contained in the video data.

[1347] A "microphone" is an acoustic device for capturing sound as digital data.

[1348] "Voice command" refers to voice data of instructions or questions uttered by a user.

[1349] "Convert to text" is the process of converting audio data into text using natural language processing techniques.

[1350] "Emotion recognition" is the process of analyzing and identifying a user's emotional state from voice and text data.

[1351] "Feedback information" refers to the response content generated in response to information or instructions requested by the user.

[1352] "Providing by voice" refers to the process of conveying the generated feedback information to the user using voice synthesis technology.

[1353] A "system" refers to a collection of multiple interrelated components that work together to perform a function.

[1354] A "restaurant menu" is a document that lists the dishes and drinks served at a restaurant.

[1355] "Directions" are instructions that show the route and direction for the user to reach the destination.

[1356] MODE FOR CARRYING OUT THE INVENTION

[1357] This invention is a support system for visually impaired people to obtain real-time information about their surroundings in daily life, recognize the user's emotions, and provide optimal feedback. The system consists of a camera, a microphone, a speaker, an emotion engine, and a server.

[1358] First, the device is started up and the camera, microphone, and speaker are initialized. The camera captures visual information and generates video data. The microphone captures the user's voice commands and generates audio data. The speaker plays back feedback information from the server as audio.

[1359] The video and audio data captured by the device is sent to a server via the network. The server then uses software such as OpenCV and Tesseract to analyze the video data and extract object and text information. For example, it can recognize objects and text such as "traffic lights" and "menus" in the video.

[1360] Meanwhile, the voice data is converted to text data using the Google Speech-to-Text API, which is then understood using natural language processing (NLP) to analyze the user's intent, and an emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's emotions from the voice data.

[1361] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback. The generated feedback is adjusted to take the user's emotions into account. For example, if the user shows anxiety, the server generates more polite and reassuring feedback.

[1362] The generated feedback information is sent from the server to the device, which then provides it to the user through a speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[1363] Specific examples

[1364] Example 1: Explaining the location of traffic lights

[1365] 1. The user asks, "Where is the next traffic light?"

[1366] 2. The device's microphone captures the audio and sends it to the server.

[1367] 3. The server converts the voice into text and analyzes the user's emotions using an emotion engine.

[1368] 4. The server analyzes the camera footage and identifies the location of the traffic light.

[1369] 5. The server generates feedback such as "The next traffic light is 50 meters ahead on your right."

[1370] 6. The device relays this feedback to the user through the speaker.

[1371] Prompt Sentence Examples

[1372] "If the user asks where the next traffic light is, identify the traffic light in the camera footage and provide instructions taking into account the user's emotions."

[1373] Example 2: Reading a menu at a restaurant

[1374] 1. The user requests, "Please read the menu."

[1375] 2. The device captures the menu image with its camera and sends it to the server.

[1376] 3. The server analyzes the video and extracts the menu text.

[1377] 4. The server recognizes emotions from the user's voice and generates friendly feedback.

[1378] 5. The device tells the user through the speaker, "Sorry to keep you waiting. I'll read it out in order."

[1379] Prompt Sentence Examples

[1380] "If a user asks to have a menu read aloud at a restaurant, capture the menu with the camera, extract the text, and provide helpful audio feedback."

[1381] In this way, visually impaired people can obtain the information they need in their daily lives in real time and receive optimal feedback based on the user's emotions.

[1382] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1383] Step 1:

[1384] When the device is started, the camera, microphone, and speaker are initialized. The camera resolution, microphone sensitivity, and speaker volume are set. This creates an environment for accurate capture of visual and audio information. The input is the device startup signal, and the output is the camera, microphone, and speaker ready state.

[1385] Step 2:

[1386] The user inputs a voice command. For example, "Where is the next traffic light?" The input is the user's voice command, and the output is voice data. The device's microphone captures this voice and sends it to the server as digital data. Specifically, the voice waveform is converted into a digital signal and sent to the server.

[1387] Step 3:

[1388] The server converts the received voice data into text data using the Google Speech-to-Text API. The input is voice data and the output is text data. This allows the information entered by voice to be handled as a string of characters. Specifically, the voice data is sent to the API and a response in text format is received.

[1389] Step 4:

[1390] The server analyzes the converted text data to understand the user's intent. It uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The input is text data, and the output is the user's intent and emotional information. Specifically, it performs text analysis processing to identify the user's requests and emotions.

[1391] Step 5:

[1392] The device activates the camera and captures video data of the surroundings. The input is the camera image and the output is the video data. The captured video data is sent to a server via a network. Specifically, the camera shutter opens and the video is recorded as digital data.

