system

Abstract

We provide the system. [Solution] A means for receiving input data from a braille display, A means of converting received braille data into text data, A means of sending the converted text data to the server, A means for generating response text based on text data received by a server using AI generation, A means of sending the generated response text back to the terminal, A means of converting the returned response text into audio data, A means of playing audio data, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When visually impaired people efficiently utilize generative AI to obtain information and perform learning and communication, the process of information input and output in the conventional technology was inefficient and the usability was poor. In addition, there was a lack of a system that seamlessly performs a series of processes of accurately converting the input from a braille display into text, generating an appropriate response by a generative AI based on the text, and further reading out the response in voice.

Means for Solving the Problems

[0005] By providing a system that includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to a server, means for the server to generate response text based on the received text data using a generation AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, and means for playing the audio data, a system is provided that allows visually impaired people to obtain appropriate responses from information input through a braille display using a generation AI and hear them as audio. This enables visually impaired people to acquire information more efficiently and to engage in learning and communication.

[0006] A "braille display" is an electronic device used by visually impaired people to input and read braille.

[0007] "Input data" refers to the braille data entered by the user via a braille display.

[0008] "Means of receiving" refers to a device or program equipped with the function of receiving input data from a Braille display.

[0009] "Means of conversion" refers to a device or program equipped with the function of converting received braille data into corresponding text data.

[0010] "Text data" refers to Braille data converted into a string of characters, and is the data format transmitted to the server.

[0011] "Means of transmission" refers to a device or program for sending converted text data to a server over a network.

[0012] A "server" is a computer system used to process received text data.

[0013] "Generative AI" refers to an artificial intelligence system that can generate text in a manner similar to that of a human.

[0014] "Response text" refers to the string of characters generated by the generation AI based on the text data entered.

[0015] "Means of sending back" refers to a device or program that sends the generated response text back to the terminal via the network.

[0016] "Audio data" refers to a data format in which text data is converted into speech.

[0017] "Means for converting to audio data" refers to a device or program for converting received response text into speech.

[0018] "Means of playback" refers to speakers or audio playback devices used to allow users to listen to the converted audio data.

[0019] The term "system" refers to the totality of a set of devices and software that combine these functions to enable visually impaired individuals to obtain AI responses through a braille display. [Brief explanation of the drawing]

[0020] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6]It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display. The following describes in detail each component of the system and its operation.

[0042] System Overview

[0043] The system consists of three main elements: a braille display, a terminal, and a server. The user inputs text using the braille display, the AI ​​processes that text data to generate a response, and finally provides that response to the user in voice.

[0044] Braille display input reception (terminal)

[0045] The user inputs text using a braille display. The terminal receives the input data from the braille display. For example, if the user inputs "hello" into the braille display, the terminal receives that braille data.

[0046] Next, the terminal converts the received braille data into text data. The braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello".

[0047] Sending text data to the server (terminal)

[0048] The terminal sends the converted text data to the server. This is done using network communication. The text data is sent to a specific endpoint on the server side.

[0049] Response generation by AI (server)

[0050] The server receives text data sent from the terminal. Based on the received text data, the generation AI generates a response text.

[0051] For example, when the text data "Hello" is received, the generating AI will produce the response "Hello! How are you?".

[0052] Sending response text back to the terminal (server)

[0053] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[0054] Speech conversion and reading aloud of response text (on the device)

[0055] The terminal receives the response text sent back from the server. The received response text is then converted into audio data. This step utilizes a text-to-speech engine or similar technology.

[0056] For example, when the response text "Hello! How are you?" is received, it is converted into speech. The generated speech data is then read aloud to the user using a speaker or headphones.

[0057] Specific example

[0058] The process from input to response

[0059] The user enters "Hello" into the braille display.

[0060] The device receives the Braille data and converts it into the text data "Hello".

[0061] The device sends this text data to the server.

[0062] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[0063] The server sends the generated response back to the terminal.

[0064] The terminal converts the returned response into audio data and reads it aloud to the user.

[0065] In this way, based on data entered by a visually impaired person using a Braille display, the generating AI generates an appropriate response and provides it as audio, enabling a seamless process from information acquisition to response. The system of the present invention makes it possible for visually impaired people to learn and communicate more efficiently.

[0066] The following describes the processing flow.

[0067] Step 1:

[0068] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[0069] Step 2:

[0070] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[0071] Step 3:

[0072] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[0073] Step 4:

[0074] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[0075] Step 5:

[0076] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[0077] Step 6:

[0078] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[0079] Step 7:

[0080] The server sends the generated response text back to the terminal. This return is also done as an HTTP response, and the data is sent in a format that the terminal can receive.

[0081] Step 8:

[0082] The terminal receives the response text sent back from the server. The terminal analyzes the received data and extracts the response text "Hello! How are you?".

[0083] Step 9:

[0084] The device converts the received response text into audio data. It uses a text-to-speech engine to perform the process of converting the text "Hello! How are you?" into speech.

[0085] Step 10:

[0086] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[0087] In this way, the process is completed in which the generating AI processes the input from the braille display and provides feedback to the user as audio.

[0088] (Example 1)

[0089] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] Currently, there are limited methods and systems for visually impaired individuals to efficiently acquire digital information. Therefore, visually impaired individuals face many more difficulties in information acquisition compared to sighted individuals. In particular, information acquisition using generative AI involves a complex process from text data input to output, and an efficient system is needed to enable visually impaired individuals to perform this process smoothly. This invention aims to enable visually impaired individuals to efficiently acquire information from generative AI using a braille display.

[0091] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0092] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, software means for converting braille data, means for inputting text data as a prompt to the generation AI, means for the generation AI model to generate a response based on the prompt, and encryption means for securely sending and receiving text data. This makes it possible for visually impaired people to efficiently perform a series of operations from information acquisition to response through a braille display.

[0093] A "Braille display" is a device that allows visually impaired individuals to input and output information in Braille.

[0094] "Input data" refers to information entered by the user via a braille display and represented in braille format.

[0095] "Text data" refers to information obtained by converting braille data into text format, and is represented as a string of characters.

[0096] A "server" refers to a computer system that receives and transmits data over a network and generates response text using a generative AI.

[0097] "Generative AI" refers to artificial intelligence that uses natural language processing to generate appropriate responses to input text data.

[0098] "Response text" refers to text data generated by a generative AI as a response to the input text.

[0099] "Audio data" refers to information obtained by converting text data into an audio format, and is then played back as sound.

[0100] "Conversion means" refers to software or hardware used to convert received braille data into text data.

[0101] "Transmission means" refers to the function for sending the converted text data to the server.

[0102] "Receiving means" refers to the function that allows a server to receive data sent from a terminal.

[0103] "Playback means" refers to devices such as speakers and headphones that allow users to listen to audio data.

[0104] "Encryption methods" refer to technologies that encrypt data to maintain security when sending and receiving data.

[0105] This invention relates to a system for visually impaired individuals to efficiently obtain information generated by AI using a braille display. The system consists of three main components: a braille display, a terminal, and a server.

[0106] System Configuration

[0107] Braille display

[0108] The user inputs text using a braille display. When the user types "hello" on the braille display, the braille data is sent to the terminal.

[0109] terminal

[0110] The terminal receives braille data transmitted from the braille display. For example, when a user enters "hello," this is sent to the terminal as braille data ("⠓⠑⠇⠇⠕"). This braille data is converted into text data using braille reading software (e.g., Liblouis). For example, the braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello."

[0111] server

[0112] The terminal sends the converted text data to the server. Here, the text data is sent to the server using a network protocol such as HTTPS. The server processes the text data received from the terminal and uses a generative AI (natural language generation model) to generate a response text. For example, if "hello" is sent to the server, the generative AI will generate the response "Hello! How are you?".

[0113] Sending a response

[0114] The server sends the generated response text back to the terminal. The returned response text is then sent back to the terminal via HTTPS or another method. The terminal receives the response text returned from the server and uses a text-to-speech engine (e.g., Google® Cloud Text-to-Speech) to convert the response text into speech data.

[0115] Output of audio data

[0116] The converted audio data is read aloud to the user using an audio playback device such as a speaker or headphones. For example, the response "Hello! How are you?" is conveyed to the user verbally.

[0117] Specific example

[0118] The following are specific examples of how visually impaired individuals use the system.

[0119] The user enters "Hello" into the braille display.

[0120] The terminal receives the braille data and uses braille reading software to convert it into text data that says "Hello".

[0121] The terminal sends the converted text data "Hello" to the server.

[0122] The server receives text data, and a generation AI generates the response text "Hello! How are you?".

[0123] The server sends the generated response back to the terminal.

[0124] The device converts the received response text into audio data and reads it aloud to the user through the speaker.

[0125] Example of a prompt

[0126] The following are examples of prompt statements that are input to the generative AI model in this system:

[0127] When the user enters "Hello" into the Braille display

[0128] User: Hello

[0129] AI: Hello! How are you?

[0130] If the user enters "Tell me today's weather" into the braille display

[0131] User: Tell me today's weather.

[0132] AI: Today's weather is sunny. The high temperature will be 25 degrees Celsius and the low temperature will be 18 degrees Celsius.

[0133] This invention enables visually impaired individuals to efficiently acquire information through a Braille display and receive appropriate responses via voice generated by AI. By seamlessly facilitating the process from information acquisition to response, this system significantly contributes to the daily lives, learning, and communication of visually impaired individuals.

[0134] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0135] Step 1:

[0136] The user enters text into the braille display. For example, the input might be the braille text "Hello" (⠓⠑⠇⠇⠕). The input data is then transmitted to the terminal via the braille display.

[0137] Step 2:

[0138] The terminal converts the braille data received from the braille display into text data using braille reading software. Specifically, it uses braille reading software (e.g., Liblouis) to convert the braille data "⠓⠑⠇⠇⠕" into the text data "こんにちは" (hello).

[0139] Input: Braille data (⠓⠑⠇⠇⠕)

[0140] Output: Text data (Hello)

[0141] Step 3:

[0142] The terminal sends the converted text data to the server. The HTTPS protocol is used for communication, and the text data is sent to a specific endpoint on the server.

[0143] Input: Text data (Hello)

[0144] Output: Send to server

[0145] Step 4:

[0146] The server receives text data sent from the terminal. Based on the received data, it inputs prompts into the generating AI model. For example, if it receives the text data "Hello", it inputs the prompt into the generating AI model in the format "User:Hello\nAI:".

[0147] Input: Text data (Hello)

[0148] Output: Prompt input to the generated AI model

[0149] Step 5:

[0150] The server retrieves the response text from the generating AI. The generating AI model generates an appropriate response based on the prompt. For example, in response to the prompt "User: Hello\nAI:", it generates the response "Hello! How are you?".

[0151] Input: Prompt to generated AI

[0152] Output: Response text (Hello! How are you?)

[0153] Step 6:

[0154] The server sends the generated response text back to the terminal. The HTTPS protocol is used again for communication, and the response text is sent to the terminal.

[0155] Input: Response text (Hello! How are you?)

[0156] Output: Send to terminal

[0157] Step 7:

[0158] The terminal receives the response text sent back from the server and converts it into speech data using a text-to-speech engine. Specifically, it uses a text-to-speech engine (e.g., Google Cloud Text-to-Speech) to convert the text data "Hello! How are you?" into speech data.

[0159] Input: Response text (Hello! How are you?)

[0160] Output: Audio data

[0161] Step 8:

[0162] The generated audio data is played back to the user using an audio playback device such as a speaker or headphones. The user can listen to the audio data, "Hello! How are you?", and obtain the information.

[0163] Input: Audio data

[0164] Output: Audio playback

[0165] (Application Example 1)

[0166] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0167] Conventional support systems for the visually impaired have many limitations in efficiently obtaining information and communicating. Furthermore, visually impaired individuals often find it difficult to operate food delivery services or confirm their orders. Therefore, there is a need to develop a system that allows visually impaired individuals to use food delivery services simply and reliably.

[0168] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0169] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generating AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, and means for inputting an order for a food delivery service from a braille display, with the generating AI confirming and responding to the order. This makes it possible for visually impaired people to use food delivery services easily and reliably.

[0170] A "Braille display" is a device that allows visually impaired people to input and read information using Braille.

[0171] "Input data" refers to data in Braille that is transmitted from the Braille display to the terminal.

[0172] "Text data" refers to the received braille data converted into character data.

[0173] A "server" is a computer device that communicates with terminals via a network and generates response text based on text data using generative AI.

[0174] "Generative AI" is artificial intelligence that automatically generates appropriate response text based on received text data.

[0175] "Response text" refers to the response generated by the AI ​​related to the order details.

[0176] A "terminal" is a device that receives braille data from a braille display, converts it into text data, communicates with a server, and converts the returned response text into audio data.

[0177] "Audio data" refers to the conversion of response text into speech.

[0178] A "food delivery service" is a service that allows users to order food online and have it delivered to a specified location.

[0179] This invention relates to a system that allows visually impaired individuals to efficiently use food delivery services using a Braille display. The system's configuration and operation are described in detail below.

[0180] System Overview

[0181] The system consists of three main components: a braille display, a terminal, and a server. Users input their food delivery order details using the braille display, this data is processed by a generating AI, and the final response is provided to the user in voice.

[0182] Terminal configuration and operation

[0183] 1. Braille input reception

[0184] The user enters their food delivery order details into a braille display. The terminal receives the input data from the braille display. For example, if the user enters "I want to order a pizza" into the braille display, that braille data is transmitted to the terminal.

[0185] 2. Text data conversion

[0186] The terminal converts the received braille data into text data. Here, a braille-to-text conversion API is used. The braille data "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" is converted into the text data "I want to order a pizza".

[0187] 3. Sending text data to the server

[0188] The terminal sends the converted text data to the server. The HTTP protocol is used for communication. For example, the text data "I want to order a pizza" is sent to the server as an HTTP POST request.

[0189] Server configuration and operation

[0190] 4. Response generation by generative AI

[0191] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4(registered trademark)) generates a response text. For example, a response such as "Hello! Please choose a pizza from the menu" is generated.

[0192] Example of a prompt:

[0193] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[0194] 5. Sending a response text back to the terminal

[0195] The server sends the generated response text back to the terminal. For example, the response text "Hello! Please choose a pizza from the menu" is sent back to the terminal as an HTTP response.

[0196] Terminal reconfiguration and operation

[0197] 6. Audio Data Conversion

[0198] The terminal receives the response text sent back from the server. The received response text is converted into speech data. A text-to-speech engine (e.g., Google Cloud Text-to-Speech) is used in this step. For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech data.

[0199] 7. Audio data playback

[0200] The device reads the generated audio data aloud to the user using a speaker or headphones. For example, the device might say, "Hello! Please choose a pizza from the menu."

[0201] Specific example

[0202] The user enters "I want to order a pizza" into the braille display.

[0203] The terminal receives the Braille data and converts it into text data that says, "I want to order a pizza."

[0204] The device sends this text data to the server.

[0205] The server receives text data and a generating AI produces the response, "Hello! Please choose a pizza from the menu."

[0206] The server sends the generated response back to the terminal.

[0207] The terminal converts the returned response into audio data and reads it aloud to the user.

[0208] In this way, visually impaired individuals can place food delivery orders using a Braille display, and the AI ​​generates appropriate responses in voice, allowing for seamless order confirmation and use of the food delivery service.

[0209] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0210] Step 1:

[0211] The user enters their food delivery order details on a braille display. For example, the braille data entered here might be "I want to order a pizza." This data is then transmitted directly from the braille display to the terminal. Input: braille data. Output: braille data.

[0212] Step 2:

[0213] The terminal converts the braille data received from the braille display into text data. Specifically, it uses a braille-to-text conversion API to convert the braille "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" into the text "I want to order a pizza". Input: braille data. Output: text data.

[0214] Step 3:

[0215] The terminal sends the converted text data to the server. The HTTP protocol is used for this communication. The text data "I want to order a pizza" is sent to the specified endpoint as an HTTP POST request. Input: Text data. Output: HTTP request to the server.

[0216] Step 4:

[0217] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4) generates a response text. This response may include something like, "Hello! Please choose a pizza from the menu." The generative AI generates the response using the following prompt:

[0218] Example of a prompt:

[0219] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[0220] Input: Text data. Output: Response text.

[0221] Step 5:

[0222] The server sends a response text back to the terminal. The generated response text is sent to the terminal as an HTTP response. Input: Response text. Output: HTTP response from the server.

[0223] Step 6:

[0224] The device receives the response text sent back from the server. The received response text is converted into speech data using a text-to-speech engine (e.g., Google Cloud Text-to-Speech). For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech. Input: Response text. Output: Speech data.

[0225] Step 7:

[0226] The device plays the generated audio data and provides a voice response to the user. Specifically, the voice is read aloud to the user through the device's speaker or headphones. Input: Audio data. Output: Voice response.

[0227] The above describes the processing flow of the system program that implements the application example.

[0228] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0229] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display, and further to recognize the user's emotions and optimize the response. The following describes in detail each component of the system and its operation.

[0230] System Overview

[0231] The system consists of four main elements: a braille display, a terminal, a server, and an emotion engine. The user inputs text using the braille display, and the generating AI processes this text data to generate a response, which is then provided to the user in voice. In addition, the emotion engine recognizes the user's emotions, and the generating AI generates a response based on those emotions.

[0232] Braille display input reception (terminal)

[0233] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[0234] Next, the terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[0235] Text data conversion and server transmission (terminal)

[0236] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[0237] Next, the terminal sends the converted text data to the server. This is done using an HTTP POST request, and the text data is sent to the specified server endpoint.

[0238] Text data analysis and response generation (server)

[0239] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[0240] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[0241] Sending response text back to the terminal (server)

[0242] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[0243] Emotion engine operation (device)

[0244] The device uses an emotion engine to recognize the user's emotions. The emotion engine acquires emotion data from the user's voice, facial expressions, body movements, etc. This emotion data is analyzed in real time when the user makes input or receives a response.

[0245] Optimization of response text (server)

[0246] The server optimizes the response generated by the AI ​​based on the received emotional data. For example, if the emotional engine recognizes that the user is tired, the AI ​​will generate a gentle response such as, "Hi! What's up today?"

[0247] Speech conversion and reading aloud of response text (on the device)

[0248] The terminal receives the response text sent back from the server. The received text data is converted into audio data. A text-to-speech engine is used to perform the process of converting the text "Hello! How are you?" into speech.

[0249] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[0250] Specific example

[0251] The process from input to response

[0252] The user enters "Hello" into the braille display.

[0253] The device receives the Braille data and converts it into the text data "Hello".

[0254] The device sends this text data to the server.

[0255] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[0256] The server sends the generated response back to the terminal.

[0257] The terminal converts the returned response into audio data and reads it aloud to the user.

[0258] Furthermore, the emotion engine recognizes the user's emotions, and if it determines that the user is tired, the generated response will change to something like, "Hello, you look tired today. How can I help you?" This allows for dialogue that is more tailored to the user's state.

[0259] In this way, the generation AI processes the input from the braille display and completes a series of processes that provide the optimal response in voice, tailored to the user's emotions.

[0260] The following describes the processing flow.

[0261] Step 1:

[0262] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[0263] Step 2:

[0264] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[0265] Step 3:

[0266] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[0267] Step 4:

[0268] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[0269] Step 5:

[0270] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[0271] Step 6:

[0272] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[0273] Step 7:

[0274] The server invokes the emotion engine and requests data from the terminal necessary to recognize the user's emotions. This includes requesting a detailed analysis of emotional information such as cheek texture, tone of voice, and facial expressions.

[0275] Step 8:

[0276] The device activates its camera and microphone to collect user emotional information, gathering data in real time. For example, it might detect if the user's voice tone is low and their facial expression is tired.

[0277] Step 9:

[0278] The device collects emotional data and sends it to the server. The emotional information is encoded as audio or video data and sent to the server.

[0279] Step 10:

[0280] The server analyzes the received emotional data using an emotion engine to determine the user's emotional state. For example, it might determine that the user is tired.

[0281] Step 11:

[0282] The server optimizes the response text of the generative AI based on the analysis results from the emotion engine. For example, when the user is tired, it generates a response like "Hello! You look tired. What happened today?"

[0283] Step 12:

[0284] The server returns the optimized response text to the terminal. This return is also made as an HTTP response, and the data is sent in a format that the terminal can receive. <~0>000901> Step 13:

[0286] The terminal receives the response text sent from the server. The terminal analyzes the received data and extracts the response text "Hello! You look tired. What happened today?"

[0287] Step 14:

[0288] The terminal converts the received response text into voice data. It executes a process of converting the text "Hello! You look tired. What happened today?" into voice using a text-to-speech engine.

[0289] Step 15:

[0290] The terminal plays the generated voice data. It outputs the voice through a speaker or headphones and lets the user hear it. The user can receive the response from the generative AI in voice.

[0291] In this way, a series of processes in which the generative AI processes the input from the braille display and provides an optimal response according to the user's emotion as voice is completed.

[0292] (Example 2)

[0293] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0294] Braille displays are widely used as a means for visually impaired people to efficiently acquire information. However, the simple text input and output of Braille displays alone is insufficient to complement visual information. Furthermore, obtaining responses using generative AI models has limitations in providing optimal communication tailored to the user's emotional state. Therefore, a system is needed that recognizes the user's emotions and optimizes responses based on those emotions.

[0295] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for generating response text based on the received text data using an AI model generated by the server, means for acquiring user emotion data using an emotion engine that recognizes the user's emotions, means for optimizing the response text generated based on the acquired emotion data, means for returning the optimized response text to the terminal, means for converting the returned response text into audio data, and means for playing the audio data. This makes it possible for visually impaired people using a braille display to efficiently acquire AI information and receive optimal responses in real time that correspond to their emotions.

[0296] A "Braille display" is a device that allows visually impaired people to input and read Braille.

[0297] "Input data" refers to information entered by the user using a braille display.

[0298] A "terminal" is a device that is connected to a braille display and receives and processes input data.

[0299] "Text data" refers to character information obtained by converting braille data.

[0300] "Server" refers to a computer system that receives data transmitted from a terminal through a network and performs analysis and response generation.

[0301] "Generative AI model" refers to an algorithm or program for generating appropriate response text based on received text data using artificial intelligence.

[0302] "Emotion engine" refers to a system that acquires emotion data from a user's voice and expression and performs analysis thereof.

[0303] "Emotion data" refers to data indicating the emotional state of a user acquired by an emotion engine.

[0304] "Response text" refers to text data of a response to a user's input generated by a generative AI model.

[0305] "Optimization" refers to a process of adjusting the content and tone of a response text based on acquired emotion data.

[0306] "Voice data" refers to data obtained by converting text data into voice by a voice synthesis engine.

[0307] "Reproduction means" refers to a device used to let a user hear generated voice data, specifically, a speaker or headphones.

[0308] The present invention is a system in which a visually impaired person efficiently obtains information from a generative AI using a braille display, and recognizes the emotion of the user at that time to optimize the response. This system is composed of four main elements: a braille display, a terminal, a server, and an emotion engine.

[0309] Basic System Configuration

[0310] Braille display

[0311] Users input text using a braille display. For example, typing "hello" is done by pressing a specific button or key on the braille display. The braille display connects to the terminal via Bluetooth or USB and transmits the input data to the terminal in real time.