[1393] Step 6:

[1394] The server receives the video data and analyzes it using software such as OpenCV and Tesseract to detect objects and text. The input is video data, and the output is object information and text information. Specifically, the video data is processed using an algorithm to recognize traffic lights and text.

[1395] Step 7:

[1396] The server integrates text data, video analysis results, and emotion recognition results to generate optimal feedback information. The inputs are text data, object information, text information, and emotion information. The output is feedback information. Specifically, a feedback generation algorithm is used to create an appropriate answer to the user's question.

[1397] Step 8:

[1398] The server sends the generated feedback information to the terminal. The input is the feedback information, and the output is the completion status of the transmission to the terminal. Specifically, the feedback information is sent to the terminal via the network.

[1399] Step 9:

[1400] The device provides feedback information to the user through the speaker. The input is feedback information and the output is voice feedback. Specifically, the feedback information is converted into voice data by a voice synthesis engine and played back from the speaker.

[1401] (Application example 2)

[1402] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1403] When visually impaired people shop in brick-and-mortar stores, they face challenges in obtaining real-time information about their surroundings and receiving feedback based on their emotional state. This can hinder safe and efficient movement and product exploration. Furthermore, the lack of appropriate guidance and feedback significantly limits the shopping experience for visually impaired people.

[1404] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing surrounding video data using a camera, means for transmitting the captured video data to the server, and means for the server to analyze the video data and detect objects and text. This enables a function to provide product information and location guidance within a physical store. The server also includes means for receiving voice commands using a microphone, means for converting the voice commands into text, means for the server to generate feedback information based on the voice commands and the analysis results, means for providing the feedback information to the user by voice, means for recognizing emotions from the voice commands using an emotion recognition engine, and means for reflecting the emotion recognition results in the feedback information. This allows visually impaired people to obtain information about their surroundings in real time and receive optimal feedback based on their emotions, resulting in a safe and efficient shopping experience.

[1405] A "camera" is a device for capturing video data of the surroundings.

[1406] "Video Data" refers to visual information of the surroundings captured by a camera.

[1407] A "server" is a computer system that analyzes captured video data and voice commands and generates feedback information.

[1408] "Object" refers to a specific thing or entity that the server detects from the video data.

[1409] "Text" refers to information expressed as characters or strings of characters.

[1410] A "microphone" is a device for capturing voice commands.

[1411] "Voice command" refers to instructions or questions entered by a user through speech.

[1412] "Text conversion means" refers to the process or technology that converts voice commands into written information.

[1413] "Feedback information" refers to information or instructions provided to the user that are generated by the server based on the analysis results or voice commands.

[1414] "Means for providing to the user by voice" refers to the process or technology for conveying the generated feedback information to the user by voice.

[1415] An "emotion recognition engine" refers to a technology or system for recognizing and extracting a user's emotions from voice commands.

[1416] "Emotion recognition result" refers to the user's emotion information obtained by the emotion recognition engine.

[1417] "Brick and mortar store" refers to a retail store or commercial establishment that exists in a physical location.

[1418] "Product information" refers to information such as the name, location, and description of the product that the user is looking for in the store.

[1419] "Location navigation" refers to the process or technology that generates feedback to direct users to the specific location of the product they are looking for.

[1420] This system allows visually impaired people to obtain product information in real time in a physical store, and also recognizes the user's emotions and provides optimal feedback. This system is composed of a camera, a microphone, a speaker, an emotion recognition engine, and a server.

[1421] First, the device (smartphone or smart glasses) activates its camera and captures video data of the surroundings. This video data is then sent over the network to a server, which then analyzes the video data and uses the Google Cloud Vision API to detect objects and text.

[1422] The device then uses a microphone to capture the user's voice commands, which are then sent to a server where they are converted to text using SpeechRecognition. For example, a user can ask a question like "Where's the milk?" and the speech is converted to text.

[1423] Furthermore, when analyzing voice commands, the server uses an emotion recognition engine to recognize the user's emotions. Here, the emotion_recognition module is used. The recognized emotion information is taken into account when generating feedback information. If the user is confused, the feedback will be adjusted to provide more detailed and gentler expressions.

[1424] The server generates optimal feedback information based on the converted text data, video analysis results, and emotion recognition results. The generated feedback information is converted into audio using the Google Cloud Text-to-Speech API. For example, if "milk" is identified through video analysis and its location becomes clear, the server generates feedback such as "The milk is in the refrigerated shelf in the front right." If the user is confused, the server also provides additional reassuring feedback such as "Don't worry, I'll show you the way."