[0312] terminal

[0313] The terminal is responsible for receiving braille data from a braille display, converting it into text data, and sending that text data to the server. Using a conversion algorithm, it converts the braille data "⠓⠑⠇⠇⠕" into the text data "hello". It also uses a text-to-speech engine to convert the response text sent back from the server into audio data and play it back.

[0314] server

[0315] The server receives text data sent from the terminal, analyzes the received data, and generates response text using a generative AI model. Furthermore, it optimizes the response based on sentiment data from the sentiment engine and sends the optimized response text back to the terminal. As an example of response generation, the response "Hello! How are you?" is generated in response to the text "Hello".

[0316] Emotional Engine

[0317] The emotion engine built into the device analyzes the user's voice tone, facial expressions, and body movements to recognize their emotions. Emotional data is acquired in real time, sent to the server, and used to generate responses. For example, if the emotion engine detects that the user is tired, the server will generate a gentle response such as, "You look tired today. What's the matter?"

[0318] Specific example

[0319] The user inputs "hello" using a braille display. The data transmitted from the braille display is converted to the text "hello" by the terminal and sent to the server. The server generates a response, "Hello! How are you?" and then the emotion engine recognizes the user's emotions. If it determines, for example, that the user is tired, the response changes to "Hello, you look tired today. What's the matter?" Finally, this response is converted into audio data and transmitted to the user through speakers or headphones.

[0320] Example of a prompt

[0321] The user typed "Hello" using a braille display. The generated response was "Hello! How are you?". If the system determined the user was tired, the response changed to "Hello, you look tired today. What's the matter?".

[0322] In this way, the AI ​​processes input from the braille display and provides an optimal response in voice that reflects the user's emotions, completing a series of processes. This makes it possible for visually impaired people to acquire information and communicate more comfortably.

[0323] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0324] Step 1:

[0325] The user inputs "Hello" using a braille display. The braille display transmits the input data to the terminal in real time, and the terminal receives this data. Specifically, by performing certain button or key operations on the braille display, the braille data "⠓⠑⠇⠇⠕" is generated. This braille data is then transmitted to the terminal.

[0326] Input: User's Braille input data

[0327] Output: Data transmission from braille display to terminal

[0328] Step 2:

[0329] The terminal receives braille data "⠓⠑⠇⠇⠕" and converts it to text data "hello". Specifically, it applies a braille-to-corresponding text conversion algorithm to convert the braille data to text data. This converted text data is then sent to the server endpoint specified in the HTTP POST request.

[0330] Input: Received braille data "⠓⠑⠇⠇⠕"

[0331] Output: Converted text data "hello", and transmission to the server.

[0332] Step 3:

[0333] The server receives the text data "hello" sent from the terminal. The server analyzes the received data and calls a generative AI model to generate an appropriate response, "Hello! How are you?". Specifically, the process involves extracting text data from the HTTP request and inputting it into the generative AI model to generate the response text.

[0334] Input: Text data "hello" sent from the terminal.

[0335] Output: Generated response text "Hello! How are you?"

[0336] Step 4:

[0337] The server sends the generated response text back to the terminal via the network. Specifically, it structures the response text in JSON format or similar and sends it to the terminal as an HTTP response.

[0338] Input: Generated response text "Hello! How are you?"

[0339] Output: Send response text to the terminal as an HTTP response.

[0340] Step 5:

[0341] The device receives a response text sent back from the server. The device uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's tone of voice, facial expressions, body movements, etc., to obtain emotional data.

[0342] Input: Response text from the server, and user emotion input data (voice, facial expressions, etc.)

[0343] Output: Acquired sentiment data

[0344] Step 6:

[0345] The server receives emotion data sent from the terminal and optimizes the response text based on it. If the server detects that the user is tired, it reflects the parameters in the generating AI model and changes the response to a gentler tone, such as, "Hello, you look tired today. How can I help you?"

[0346] Input: Acquired sentiment data

[0347] Output: Optimized response text "Hello, you look tired today. How can I help you?"

[0348] Step 7:

[0349] The device converts the optimized response text into audio data. Specifically, it uses a text-to-speech engine to convert the response text "Hello! How are you?" into audio data. The generated audio data is then played back to the user through speakers or headphones.

[0350] Input: Optimized response text

[0351] Output: Generated audio data, playback of audio data

[0352] Through the steps described above, user input from the braille display is processed by a generative AI, and a response optimized for the user's emotions is provided as voice.

[0353] (Application Example 2)

[0354] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0355] When visually impaired individuals shop online, they face challenges such as inefficiently obtaining text information or receiving responses that reflect their emotions. Furthermore, there is a growing need for a more comfortable shopping experience by providing responses optimized based on the user's emotional state.

[0356] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0357] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for returning the generated response text to the terminal, means for converting the returned response text into audio data, means for playing the audio data, and means for analyzing the user's emotional data using an emotion recognition engine and optimizing the response by the generation AI based on the received emotional data. This enables visually impaired people to efficiently shop online using a braille display and to provide an optimal response based on the user's emotional state.

[0358] A "braille display" is a device that allows visually impaired people to input and output information using braille.

[0359] "Means for receiving input data" refers to a function or device for acquiring braille input data from a braille display.

[0360] "Means for converting to text data" refers to a process or device for converting Braille data into corresponding character data.

[0361] "Means of sending to the server" refers to a function or device for sending the converted text data to a server via a network.

[0362] "Generative AI" is an artificial intelligence technology that generates appropriate responses based on received text data.

[0363] "Means for generating response text" refers to a function or device for creating response text for input text data using a generation AI.

[0364] "Means of returning to the terminal" refers to a function or device for sending the generated response text back to the terminal via the network.

[0365] "Means for converting to audio data" refers to a process or device for converting the returned response text into an audio format.

[0366] "Means for playing audio data" refers to a function or device that allows the user to hear the converted audio data through a speaker or similar device.

[0367] An "emotion recognition engine" is a technology or device that analyzes and recognizes a user's emotional state from their voice, biosignals, etc.

[0368] "Means for analyzing emotional data" refers to a function or device that uses an emotional recognition engine to analyze a user's emotional state and acquire specific emotional data.

[0369] "Means for optimizing responses by generative AI" refers to a function or device for optimizing the responses generated by generative AI to match the user's emotional state, based on analyzed emotional data.

[0370] This invention relates to a system that enables visually impaired individuals to efficiently conduct online shopping using a Braille display, and further provides optimal responses tailored to the user's emotions.

[0371] System Configuration

[0372] The system consists of the following elements:

[0373] Braille display

[0374] Device (smartphone)

[0375] server

[0376] Emotion recognition engine

[0377] Generation AI

[0378] Speech synthesis engine

[0379] Operation overview

[0380] The user first inputs text using a braille display. For example, if the user types "What products do you recommend?" on the braille display, this braille data is sent to the terminal in real time.

[0381] The terminal converts the received braille data into text data. This conversion uses a conversion algorithm that converts the braille data "⠕⠽⠗⠕⠕⠫" into the text data "What products do you recommend?".

[0382] The converted text data is sent to the server using an HTTP POST request. The server receives this text data via the specified endpoint.

[0383] The server analyzes the received text data and calls a generation AI to generate a response text. For example, in response to the text data "What products do you recommend?", the generation AI generates the response "These are the products we recommend for you."

[0384] Next, the server sends the generated response text back to the terminal via the network. The returned response text is received by the terminal.

[0385] The device uses a speech synthesis engine to convert this response text into speech data. In this process, the text "Here are some products we recommend for you" is converted into speech.

[0386] Finally, the generated audio data is played to the user through speakers or headphones.

[0387] Furthermore, the system uses an emotion recognition engine to analyze the user's emotions in real time. The emotion recognition engine acquires emotional data from the user's voice, facial expressions, and body movements, and analyzes it when the user makes input or when a response is received. This emotional data is sent to the server, and the generating AI optimizes the response. For example, if the emotion recognition engine determines that the user is tired, the generated response will also change to a gentler tone, such as "Here are some easy-to-purchase products that we recommend for you."

[0388] Specific example

[0389] For example, if a user types "What products do you recommend?" on a braille display, and the emotion recognition engine detects the user's fatigue level, an example of the prompt message sent to the server would be as follows:

[0390] What are today's recommended products? The user seems a little tired.

[0391] Based on this prompt, the AI ​​generates a response saying, "Here are some easy-to-purchase products recommended for you," and communicates it to the user via voice. This allows visually impaired individuals to shop online efficiently and comfortably through a braille display and voice response.

[0392] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0393] Step 1:

[0394] The user inputs data using a braille display. This input data is provided in braille format. Specifically, when the user inputs "What products do you recommend?" into the braille display, braille data is generated. The braille display then transmits this data to the terminal.

[0395] Input: Braille data entered on a Braille display.

[0396] Output: Braille data sent to the terminal

[0397] Step 2:

[0398] The terminal converts the braille data received from the braille display into text data. The braille data "⠕⠽⠗⠕⠕⠫" is converted into the text data "What products do you recommend?". This conversion is performed by an algorithm that replaces braille characters with their corresponding characters.

[0399] Input: Braille data

[0400] Output: Text data "What products do you recommend?"

[0401] Step 3:

[0402] The terminal sends the converted text data to the server using an HTTP POST request. This request contains the converted text data.

[0403] Input: Text data "What products would you recommend?"

[0404] Output: HTTP POST request sent to the server

[0405] Step 4:

[0406] The server receives text data sent from the terminal and generates response text using a generation AI. Based on the prompt text corresponding to the input text "What products do you recommend?", the generation AI generates the response text "Here are the products we recommend for you."

[0407] Input: Text data sent from the device: "What products do you recommend?"

[0408] Output: Generated response text "Here are some products we recommend for you."

[0409] Step 5:

[0410] The server sends the generated response text back to the terminal. This return is also done via an HTTP request, and the response text is sent to the terminal.

[0411] Input: Generated response text "Here are some products we recommend for you."

[0412] Output: Response text sent back to the terminal

[0413] Step 6:

[0414] The device uses a speech synthesis engine to convert the returned response text into speech data. It performs the process of converting the text data "Here are some products we recommend for you" into speech data.

[0415] Input: Response text "Here are some products we recommend for you."

[0416] Output: Converted audio data

[0417] Step 7:

[0418] The device plays the generated audio data to the user through a speaker or headphones. This allows visually impaired individuals to confirm responses by voice.

[0419] Input: Converted audio data

[0420] Output: Audio data played from speakers or headphones: "Here are some products we recommend for you."

[0421] Step 8:

[0422] The device uses an emotion recognition engine to analyze the user's emotional data. Emotional data such as voice tone, facial expressions, and body movements are acquired in real time, and the user's emotional state is determined based on this. For example, the emotion recognition engine might determine that the user is tired.

[0423] Input: User's real-time sentiment data

[0424] Output: User's emotional state as an analysis result (e.g., tired)

[0425] Step 9:

[0426] The server optimizes the AI's response based on the received emotional data. If the AI ​​determines that the user is tired, it will generate a gentler response, such as, "Here are some easy-to-purchase products that we recommend for you."

[0427] Input: Sentiment data analysis results

[0428] Output: Optimized response text

[0429] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0430] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0431] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0432] [Second Embodiment]

[0433] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0434] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0435] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0436] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0437] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0438] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0439] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0440] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0441] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0442] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0443] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0444] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0445] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display. The following describes in detail each component of the system and its operation.

[0446] System Overview

[0447] The system consists of three main elements: a braille display, a terminal, and a server. The user inputs text using the braille display, the AI ​​processes that text data to generate a response, and finally provides that response to the user in voice.

[0448] Braille display input reception (terminal)

[0449] The user inputs text using a braille display. The terminal receives the input data from the braille display. For example, if the user inputs "hello" into the braille display, the terminal receives that braille data.

[0450] Next, the terminal converts the received braille data into text data. The braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello".

[0451] Sending text data to the server (terminal)

[0452] The terminal sends the converted text data to the server. This is done using network communication. The text data is sent to a specific endpoint on the server side.

[0453] Response generation by AI (server)

[0454] The server receives text data sent from the terminal. Based on the received text data, the generation AI generates a response text.

[0455] For example, when the text data "Hello" is received, the generating AI will produce the response "Hello! How are you?".

[0456] Sending response text back to the terminal (server)

[0457] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[0458] Speech conversion and reading aloud of response text (on the device)

[0459] The terminal receives the response text sent back from the server. The received response text is then converted into audio data. This step utilizes a text-to-speech engine or similar technology.

[0460] For example, when the response text "Hello! How are you?" is received, it is converted into speech. The generated speech data is then read aloud to the user using a speaker or headphones.

[0461] Specific example

[0462] The process from input to response

[0463] The user enters "Hello" into the braille display.

[0464] The device receives the Braille data and converts it into the text data "Hello".

[0465] The device sends this text data to the server.

[0466] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[0467] The server sends the generated response back to the terminal.

[0468] The terminal converts the returned response into audio data and reads it aloud to the user.

[0469] In this way, based on data entered by a visually impaired person using a Braille display, the generating AI generates an appropriate response and provides it as audio, enabling a seamless process from information acquisition to response. The system of the present invention makes it possible for visually impaired people to learn and communicate more efficiently.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[0473] Step 2:

[0474] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[0475] Step 3:

[0476] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[0477] Step 4:

[0478] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[0479] Step 5:

[0480] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[0481] Step 6:

[0482] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[0483] Step 7:

[0484] The server sends the generated response text back to the terminal. This return is also done as an HTTP response, and the data is sent in a format that the terminal can receive.

[0485] Step 8:

[0486] The terminal receives the response text sent back from the server. The terminal analyzes the received data and extracts the response text "Hello! How are you?".

[0487] Step 9:

[0488] The device converts the received response text into audio data. It uses a text-to-speech engine to perform the process of converting the text "Hello! How are you?" into speech.

[0489] Step 10:

[0490] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[0491] In this way, the process is completed in which the generating AI processes the input from the braille display and provides feedback to the user as audio.

[0492] (Example 1)

[0493] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0494] Currently, there are limited methods and systems for visually impaired individuals to efficiently acquire digital information. Therefore, visually impaired individuals face many more difficulties in information acquisition compared to sighted individuals. In particular, information acquisition using generative AI involves a complex process from text data input to output, and an efficient system is needed to enable visually impaired individuals to perform this process smoothly. This invention aims to enable visually impaired individuals to efficiently acquire information from generative AI using a braille display.

[0495] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0496] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, software means for converting braille data, means for inputting text data as a prompt to the generation AI, means for the generation AI model to generate a response based on the prompt, and encryption means for securely sending and receiving text data. This makes it possible for visually impaired people to efficiently perform a series of operations from information acquisition to response through a braille display.

[0497] A "Braille display" is a device that allows visually impaired individuals to input and output information in Braille.

[0498] "Input data" refers to information entered by the user via a braille display and represented in braille format.

[0499] "Text data" refers to information obtained by converting braille data into text format, and is represented as a string of characters.

[0500] A "server" refers to a computer system that receives and transmits data over a network and generates response text using a generative AI.

[0501] "Generative AI" refers to artificial intelligence that uses natural language processing to generate appropriate responses to input text data.

[0502] "Response text" refers to text data generated by a generative AI as a response to the input text.

[0503] "Audio data" refers to information obtained by converting text data into an audio format, and is then played back as sound.

[0504] "Conversion means" refers to software or hardware used to convert received braille data into text data.

[0505] "Transmission means" refers to the function for sending the converted text data to the server.

[0506] "Receiving means" refers to the function that allows a server to receive data sent from a terminal.

[0507] "Playback means" refers to devices such as speakers and headphones that allow users to listen to audio data.

[0508] "Encryption methods" refer to technologies that encrypt data to maintain security when sending and receiving data.

[0509] This invention relates to a system for visually impaired individuals to efficiently obtain information generated by AI using a braille display. The system consists of three main components: a braille display, a terminal, and a server.

[0510] System Configuration

[0511] Braille display

[0512] The user inputs text using a braille display. When the user types "hello" on the braille display, the braille data is sent to the terminal.

[0513] terminal

[0514] The terminal receives braille data transmitted from the braille display. For example, when a user enters "hello," this is sent to the terminal as braille data ("⠓⠑⠇⠇⠕"). This braille data is converted into text data using braille reading software (e.g., Liblouis). For example, the braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello."

[0515] server

[0516] The terminal sends the converted text data to the server. Here, the text data is sent to the server using a network protocol such as HTTPS. The server processes the text data received from the terminal and uses a generative AI (natural language generation model) to generate a response text. For example, if "hello" is sent to the server, the generative AI will generate the response "Hello! How are you?".

[0517] Sending a response

[0518] The server sends the generated response text back to the terminal. The returned response text is then sent back to the terminal via HTTPS or another method. The terminal receives the response text returned from the server and uses a text-to-speech engine (e.g., Google Cloud Text-to-Speech) to convert the response text into speech data.

[0519] Output of audio data

[0520] The converted audio data is read aloud to the user using an audio playback device such as a speaker or headphones. For example, the response "Hello! How are you?" is conveyed to the user verbally.

[0521] Specific example

[0522] The following are specific examples of how visually impaired individuals use the system.

[0523] The user enters "Hello" into the braille display.

[0524] The terminal receives the braille data and uses braille reading software to convert it into text data that says "Hello".

[0525] The terminal sends the converted text data "Hello" to the server.

[0526] The server receives text data, and a generation AI generates the response text "Hello! How are you?".

[0527] The server sends the generated response back to the terminal.

[0528] The device converts the received response text into audio data and reads it aloud to the user through the speaker.

[0529] Example of a prompt

[0530] The following are examples of prompt statements that are input to the generative AI model in this system:

[0531] When the user enters "Hello" into the Braille display

[0532] User: Hello

[0533] AI: Hello! How are you?

[0534] If the user enters "Tell me today's weather" into the braille display

[0535] User: Tell me today's weather.

[0536] AI: Today's weather is sunny. The high temperature will be 25 degrees Celsius and the low temperature will be 18 degrees Celsius.

[0537] This invention enables visually impaired individuals to efficiently acquire information through a Braille display and receive appropriate responses via voice generated by AI. By seamlessly facilitating the process from information acquisition to response, this system significantly contributes to the daily lives, learning, and communication of visually impaired individuals.

[0538] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0539] Step 1:

[0540] The user enters text into the braille display. For example, the input might be the braille text "Hello" (⠓⠑⠇⠇⠕). The input data is then transmitted to the terminal via the braille display.

[0541] Step 2:

[0542] The terminal converts the braille data received from the braille display into text data using braille reading software. Specifically, it uses braille reading software (e.g., Liblouis) to convert the braille data "⠓⠑⠇⠇⠕" into the text data "こんにちは" (hello).

[0543] Input: Braille data (⠓⠑⠇⠇⠕)

[0544] Output: Text data (Hello)

[0545] Step 3:

[0546] The terminal sends the converted text data to the server. The HTTPS protocol is used for communication, and the text data is sent to a specific endpoint on the server.

[0547] Input: Text data (Hello)

[0548] Output: Send to server

[0549] Step 4:

[0550] The server receives text data sent from the terminal. Based on the received data, it inputs prompts into the generating AI model. For example, if it receives the text data "Hello", it inputs the prompt into the generating AI model in the format "User:Hello\nAI:".

[0551] Input: Text data (Hello)

[0552] Output: Prompt input to the generated AI model

[0553] Step 5:

[0554] The server retrieves the response text from the generating AI. The generating AI model generates an appropriate response based on the prompt. For example, in response to the prompt "User: Hello\nAI:", it generates the response "Hello! How are you?".

[0555] Input: Prompt to generated AI

[0556] Output: Response text (Hello! How are you?)

[0557] Step 6:

[0558] The server sends the generated response text back to the terminal. The HTTPS protocol is used again for communication, and the response text is sent to the terminal.

[0559] Input: Response text (Hello! How are you?)

[0560] Output: Send to terminal

[0561] Step 7:

[0562] The terminal receives the response text sent back from the server and converts it into speech data using a text-to-speech engine. Specifically, it uses a text-to-speech engine (e.g., Google Cloud Text-to-Speech) to convert the text data "Hello! How are you?" into speech data.

[0563] Input: Response text (Hello! How are you?)

[0564] Output: Audio data

[0565] Step 8:

[0566] The generated audio data is played back to the user using an audio playback device such as a speaker or headphones. The user can listen to the audio data, "Hello! How are you?", and obtain the information.

[0567] Input: Audio data

[0568] Output: Audio playback

[0569] (Application Example 1)

[0570] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0571] Conventional support systems for the visually impaired have many limitations in efficiently obtaining information and communicating. Furthermore, visually impaired individuals often find it difficult to operate food delivery services or confirm their orders. Therefore, there is a need to develop a system that allows visually impaired individuals to use food delivery services simply and reliably.

[0572] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0573] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generating AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, and means for inputting an order for a food delivery service from a braille display, with the generating AI confirming and responding to the order. This makes it possible for visually impaired people to use food delivery services easily and reliably.

[0574] A "Braille display" is a device that allows visually impaired people to input and read information using Braille.

[0575] "Input data" refers to data in Braille that is transmitted from the Braille display to the terminal.

[0576] "Text data" refers to the received braille data converted into character data.

[0577] A "server" is a computer device that communicates with terminals via a network and generates response text based on text data using generative AI.

[0578] "Generative AI" is artificial intelligence that automatically generates appropriate response text based on received text data.

[0579] "Response text" refers to the response generated by the AI ​​related to the order details.

[0580] A "terminal" is a device that receives braille data from a braille display, converts it into text data, communicates with a server, and converts the returned response text into audio data.

[0581] "Audio data" refers to the conversion of response text into speech.

[0582] A "food delivery service" is a service that allows users to order food online and have it delivered to a specified location.

[0583] This invention relates to a system that allows visually impaired individuals to efficiently use food delivery services using a Braille display. The system's configuration and operation are described in detail below.

[0584] System Overview

[0585] The system consists of three main components: a braille display, a terminal, and a server. Users input their food delivery order details using the braille display, this data is processed by a generating AI, and the final response is provided to the user in voice.

[0586] Terminal configuration and operation

[0587] 1. Braille input reception

[0588] The user enters their food delivery order details into a braille display. The terminal receives the input data from the braille display. For example, if the user enters "I want to order a pizza" into the braille display, that braille data is transmitted to the terminal.

[0589] 2. Text data conversion

[0590] The terminal converts the received braille data into text data. Here, a braille-to-text conversion API is used. The braille data "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" is converted into the text data "I want to order a pizza".

[0591] 3. Sending text data to the server

[0592] The terminal sends the converted text data to the server. The HTTP protocol is used for communication. For example, the text data "I want to order a pizza" is sent to the server as an HTTP POST request.

[0593] Server configuration and operation

[0594] 4. Response generation by generative AI

[0595] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4) generates a response text. For example, a response such as "Hello! Please choose a pizza from the menu" is generated.

[0596] Example of a prompt:

[0597] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[0598] 5. Sending a response text back to the terminal

[0599] The server sends the generated response text back to the terminal. For example, the response text "Hello! Please choose a pizza from the menu" is sent back to the terminal as an HTTP response.

[0600] Terminal reconfiguration and operation

[0601] 6. Audio Data Conversion

[0602] The terminal receives the response text sent back from the server. The received response text is converted into speech data. A text-to-speech engine (e.g., Google Cloud Text-to-Speech) is used in this step. For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech data.

[0603] 7. Audio data playback

[0604] The device reads the generated audio data aloud to the user using a speaker or headphones. For example, the device might say, "Hello! Please choose a pizza from the menu."