[1425] This generated feedback is sent to the device and provided to the user via audible audio through the speaker, allowing the user to obtain the necessary information in real time and take appropriate action.

[1426] As a specific use case, consider a user searching for a specific product in a supermarket. The user speaks to their smart glasses or smartphone, asking, "Where is the milk?" The device's camera captures video of the surroundings and sends it to the server. The server then analyzes the video to determine the location of the milk and recognizes the user's confusion from the voice command. Finally, it provides feedback such as, "The milk is in the refrigerated shelf in front of you on the right. Don't worry, I'll show you the way."

[1427] Example prompt sentence:

[1428] 1. Video capture: "A user wearing smart glasses captures an image of a scene in a supermarket."

[1429] 2. Voice command: "The user speaks to the smart glasses, 'Where is the milk?'"

[1430] 3. Emotion Recognition: "The AI ​​receives voice commands and detects confusion in the user's voice."

[1431] 4. Image analysis: "Identify the location of refrigerated shelves in captured footage."

[1432] 5. Feedback generation: "When the user asks where the milk is, the AI ​​will respond by saying, 'The milk is in the refrigerator, in the front right.'"

[1433] 6. Emotional feedback: "If the user is confused, generate additional reassuring feedback."

[1434] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1435] Step 1:

[1436] The device activates its camera and captures video data of the surroundings. As input, it provides visual information of the surroundings. Here, the device (smartphone or smart glasses) uses its camera hardware to obtain the captured video data. As output, it obtains the captured video data.

[1437] Step 2:

[1438] The device sends the captured video data to the server. The input is the video data obtained in step 1. The data is sent to the server via the network. The output is the video data sent to the server. Specifically, the device establishes a network connection, divides the data into packets, and sends them.

[1439] Step 3:

[1440] The server analyzes the received video data and detects objects and text. The input is the video data sent in step 2. The server analyzes the video data using the Google Cloud Vision API and extracts object positions and text information. The output is the object and text detection data as the analysis result. Specifically, the server sends video data to the API and analyzes the response.

[1441] Step 4:

[1442] The device uses a microphone to capture the user's voice commands. The input is the user's voice. Here, the device's microphone hardware is used to capture voice data. The output is the captured voice command data. Specifically, the microphone converts the user's voice into a digital signal.

[1443] Step 5:

[1444] The device sends the captured voice data to the server. The input is the voice command data obtained in step 4. The data is sent to the server via the network. The output is the voice data sent to the server. Specifically, the device establishes a network connection, divides the voice data into packets, and sends them.

[1445] Step 6:

[1446] The server converts the received voice data into text data using speech recognition technology. The input is the voice data sent in step 5. The server uses SpeechRecognition to analyze the voice data and convert it into text. The output is the converted text data. Specifically, the speech recognition model analyzes the voice signal and generates the corresponding text.

[1447] Step 7:

[1448] The server analyzes the voice command and recognizes the user's emotion using the emotion recognition engine. The input is the text data obtained in step 6. The server recognizes the emotion using the emotion_recognition module. The output is the recognized emotion data. Specifically, the emotion recognition model analyzes the text and generates emotion labels.

[1449] Step 8:

[1450] The server generates feedback information based on the voice command, video analysis results, and emotion recognition results. The inputs are the object and text detection data from step 3, the text data from step 6, and the emotion recognition data from step 7. The server combines these data to generate optimal feedback information. The output is feedback information data. Specifically, the AI ​​model analyzes various data and creates a feedback message.

[1451] Step 9:

[1452] The server converts the generated feedback information into audio data. The input is the feedback information data generated in step 8. The server converts the text into audio data using the Google Cloud Text-to-Speech API. The output is audio feedback data. Specifically, the server sends text data to the API and receives audio data.

[1453] Step 10:

[1454] The terminal receives the audio feedback and provides the feedback information to the user via a speaker. The input is the audio feedback data sent in step 9. The terminal plays back this data and provides it to the user. The output is the audio feedback that the user hears. Specifically, the terminal's speaker plays back the digital audio signal as analog audio.

[1455] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1456] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1457] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1458] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1459] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1460] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1461] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1462] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1463] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1464] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1465] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1466] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1467] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1468] 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.

[1469] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1470] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1471] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1472] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1473] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1474] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1475] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1476] The following is further disclosed regarding the above embodiment.

[1477] (Claim 1)

[1478] a means for capturing video data of the surroundings using a camera;

[1479] means for transmitting the captured video data to a server;

[1480] A server analyzes the video data and detects objects and text;

[1481] a means for receiving voice commands using a microphone;

[1482] means for converting said voice commands into text;

[1483] a means for generating feedback information based on the voice command and the analysis result in the server;

[1484] means for providing the feedback information to the user audibly;

[1485] A system including:

[1486] (Claim 2)

[1487] 10. The system of claim 1, including the ability to read restaurant menus.

[1488] (Claim 3)

[1489] 10. The system of claim 1, further comprising the functionality to generate directions for driving directions.

[1490] "Example 1"

[1491] (Claim 1)

[1492] a means for capturing video data of the surroundings using a camera;

[1493] means for transmitting the captured video data to a server;

[1494] A server analyzes the video data and detects objects and text;

[1495] a means for receiving voice commands using a microphone;

[1496] means for converting said voice commands into text;

[1497] a means for generating feedback information based on the voice command and the analysis result in the server;

[1498] means for providing the feedback information to the user audibly;

[1499] A means for compressing and transferring the received video data in real time;

[1500] A means to use AI models to analyze objects and text in video using deep learning,

[1501] A means for processing the voice command using voice recognition technology and converting it into text data;

[1502] A means for generating appropriate feedback for a user in natural language using a generative AI model;

[1503] means for transmitting feedback information with low latency using a communication protocol;

[1504] A system including:

[1505] (Claim 2)

[1506] 10. The system of claim 1, including the ability to read restaurant menus.

[1507] (Claim 3)

[1508] 10. The system of claim 1, further comprising the functionality to generate directions for driving directions.

[1509] "Application Example 1"

[1510] (Claim 1)

[1511] a means for capturing video data of the surroundings using a camera;

[1512] means for transmitting the captured video data to a server;

[1513] A server analyzes the video data and detects objects and text;

[1514] a means for receiving voice commands using a microphone;

[1515] means for converting said voice commands into text;

[1516] a means for generating feedback information based on the voice command and the analysis result in the server;

[1517] means for providing the feedback information to the user audibly;

[1518] A means for a visually impaired person to obtain information about food delivery services using voice commands;

[1519] A system including:

[1520] (Claim 2)

[1521] 10. The system of claim 1, including the ability to read restaurant menus.

[1522] (Claim 3)

[1523] 10. The system of claim 1, further comprising the functionality to generate directions for driving directions.

[1524] (Claim 4)

[1525] The system of claim 1, further comprising a function for reading out menus of food delivery services.

[1526] (Claim 5)

[1527] The system according to claim 1, further comprising a function of notifying delivery location and time by voice.

[1528] "Example 2: Combining Emotion Engines"

[1529] (Claim 1)

[1530] a means for capturing video data of the surroundings using a camera;

[1531] means for transmitting the captured video data to a server;

[1532] A server analyzes the video data and detects objects and text;

[1533] a means for receiving voice commands using a microphone;

[1534] means for converting said voice commands into text;

[1535] A server analyzes the voice command and recognizes the user's emotion;

[1536] a means for generating feedback information based on the voice command, the analysis result, and emotion information in a server;

[1537] means for providing the feedback information to the user audibly;

[1538] A system including:

[1539] (Claim 2)

[1540] 10. The system of claim 1, including the ability to read restaurant menus.

[1541] (Claim 3)

[1542] 10. The system of claim 1, further comprising the functionality to generate directions for driving directions.

[1543] "Application example 2 when combining emotion engines"

[1544] (Claim 1)

[1545] a means for capturing video data of the surroundings using a camera;

[1546] means for transmitting the captured video data to a server;

[1547] A server analyzes the video data and detects objects and text;

[1548] a means for receiving voice commands using a microphone;

[1549] means for converting said voice commands into text;

[1550] a means for generating feedback information based on the voice command and the analysis result in the server;

[1551] means for providing the feedback information to the user audibly;

[1552] means for recognizing emotions from voice commands using an emotion recognition engine;

[1553] means for reflecting the emotion recognition result in feedback information;

[1554] A system including:

[1555] (Claim 2)

[1556] 10. The system of claim 1, including the ability to read restaurant menus.

[1557] (Claim 3)

[1558] 10. The system of claim 1, further comprising the functionality to generate directions for driving directions.

[1559] (Claim 4)

[1560] The system according to claim 1, characterized in that it includes a function for providing product information and location information within a physical store. [Explanation of symbols]

[1561] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for capturing video data of the surroundings using a camera; means for transmitting the captured video data to a server; A server analyzes the video data and detects objects and text; a means for receiving voice commands using a microphone; means for converting said voice commands into text; a means for generating feedback information based on the voice command and the analysis result in the server; means for providing the feedback information to the user audibly; A system including:

2. 10. The system of claim 1, further comprising a function for reading restaurant menus.

3. 10. The system of claim 1, further comprising the functionality to generate directions for driving directions.

Images