[0605] Specific example

[0606] The user enters "I want to order a pizza" into the braille display.

[0607] The terminal receives the Braille data and converts it into text data that says, "I want to order a pizza."

[0608] The device sends this text data to the server.

[0609] The server receives text data and a generating AI produces the response, "Hello! Please choose a pizza from the menu."

[0610] The server sends the generated response back to the terminal.

[0611] The terminal converts the returned response into audio data and reads it aloud to the user.

[0612] In this way, visually impaired individuals can place food delivery orders using a Braille display, and the AI ​​generates appropriate responses in voice, allowing for seamless order confirmation and use of the food delivery service.

[0613] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0614] Step 1:

[0615] The user enters their food delivery order details on a braille display. For example, the braille data entered here might be "I want to order a pizza." This data is then transmitted directly from the braille display to the terminal. Input: braille data. Output: braille data.

[0616] Step 2:

[0617] The terminal converts the braille data received from the braille display into text data. Specifically, it uses a braille-to-text conversion API to convert the braille "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" into the text "I want to order a pizza". Input: braille data. Output: text data.

[0618] Step 3:

[0619] The terminal sends the converted text data to the server. The HTTP protocol is used for this communication. The text data "I want to order a pizza" is sent to the specified endpoint as an HTTP POST request. Input: Text data. Output: HTTP request to the server.

[0620] Step 4:

[0621] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4) generates a response text. This response may include something like, "Hello! Please choose a pizza from the menu." The generative AI generates the response using the following prompt:

[0622] Example of a prompt:

[0623] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[0624] Input: Text data. Output: Response text.

[0625] Step 5:

[0626] The server sends a response text back to the terminal. The generated response text is sent to the terminal as an HTTP response. Input: Response text. Output: HTTP response from the server.

[0627] Step 6:

[0628] The device receives the response text sent back from the server. The received response text is converted into speech data using a text-to-speech engine (e.g., Google Cloud Text-to-Speech). For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech. Input: Response text. Output: Speech data.

[0629] Step 7:

[0630] The device plays the generated audio data and provides a voice response to the user. Specifically, the voice is read aloud to the user through the device's speaker or headphones. Input: Audio data. Output: Voice response.

[0631] The above describes the processing flow of the system program that implements the application example.

[0632] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0633] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display, and further to recognize the user's emotions and optimize the response. The following describes in detail each component of the system and its operation.

[0634] System Overview

[0635] The system consists of four main elements: a braille display, a terminal, a server, and an emotion engine. The user inputs text using the braille display, and the generating AI processes this text data to generate a response, which is then provided to the user in voice. In addition, the emotion engine recognizes the user's emotions, and the generating AI generates a response based on those emotions.

[0636] Braille display input reception (terminal)

[0637] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[0638] Next, the terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[0639] Text data conversion and server transmission (terminal)

[0640] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[0641] Next, the terminal sends the converted text data to the server. This is done using an HTTP POST request, and the text data is sent to the specified server endpoint.

[0642] Text data analysis and response generation (server)

[0643] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[0644] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[0645] Sending response text back to the terminal (server)

[0646] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[0647] Emotion engine operation (device)

[0648] The device uses an emotion engine to recognize the user's emotions. The emotion engine acquires emotion data from the user's voice, facial expressions, body movements, etc. This emotion data is analyzed in real time when the user makes input or receives a response.

[0649] Optimization of response text (server)

[0650] The server optimizes the response generated by the AI ​​based on the received emotional data. For example, if the emotional engine recognizes that the user is tired, the AI ​​will generate a gentle response such as, "Hi! What's up today?"

[0651] Speech conversion and reading aloud of response text (on the device)

[0652] The terminal receives the response text sent back from the server. The received text data is converted into audio data. A text-to-speech engine is used to perform the process of converting the text "Hello! How are you?" into speech.

[0653] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[0654] Specific example

[0655] The process from input to response

[0656] The user enters "Hello" into the braille display.

[0657] The device receives the Braille data and converts it into the text data "Hello".

[0658] The device sends this text data to the server.

[0659] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[0660] The server sends the generated response back to the terminal.

[0661] The terminal converts the returned response into audio data and reads it aloud to the user.

[0662] Furthermore, the emotion engine recognizes the user's emotions, and if it determines that the user is tired, the generated response will change to something like, "Hello, you look tired today. How can I help you?" This allows for dialogue that is more tailored to the user's state.

[0663] In this way, the generation AI processes the input from the braille display and completes a series of processes that provide the optimal response in voice, tailored to the user's emotions.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[0667] Step 2:

[0668] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[0669] Step 3:

[0670] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[0671] Step 4:

[0672] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[0673] Step 5:

[0674] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[0675] Step 6:

[0676] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[0677] Step 7:

[0678] The server invokes the emotion engine and requests data from the terminal necessary to recognize the user's emotions. This includes requesting a detailed analysis of emotional information such as cheek texture, tone of voice, and facial expressions.

[0679] Step 8:

[0680] The device activates its camera and microphone to collect user emotional information, gathering data in real time. For example, it might detect if the user's voice tone is low and their facial expression is tired.

[0681] Step 9:

[0682] The device collects emotional data and sends it to the server. The emotional information is encoded as audio or video data and sent to the server.

[0683] Step 10:

[0684] The server analyzes the received emotional data using an emotion engine to determine the user's emotional state. For example, it might determine that the user is tired.

[0685] Step 11:

[0686] The server optimizes the AI's response text based on the analysis results from the emotion engine. For example, if the user is tired, it might generate a response like, "Hello! You must be tired. How was your day?"

[0687] Step 12:

[0688] The server sends an optimized response text back to the terminal. This response is also sent as an HTTP response, and the data is sent in a format that the terminal can receive.

[0689] Step 13:

[0690] The terminal receives the response text sent back from the server. The terminal analyzes the received data and extracts the response text "Hello! Thank you for your hard work. What happened today?".

[0691] Step 14:

[0692] The terminal converts the received response text into audio data. Using a text-to-speech engine, it performs the process of converting the text "Hello! Good work today. What happened today?" into speech.

[0693] Step 15:

[0694] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[0695] In this way, the generation AI processes the input from the braille display and completes a series of processes that provide the optimal response in voice, tailored to the user's emotions.

[0696] (Example 2)

[0697] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0698] Braille displays are widely used as a means for visually impaired people to efficiently acquire information. However, the simple text input and output of Braille displays alone is insufficient to complement visual information. Furthermore, obtaining responses using generative AI models has limitations in providing optimal communication tailored to the user's emotional state. Therefore, a system is needed that recognizes the user's emotions and optimizes responses based on those emotions.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for generating response text based on the received text data using an AI model generated by the server, means for acquiring user emotion data using an emotion engine that recognizes the user's emotions, means for optimizing the response text generated based on the acquired emotion data, means for returning the optimized response text to the terminal, means for converting the returned response text into audio data, and means for playing the audio data. This makes it possible for visually impaired people using a braille display to efficiently acquire AI information and receive optimal responses in real time that correspond to their emotions.

[0700] A "Braille display" is a device that allows visually impaired people to input and read Braille.

[0701] "Input data" refers to information entered by the user using a braille display.

[0702] A "terminal" is a device that is connected to a braille display and receives and processes input data.

[0703] "Text data" refers to character information obtained by converting Braille data.

[0704] A "server" is a computer system that receives data transmitted from terminals via a network and performs analysis and response generation.

[0705] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate appropriate response text based on received text data.

[0706] An "emotion engine" is a system that acquires emotional data from the user's voice and facial expressions and analyzes that data.

[0707] "Emotional data" refers to data that indicates the user's emotional state, acquired by the emotion engine.

[0708] "Response text" refers to the text data of the response to user input, generated by a generative AI model.

[0709] "Optimization" refers to the process of adjusting the content and tone of response text based on acquired sentiment data.

[0710] "Audio data" refers to data obtained by converting text data into speech using a speech synthesis engine.

[0711] "Playback means" refers to devices used to allow users to listen to the generated audio data, specifically speakers and headphones.

[0712] This invention provides a system that enables visually impaired individuals to efficiently obtain information from AI-generated using a Braille display, while recognizing the user's emotions and optimizing the response accordingly. The system consists of four main components: a Braille display, a terminal, a server, and an emotion engine.

[0713] Basic System Configuration

[0714] Braille display

[0715] Users input text using a braille display. For example, typing "hello" is done by pressing a specific button or key on the braille display. The braille display connects to the terminal via Bluetooth or USB and transmits the input data to the terminal in real time.

[0716] terminal

[0717] The terminal is responsible for receiving braille data from a braille display, converting it into text data, and sending that text data to the server. Using a conversion algorithm, it converts the braille data "⠓⠑⠇⠇⠕" into the text data "hello". It also uses a text-to-speech engine to convert the response text sent back from the server into audio data and play it back.

[0718] server

[0719] The server receives text data sent from the terminal, analyzes the received data, and generates response text using a generative AI model. Furthermore, it optimizes the response based on sentiment data from the sentiment engine and sends the optimized response text back to the terminal. As an example of response generation, the response "Hello! How are you?" is generated in response to the text "Hello".

[0720] Emotional Engine

[0721] The emotion engine built into the device analyzes the user's voice tone, facial expressions, and body movements to recognize their emotions. Emotional data is acquired in real time, sent to the server, and used to generate responses. For example, if the emotion engine detects that the user is tired, the server will generate a gentle response such as, "You look tired today. What's the matter?"

[0722] Specific example

[0723] The user inputs "hello" using a braille display. The data transmitted from the braille display is converted to the text "hello" by the terminal and sent to the server. The server generates a response, "Hello! How are you?" and then the emotion engine recognizes the user's emotions. If it determines, for example, that the user is tired, the response changes to "Hello, you look tired today. What's the matter?" Finally, this response is converted into audio data and transmitted to the user through speakers or headphones.

[0724] Example of a prompt

[0725] The user typed "Hello" using a braille display. The generated response was "Hello! How are you?". If the system determined the user was tired, the response changed to "Hello, you look tired today. What's the matter?".

[0726] In this way, the AI ​​processes input from the braille display and provides an optimal response in voice that reflects the user's emotions, completing a series of processes. This makes it possible for visually impaired people to acquire information and communicate more comfortably.

[0727] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0728] Step 1:

[0729] The user inputs "Hello" using a braille display. The braille display transmits the input data to the terminal in real time, and the terminal receives this data. Specifically, by performing certain button or key operations on the braille display, the braille data "⠓⠑⠇⠇⠕" is generated. This braille data is then transmitted to the terminal.

[0730] Input: User's Braille input data

[0731] Output: Data transmission from braille display to terminal

[0732] Step 2:

[0733] The terminal receives braille data "⠓⠑⠇⠇⠕" and converts it to text data "hello". Specifically, it applies a braille-to-corresponding text conversion algorithm to convert the braille data to text data. This converted text data is then sent to the server endpoint specified in the HTTP POST request.

[0734] Input: Received braille data "⠓⠑⠇⠇⠕"

[0735] Output: Converted text data "hello", and transmission to the server.

[0736] Step 3:

[0737] The server receives the text data "hello" sent from the terminal. The server analyzes the received data and calls a generative AI model to generate an appropriate response, "Hello! How are you?". Specifically, the process involves extracting text data from the HTTP request and inputting it into the generative AI model to generate the response text.

[0738] Input: Text data "hello" sent from the terminal.

[0739] Output: Generated response text "Hello! How are you?"

[0740] Step 4:

[0741] The server sends the generated response text back to the terminal via the network. Specifically, it structures the response text in JSON format or similar and sends it to the terminal as an HTTP response.

[0742] Input: Generated response text "Hello! How are you?"

[0743] Output: Send response text to the terminal as an HTTP response.

[0744] Step 5:

[0745] The device receives a response text sent back from the server. The device uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's tone of voice, facial expressions, body movements, etc., to obtain emotional data.

[0746] Input: Response text from the server, and user emotion input data (voice, facial expressions, etc.)

[0747] Output: Acquired sentiment data

[0748] Step 6:

[0749] The server receives emotion data sent from the terminal and optimizes the response text based on it. If the server detects that the user is tired, it reflects the parameters in the generating AI model and changes the response to a gentler tone, such as, "Hello, you look tired today. How can I help you?"

[0750] Input: Acquired sentiment data

[0751] Output: Optimized response text "Hello, you look tired today. How can I help you?"

[0752] Step 7:

[0753] The device converts the optimized response text into audio data. Specifically, it uses a text-to-speech engine to convert the response text "Hello! How are you?" into audio data. The generated audio data is then played back to the user through speakers or headphones.

[0754] Input: Optimized response text

[0755] Output: Generated audio data, playback of audio data

[0756] Through the steps described above, user input from the braille display is processed by a generative AI, and a response optimized for the user's emotions is provided as voice.

[0757] (Application Example 2)

[0758] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0759] When visually impaired individuals shop online, they face challenges such as inefficiently obtaining text information or receiving responses that reflect their emotions. Furthermore, there is a growing need for a more comfortable shopping experience by providing responses optimized based on the user's emotional state.

[0760] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0761] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for returning the generated response text to the terminal, means for converting the returned response text into audio data, means for playing the audio data, and means for analyzing the user's emotional data using an emotion recognition engine and optimizing the response by the generation AI based on the received emotional data. This enables visually impaired people to efficiently shop online using a braille display and to provide an optimal response based on the user's emotional state.

[0762] A "braille display" is a device that allows visually impaired people to input and output information using braille.

[0763] "Means for receiving input data" refers to a function or device for acquiring braille input data from a braille display.

[0764] "Means for converting to text data" refers to a process or device for converting Braille data into corresponding character data.

[0765] "Means of sending to the server" refers to a function or device for sending the converted text data to a server via a network.

[0766] "Generative AI" is an artificial intelligence technology that generates appropriate responses based on received text data.

[0767] "Means for generating response text" refers to a function or device for creating response text for input text data using a generation AI.

[0768] "Means of returning to the terminal" refers to a function or device for sending the generated response text back to the terminal via the network.

[0769] "Means for converting to audio data" refers to a process or device for converting the returned response text into an audio format.

[0770] "Means for playing audio data" refers to a function or device that allows the user to hear the converted audio data through a speaker or similar device.

[0771] An "emotion recognition engine" is a technology or device that analyzes and recognizes a user's emotional state from their voice, biosignals, etc.

[0772] "Means for analyzing emotional data" refers to a function or device that uses an emotional recognition engine to analyze a user's emotional state and acquire specific emotional data.

[0773] "Means for optimizing responses by generative AI" refers to a function or device for optimizing the responses generated by generative AI to match the user's emotional state, based on analyzed emotional data.

[0774] This invention relates to a system that enables visually impaired individuals to efficiently conduct online shopping using a Braille display, and further provides optimal responses tailored to the user's emotions.

[0775] System Configuration

[0776] The system consists of the following elements:

[0777] Braille display

[0778] Device (smartphone)

[0779] server

[0780] Emotion recognition engine

[0781] Generation AI

[0782] Speech synthesis engine

[0783] Operation overview

[0784] The user first inputs text using a braille display. For example, if the user types "What products do you recommend?" on the braille display, this braille data is sent to the terminal in real time.

[0785] The terminal converts the received braille data into text data. This conversion uses a conversion algorithm that converts the braille data "⠕⠽⠗⠕⠕⠫" into the text data "What products do you recommend?".

[0786] The converted text data is sent to the server using an HTTP POST request. The server receives this text data via the specified endpoint.

[0787] The server analyzes the received text data and calls a generation AI to generate a response text. For example, in response to the text data "What products do you recommend?", the generation AI generates the response "These are the products we recommend for you."

[0788] Next, the server sends the generated response text back to the terminal via the network. The returned response text is received by the terminal.

[0789] The device uses a speech synthesis engine to convert this response text into speech data. In this process, the text "Here are some products we recommend for you" is converted into speech.

[0790] Finally, the generated audio data is played to the user through speakers or headphones.

[0791] Furthermore, the system uses an emotion recognition engine to analyze the user's emotions in real time. The emotion recognition engine acquires emotional data from the user's voice, facial expressions, and body movements, and analyzes it when the user makes input or when a response is received. This emotional data is sent to the server, and the generating AI optimizes the response. For example, if the emotion recognition engine determines that the user is tired, the generated response will also change to a gentler tone, such as "Here are some easy-to-purchase products that we recommend for you."

[0792] Specific example

[0793] For example, if a user types "What products do you recommend?" on a braille display, and the emotion recognition engine detects the user's fatigue level, an example of the prompt message sent to the server would be as follows:

[0794] What are today's recommended products? The user seems a little tired.

[0795] Based on this prompt, the AI ​​generates a response saying, "Here are some easy-to-purchase products recommended for you," and communicates it to the user via voice. This allows visually impaired individuals to shop online efficiently and comfortably through a braille display and voice response.

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The user inputs data using a braille display. This input data is provided in braille format. Specifically, when the user inputs "What products do you recommend?" into the braille display, braille data is generated. The braille display then transmits this data to the terminal.

[0799] Input: Braille data entered on a Braille display.

[0800] Output: Braille data sent to the terminal

[0801] Step 2:

[0802] The terminal converts the braille data received from the braille display into text data. The braille data "⠕⠽⠗⠕⠕⠫" is converted into the text data "What products do you recommend?". This conversion is performed by an algorithm that replaces braille characters with their corresponding characters.

[0803] Input: Braille data

[0804] Output: Text data "What products do you recommend?"

[0805] Step 3:

[0806] The terminal sends the converted text data to the server using an HTTP POST request. This request contains the converted text data.

[0807] Input: Text data "What products would you recommend?"

[0808] Output: HTTP POST request sent to the server

[0809] Step 4:

[0810] The server receives text data sent from the terminal and generates response text using a generation AI. Based on the prompt text corresponding to the input text "What products do you recommend?", the generation AI generates the response text "Here are the products we recommend for you."

[0811] Input: Text data sent from the device: "What products do you recommend?"

[0812] Output: Generated response text "Here are some products we recommend for you."

[0813] Step 5:

[0814] The server sends the generated response text back to the terminal. This return is also done via an HTTP request, and the response text is sent to the terminal.

[0815] Input: Generated response text "Here are some products we recommend for you."

[0816] Output: Response text sent back to the terminal

[0817] Step 6:

[0818] The device uses a speech synthesis engine to convert the returned response text into speech data. It performs the process of converting the text data "Here are some products we recommend for you" into speech data.

[0819] Input: Response text "Here are some products we recommend for you."

[0820] Output: Converted audio data

[0821] Step 7:

[0822] The device plays the generated audio data to the user through a speaker or headphones. This allows visually impaired individuals to confirm responses by voice.

[0823] Input: Converted audio data

[0824] Output: Audio data played from speakers or headphones: "Here are some products we recommend for you."

[0825] Step 8:

[0826] The device uses an emotion recognition engine to analyze the user's emotional data. Emotional data such as voice tone, facial expressions, and body movements are acquired in real time, and the user's emotional state is determined based on this. For example, the emotion recognition engine might determine that the user is tired.

[0827] Input: User's real-time sentiment data

[0828] Output: User's emotional state as an analysis result (e.g., tired)

[0829] Step 9:

[0830] The server optimizes the AI's response based on the received emotional data. If the AI ​​determines that the user is tired, it will generate a gentler response, such as, "Here are some easy-to-purchase products that we recommend for you."

[0831] Input: Sentiment data analysis results

[0832] Output: Optimized response text

[0833] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0834] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0835] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0836] [Third Embodiment]

[0837] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0838] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0839] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0840] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0841] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0842] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0843] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0844] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0845] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0846] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0847] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0848] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0849] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display. The following describes in detail each component of the system and its operation.

[0850] System Overview

[0851] The system consists of three main elements: a braille display, a terminal, and a server. The user inputs text using the braille display, the AI ​​processes that text data to generate a response, and finally provides that response to the user in voice.

[0852] Braille display input reception (terminal)

[0853] The user inputs text using a braille display. The terminal receives the input data from the braille display. For example, if the user inputs "hello" into the braille display, the terminal receives that braille data.

[0854] Next, the terminal converts the received braille data into text data. The braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello".

[0855] Sending text data to the server (terminal)

[0856] The terminal sends the converted text data to the server. This is done using network communication. The text data is sent to a specific endpoint on the server side.

[0857] Response generation by AI (server)

[0858] The server receives text data sent from the terminal. Based on the received text data, the generation AI generates a response text.

[0859] For example, when the text data "Hello" is received, the generating AI will produce the response "Hello! How are you?".

[0860] Sending response text back to the terminal (server)

[0861] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[0862] Speech conversion and reading aloud of response text (on the device)

[0863] The terminal receives the response text sent back from the server. The received response text is then converted into audio data. This step utilizes a text-to-speech engine or similar technology.

[0864] For example, when the response text "Hello! How are you?" is received, it is converted into speech. The generated speech data is then read aloud to the user using a speaker or headphones.

[0865] Specific example

[0866] The process from input to response

[0867] The user enters "Hello" into the braille display.

[0868] The device receives the Braille data and converts it into the text data "Hello".

[0869] The device sends this text data to the server.

[0870] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[0871] The server sends the generated response back to the terminal.

[0872] The terminal converts the returned response into audio data and reads it aloud to the user.

[0873] In this way, based on data entered by a visually impaired person using a Braille display, the generating AI generates an appropriate response and provides it as audio, enabling a seamless process from information acquisition to response. The system of the present invention makes it possible for visually impaired people to learn and communicate more efficiently.

[0874] The following describes the processing flow.

[0875] Step 1:

[0876] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[0877] Step 2:

[0878] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[0879] Step 3:

[0880] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[0881] Step 4:

[0882] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[0883] Step 5:

[0884] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[0885] Step 6:

[0886] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[0887] Step 7:

[0888] The server sends the generated response text back to the terminal. This return is also done as an HTTP response, and the data is sent in a format that the terminal can receive.

[0889] Step 8:

[0890] The terminal receives the response text sent back from the server. The terminal analyzes the received data and extracts the response text "Hello! How are you?".

[0891] Step 9:

[0892] The device converts the received response text into audio data. It uses a text-to-speech engine to perform the process of converting the text "Hello! How are you?" into speech.

[0893] Step 10:

[0894] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[0895] In this way, the process is completed in which the generating AI processes the input from the braille display and provides feedback to the user as audio.

[0896] (Example 1)

[0897] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0898] Currently, there are limited methods and systems for visually impaired individuals to efficiently acquire digital information. Therefore, visually impaired individuals face many more difficulties in information acquisition compared to sighted individuals. In particular, information acquisition using generative AI involves a complex process from text data input to output, and an efficient system is needed to enable visually impaired individuals to perform this process smoothly. This invention aims to enable visually impaired individuals to efficiently acquire information from generative AI using a braille display.

[0899] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0900] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, software means for converting braille data, means for inputting text data as a prompt to the generation AI, means for the generation AI model to generate a response based on the prompt, and encryption means for securely sending and receiving text data. This makes it possible for visually impaired people to efficiently perform a series of operations from information acquisition to response through a braille display.

[0901] A "Braille display" is a device that allows visually impaired individuals to input and output information in Braille.

[0902] "Input data" refers to information entered by the user via a braille display and represented in braille format.

[0903] "Text data" refers to information obtained by converting braille data into text format, and is represented as a string of characters.

[0904] A "server" refers to a computer system that receives and transmits data over a network and generates response text using a generative AI.

[0905] "Generative AI" refers to artificial intelligence that uses natural language processing to generate appropriate responses to input text data.

[0906] "Response text" refers to text data generated by a generative AI as a response to the input text.

[0907] "Audio data" refers to information obtained by converting text data into an audio format, and is then played back as sound.

[0908] "Conversion means" refers to software or hardware used to convert received braille data into text data.

[0909] "Transmission means" refers to the function for sending the converted text data to the server.

[0910] "Receiving means" refers to the function that allows a server to receive data sent from a terminal.

[0911] "Playback means" refers to devices such as speakers and headphones that allow users to listen to audio data.

[0912] "Encryption methods" refer to technologies that encrypt data to maintain security when sending and receiving data.

[0913] This invention relates to a system for visually impaired individuals to efficiently obtain information generated by AI using a braille display. The system consists of three main components: a braille display, a terminal, and a server.

[0914] System Configuration

[0915] Braille display

[0916] The user inputs text using a braille display. When the user types "hello" on the braille display, the braille data is sent to the terminal.

[0917] terminal

[0918] The terminal receives braille data transmitted from the braille display. For example, when a user enters "hello," this is sent to the terminal as braille data ("⠓⠑⠇⠇⠕"). This braille data is converted into text data using braille reading software (e.g., Liblouis). For example, the braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello."

[0919] server

[0920] The terminal sends the converted text data to the server. Here, the text data is sent to the server using a network protocol such as HTTPS. The server processes the text data received from the terminal and uses a generative AI (natural language generation model) to generate a response text. For example, if "hello" is sent to the server, the generative AI will generate the response "Hello! How are you?".

[0921] Sending a response

[0922] The server sends the generated response text back to the terminal. The returned response text is then sent back to the terminal via HTTPS or another method. The terminal receives the response text returned from the server and uses a text-to-speech engine (e.g., Google Cloud Text-to-Speech) to convert the response text into speech data.

[0923] Output of audio data

[0924] The converted audio data is read aloud to the user using an audio playback device such as a speaker or headphones. For example, the response "Hello! How are you?" is conveyed to the user verbally.

[0925] Specific example

[0926] The following are specific examples of how visually impaired individuals use the system.

[0927] The user enters "Hello" into the braille display.

[0928] The terminal receives the braille data and uses braille reading software to convert it into text data that says "Hello".

[0929] The terminal sends the converted text data "Hello" to the server.

[0930] The server receives text data, and a generation AI generates the response text "Hello! How are you?".

[0931] The server sends the generated response back to the terminal.

[0932] The device converts the received response text into audio data and reads it aloud to the user through the speaker.

[0933] Example of a prompt

[0934] The following are examples of prompt statements that are input to the generative AI model in this system:

[0935] When the user enters "Hello" into the Braille display

[0936] User: Hello

[0937] AI: Hello! How are you?

[0938] If the user enters "Tell me today's weather" into the braille display

[0939] User: Tell me today's weather.

[0940] AI: Today's weather is sunny. The high temperature will be 25 degrees Celsius and the low temperature will be 18 degrees Celsius.

[0941] This invention enables visually impaired individuals to efficiently acquire information through a Braille display and receive appropriate responses via voice generated by AI. By seamlessly facilitating the process from information acquisition to response, this system significantly contributes to the daily lives, learning, and communication of visually impaired individuals.

[0942] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0943] Step 1:

[0944] The user enters text into the braille display. For example, the input might be the braille text "Hello" (⠓⠑⠇⠇⠕). The input data is then transmitted to the terminal via the braille display.

[0945] Step 2:

[0946] The terminal converts the braille data received from the braille display into text data using braille reading software. Specifically, it uses braille reading software (e.g., Liblouis) to convert the braille data "⠓⠑⠇⠇⠕" into the text data "こんにちは" (hello).

[0947] Input: Braille data (⠓⠑⠇⠇⠕)

[0948] Output: Text data (Hello)

[0949] Step 3:

[0950] The terminal sends the converted text data to the server. The HTTPS protocol is used for communication, and the text data is sent to a specific endpoint on the server.

[0951] Input: Text data (Hello)

[0952] Output: Send to server

[0953] Step 4:

[0954] The server receives text data sent from the terminal. Based on the received data, it inputs prompts into the generating AI model. For example, if it receives the text data "Hello", it inputs the prompt into the generating AI model in the format "User:Hello\nAI:".

[0955] Input: Text data (Hello)

[0956] Output: Prompt input to the generated AI model

[0957] Step 5:

[0958] The server retrieves the response text from the generating AI. The generating AI model generates an appropriate response based on the prompt. For example, in response to the prompt "User: Hello\nAI:", it generates the response "Hello! How are you?".

[0959] Input: Prompt to generated AI

[0960] Output: Response text (Hello! How are you?)

[0961] Step 6:

[0962] The server sends the generated response text back to the terminal. The HTTPS protocol is used again for communication, and the response text is sent to the terminal.

[0963] Input: Response text (Hello! How are you?)

[0964] Output: Send to terminal

[0965] Step 7:

[0966] The terminal receives the response text sent back from the server and converts it into speech data using a text-to-speech engine. Specifically, it uses a text-to-speech engine (e.g., Google Cloud Text-to-Speech) to convert the text data "Hello! How are you?" into speech data.

[0967] Input: Response text (Hello! How are you?)

[0968] Output: Audio data

[0969] Step 8:

[0970] The generated audio data is played back to the user using an audio playback device such as a speaker or headphones. The user can listen to the audio data, "Hello! How are you?", and obtain the information.

[0971] Input: Audio data

[0972] Output: Audio playback

[0973] (Application Example 1)

[0974] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0975] Conventional support systems for the visually impaired have many limitations in efficiently obtaining information and communicating. Furthermore, visually impaired individuals often find it difficult to operate food delivery services or confirm their orders. Therefore, there is a need to develop a system that allows visually impaired individuals to use food delivery services simply and reliably.

[0976] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0977] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generating AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, and means for inputting an order for a food delivery service from a braille display, with the generating AI confirming and responding to the order. This makes it possible for visually impaired people to use food delivery services easily and reliably.

[0978] A "Braille display" is a device that allows visually impaired people to input and read information using Braille.

[0979] "Input data" refers to data in Braille that is transmitted from the Braille display to the terminal.

[0980] "Text data" refers to the received braille data converted into character data.

[0981] A "server" is a computer device that communicates with terminals via a network and generates response text based on text data using generative AI.

[0982] "Generative AI" is artificial intelligence that automatically generates appropriate response text based on received text data.

[0983] "Response text" refers to the response generated by the AI ​​related to the order details.

[0984] A "terminal" is a device that receives braille data from a braille display, converts it into text data, communicates with a server, and converts the returned response text into audio data.

[0985] "Audio data" refers to the conversion of response text into speech.

[0986] A "food delivery service" is a service that allows users to order food online and have it delivered to a specified location.

[0987] This invention relates to a system that allows visually impaired individuals to efficiently use food delivery services using a Braille display. The system's configuration and operation are described in detail below.

[0988] System Overview

[0989] The system consists of three main components: a braille display, a terminal, and a server. Users input their food delivery order details using the braille display, this data is processed by a generating AI, and the final response is provided to the user in voice.

[0990] Terminal configuration and operation

[0991] 1. Braille input reception

[0992] The user enters their food delivery order details into a braille display. The terminal receives the input data from the braille display. For example, if the user enters "I want to order a pizza" into the braille display, that braille data is transmitted to the terminal.

[0993] 2. Text data conversion

[0994] The terminal converts the received braille data into text data. Here, a braille-to-text conversion API is used. The braille data "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" is converted into the text data "I want to order a pizza".

[0995] 3. Sending text data to the server

[0996] The terminal sends the converted text data to the server. The HTTP protocol is used for communication. For example, the text data "I want to order a pizza" is sent to the server as an HTTP POST request.

[0997] Server configuration and operation

[0998] 4. Response generation by generative AI

[0999] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4) generates a response text. For example, a response such as "Hello! Please choose a pizza from the menu" is generated.

[1000] Example of a prompt:

[1001] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[1002] 5. Sending a response text back to the terminal

[1003] The server sends the generated response text back to the terminal. For example, the response text "Hello! Please choose a pizza from the menu" is sent back to the terminal as an HTTP response.

[1004] Terminal reconfiguration and operation

[1005] 6. Audio Data Conversion

[1006] The terminal receives the response text sent back from the server. The received response text is converted into speech data. A text-to-speech engine (e.g., Google Cloud Text-to-Speech) is used in this step. For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech data.

[1007] 7. Audio data playback

[1008] The device reads the generated audio data aloud to the user using a speaker or headphones. For example, the device might say, "Hello! Please choose a pizza from the menu."

[1009] Specific example

[1010] The user enters "I want to order a pizza" into the braille display.

[1011] The terminal receives the Braille data and converts it into text data that says, "I want to order a pizza."

[1012] The device sends this text data to the server.

[1013] The server receives text data and a generating AI produces the response, "Hello! Please choose a pizza from the menu."

[1014] The server sends the generated response back to the terminal.

[1015] The terminal converts the returned response into audio data and reads it aloud to the user.

[1016] In this way, visually impaired individuals can place food delivery orders using a Braille display, and the AI ​​generates appropriate responses in voice, allowing for seamless order confirmation and use of the food delivery service.

[1017] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1018] Step 1:

[1019] The user enters their food delivery order details on a braille display. For example, the braille data entered here might be "I want to order a pizza." This data is then transmitted directly from the braille display to the terminal. Input: braille data. Output: braille data.

[1020] Step 2:

[1021] The terminal converts the braille data received from the braille display into text data. Specifically, it uses a braille-to-text conversion API to convert the braille "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" into the text "I want to order a pizza". Input: braille data. Output: text data.

[1022] Step 3:

[1023] The terminal sends the converted text data to the server. The HTTP protocol is used for this communication. The text data "I want to order a pizza" is sent to the specified endpoint as an HTTP POST request. Input: Text data. Output: HTTP request to the server.

[1024] Step 4:

[1025] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4) generates a response text. This response may include something like, "Hello! Please choose a pizza from the menu." The generative AI generates the response using the following prompt:

[1026] Example of a prompt:

[1027] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[1028] Input: Text data. Output: Response text.

[1029] Step 5:

[1030] The server sends a response text back to the terminal. The generated response text is sent to the terminal as an HTTP response. Input: Response text. Output: HTTP response from the server.

[1031] Step 6:

[1032] The device receives the response text sent back from the server. The received response text is converted into speech data using a text-to-speech engine (e.g., Google Cloud Text-to-Speech). For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech. Input: Response text. Output: Speech data.

[1033] Step 7:

[1034] The device plays the generated audio data and provides a voice response to the user. Specifically, the voice is read aloud to the user through the device's speaker or headphones. Input: Audio data. Output: Voice response.

[1035] The above describes the processing flow of the system program that implements the application example.

[1036] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1037] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display, and further to recognize the user's emotions and optimize the response. The following describes in detail each component of the system and its operation.

[1038] System Overview

[1039] The system consists of four main elements: a braille display, a terminal, a server, and an emotion engine. The user inputs text using the braille display, and the generating AI processes this text data to generate a response, which is then provided to the user in voice. In addition, the emotion engine recognizes the user's emotions, and the generating AI generates a response based on those emotions.

[1040] Braille display input reception (terminal)

[1041] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[1042] Next, the terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[1043] Text data conversion and server transmission (terminal)

[1044] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[1045] Next, the terminal sends the converted text data to the server. This is done using an HTTP POST request, and the text data is sent to the specified server endpoint.

[1046] Text data analysis and response generation (server)

[1047] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[1048] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[1049] Sending response text back to the terminal (server)

[1050] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[1051] Emotion engine operation (device)

[1052] The device uses an emotion engine to recognize the user's emotions. The emotion engine acquires emotion data from the user's voice, facial expressions, body movements, etc. This emotion data is analyzed in real time when the user makes input or receives a response.

[1053] Optimization of response text (server)

[1054] The server optimizes the response generated by the AI ​​based on the received emotional data. For example, if the emotional engine recognizes that the user is tired, the AI ​​will generate a gentle response such as, "Hi! What's up today?"

[1055] Speech conversion and reading aloud of response text (on the device)

[1056] The terminal receives the response text sent back from the server. The received text data is converted into audio data. A text-to-speech engine is used to perform the process of converting the text "Hello! How are you?" into speech.

[1057] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[1058] Specific example

[1059] The process from input to response

[1060] The user enters "Hello" into the braille display.

[1061] The device receives the Braille data and converts it into the text data "Hello".

[1062] The device sends this text data to the server.

[1063] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[1064] The server sends the generated response back to the terminal.

[1065] The terminal converts the returned response into audio data and reads it aloud to the user.

[1066] Furthermore, the emotion engine recognizes the user's emotions, and if it determines that the user is tired, the generated response will change to something like, "Hello, you look tired today. How can I help you?" This allows for dialogue that is more tailored to the user's state.

[1067] In this way, the generation AI processes the input from the braille display and completes a series of processes that provide the optimal response in voice, tailored to the user's emotions.

[1068] The following describes the processing flow.

[1069] Step 1:

[1070] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[1071] Step 2:

[1072] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[1073] Step 3:

[1074] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[1075] Step 4:

[1076] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[1077] Step 5:

[1078] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[1079] Step 6:

[1080] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[1081] Step 7:

[1082] The server invokes the emotion engine and requests data from the terminal necessary to recognize the user's emotions. This includes requesting a detailed analysis of emotional information such as cheek texture, tone of voice, and facial expressions.

[1083] Step 8:

[1084] The device activates its camera and microphone to collect user emotional information, gathering data in real time. For example, it might detect if the user's voice tone is low and their facial expression is tired.

[1085] Step 9:

[1086] The device collects emotional data and sends it to the server. The emotional information is encoded as audio or video data and sent to the server.

[1087] Step 10:

[1088] The server analyzes the received emotional data using an emotion engine to determine the user's emotional state. For example, it might determine that the user is tired.

[1089] Step 11:

[1090] The server optimizes the AI's response text based on the analysis results from the emotion engine. For example, if the user is tired, it might generate a response like, "Hello! You must be tired. How was your day?"

[1091] Step 12:

[1092] The server sends an optimized response text back to the terminal. This response is also sent as an HTTP response, and the data is sent in a format that the terminal can receive.

[1093] Step 13:

[1094] The terminal receives the response text sent back from the server. The terminal analyzes the received data and extracts the response text "Hello! Thank you for your hard work. What happened today?".

[1095] Step 14:

[1096] The terminal converts the received response text into audio data. Using a text-to-speech engine, it performs the process of converting the text "Hello! Good work today. What happened today?" into speech.

[1097] Step 15:

[1098] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[1099] In this way, the generation AI processes the input from the braille display and completes a series of processes that provide the optimal response in voice, tailored to the user's emotions.

[1100] (Example 2)

[1101] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1102] Braille displays are widely used as a means for visually impaired people to efficiently acquire information. However, the simple text input and output of Braille displays alone is insufficient to complement visual information. Furthermore, obtaining responses using generative AI models has limitations in providing optimal communication tailored to the user's emotional state. Therefore, a system is needed that recognizes the user's emotions and optimizes responses based on those emotions.

[1103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for generating response text based on the received text data using an AI model generated by the server, means for acquiring user emotion data using an emotion engine that recognizes the user's emotions, means for optimizing the response text generated based on the acquired emotion data, means for returning the optimized response text to the terminal, means for converting the returned response text into audio data, and means for playing the audio data. This makes it possible for visually impaired people using a braille display to efficiently acquire AI information and receive optimal responses in real time that correspond to their emotions.

[1104] A "Braille display" is a device that allows visually impaired people to input and read Braille.

[1105] "Input data" refers to information entered by the user using a braille display.

[1106] A "terminal" is a device that is connected to a braille display and receives and processes input data.

[1107] "Text data" refers to character information obtained by converting Braille data.

[1108] A "server" is a computer system that receives data transmitted from terminals via a network and performs analysis and response generation.

[1109] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate appropriate response text based on received text data.

[1110] An "emotion engine" is a system that acquires emotional data from the user's voice and facial expressions and analyzes that data.

[1111] "Emotional data" refers to data that indicates the user's emotional state, acquired by the emotion engine.

[1112] "Response text" refers to the text data of the response to user input, generated by a generative AI model.

[1113] "Optimization" refers to the process of adjusting the content and tone of response text based on acquired sentiment data.

[1114] "Audio data" refers to data obtained by converting text data into speech using a speech synthesis engine.

[1115] "Playback means" refers to devices used to allow users to listen to the generated audio data, specifically speakers and headphones.

[1116] This invention provides a system that enables visually impaired individuals to efficiently obtain information from AI-generated using a Braille display, while recognizing the user's emotions and optimizing the response accordingly. The system consists of four main components: a Braille display, a terminal, a server, and an emotion engine.

[1117] Basic System Configuration

[1118] Braille display

[1119] Users input text using a braille display. For example, typing "hello" is done by pressing a specific button or key on the braille display. The braille display connects to the terminal via Bluetooth or USB and transmits the input data to the terminal in real time.

[1120] terminal

[1121] The terminal is responsible for receiving braille data from a braille display, converting it into text data, and sending that text data to the server. Using a conversion algorithm, it converts the braille data "⠓⠑⠇⠇⠕" into the text data "hello". It also uses a text-to-speech engine to convert the response text sent back from the server into audio data and play it back.

[1122] server

[1123] The server receives text data sent from the terminal, analyzes the received data, and generates response text using a generative AI model. Furthermore, it optimizes the response based on sentiment data from the sentiment engine and sends the optimized response text back to the terminal. As an example of response generation, the response "Hello! How are you?" is generated in response to the text "Hello".

[1124] Emotional Engine

[1125] The emotion engine built into the device analyzes the user's voice tone, facial expressions, and body movements to recognize their emotions. Emotional data is acquired in real time, sent to the server, and used to generate responses. For example, if the emotion engine detects that the user is tired, the server will generate a gentle response such as, "You look tired today. What's the matter?"

[1126] Specific example

[1127] The user inputs "hello" using a braille display. The data transmitted from the braille display is converted to the text "hello" by the terminal and sent to the server. The server generates a response, "Hello! How are you?" and then the emotion engine recognizes the user's emotions. If it determines, for example, that the user is tired, the response changes to "Hello, you look tired today. What's the matter?" Finally, this response is converted into audio data and transmitted to the user through speakers or headphones.

[1128] Example of a prompt

[1129] The user typed "Hello" using a braille display. The generated response was "Hello! How are you?". If the system determined the user was tired, the response changed to "Hello, you look tired today. What's the matter?".

[1130] In this way, the AI ​​processes input from the braille display and provides an optimal response in voice that reflects the user's emotions, completing a series of processes. This makes it possible for visually impaired people to acquire information and communicate more comfortably.

[1131] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1132] Step 1:

[1133] The user inputs "Hello" using a braille display. The braille display transmits the input data to the terminal in real time, and the terminal receives this data. Specifically, by performing certain button or key operations on the braille display, the braille data "⠓⠑⠇⠇⠕" is generated. This braille data is then transmitted to the terminal.

[1134] Input: User's Braille input data

[1135] Output: Data transmission from braille display to terminal

[1136] Step 2:

[1137] The terminal receives braille data "⠓⠑⠇⠇⠕" and converts it to text data "hello". Specifically, it applies a braille-to-corresponding text conversion algorithm to convert the braille data to text data. This converted text data is then sent to the server endpoint specified in the HTTP POST request.

[1138] Input: Received braille data "⠓⠑⠇⠇⠕"

[1139] Output: Converted text data "hello", and transmission to the server.

[1140] Step 3:

[1141] The server receives the text data "hello" sent from the terminal. The server analyzes the received data and calls a generative AI model to generate an appropriate response, "Hello! How are you?". Specifically, the process involves extracting text data from the HTTP request and inputting it into the generative AI model to generate the response text.

[1142] Input: Text data "hello" sent from the terminal.

[1143] Output: Generated response text "Hello! How are you?"

[1144] Step 4:

[1145] The server sends the generated response text back to the terminal via the network. Specifically, it structures the response text in JSON format or similar and sends it to the terminal as an HTTP response.

[1146] Input: Generated response text "Hello! How are you?"

[1147] Output: Send response text to the terminal as an HTTP response.

[1148] Step 5:

[1149] The device receives a response text sent back from the server. The device uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's tone of voice, facial expressions, body movements, etc., to obtain emotional data.

[1150] Input: Response text from the server, and user emotion input data (voice, facial expressions, etc.)

[1151] Output: Acquired sentiment data

[1152] Step 6:

[1153] The server receives emotion data sent from the terminal and optimizes the response text based on it. If the server detects that the user is tired, it reflects the parameters in the generating AI model and changes the response to a gentler tone, such as, "Hello, you look tired today. How can I help you?"

[1154] Input: Acquired sentiment data

[1155] Output: Optimized response text "Hello, you look tired today. How can I help you?"

[1156] Step 7:

[1157] The device converts the optimized response text into audio data. Specifically, it uses a text-to-speech engine to convert the response text "Hello! How are you?" into audio data. The generated audio data is then played back to the user through speakers or headphones.

[1158] Input: Optimized response text

[1159] Output: Generated audio data, playback of audio data

[1160] Through the steps described above, user input from the braille display is processed by a generative AI, and a response optimized for the user's emotions is provided as voice.

[1161] (Application Example 2)

[1162] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1163] When visually impaired individuals shop online, they face challenges such as inefficiently obtaining text information or receiving responses that reflect their emotions. Furthermore, there is a growing need for a more comfortable shopping experience by providing responses optimized based on the user's emotional state.

[1164] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1165] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for returning the generated response text to the terminal, means for converting the returned response text into audio data, means for playing the audio data, and means for analyzing the user's emotional data using an emotion recognition engine and optimizing the response by the generation AI based on the received emotional data. This enables visually impaired people to efficiently shop online using a braille display and to provide an optimal response based on the user's emotional state.

[1166] A "braille display" is a device that allows visually impaired people to input and output information using braille.

[1167] "Means for receiving input data" refers to a function or device for acquiring braille input data from a braille display.

[1168] "Means for converting to text data" refers to a process or device for converting Braille data into corresponding character data.

[1169] "Means of sending to the server" refers to a function or device for sending the converted text data to a server via a network.

[1170] "Generative AI" is an artificial intelligence technology that generates appropriate responses based on received text data.

[1171] "Means for generating response text" refers to a function or device for creating response text for input text data using a generation AI.

[1172] "Means of returning to the terminal" refers to a function or device for sending the generated response text back to the terminal via the network.

[1173] "Means for converting to audio data" refers to a process or device for converting the returned response text into an audio format.

[1174] "Means for playing audio data" refers to a function or device that allows the user to hear the converted audio data through a speaker or similar device.

[1175] An "emotion recognition engine" is a technology or device that analyzes and recognizes a user's emotional state from their voice, biosignals, etc.

[1176] "Means for analyzing emotional data" refers to a function or device that uses an emotional recognition engine to analyze a user's emotional state and acquire specific emotional data.

[1177] "Means for optimizing responses by generative AI" refers to a function or device for optimizing the responses generated by generative AI to match the user's emotional state, based on analyzed emotional data.

[1178] This invention relates to a system that enables visually impaired individuals to efficiently conduct online shopping using a Braille display, and further provides optimal responses tailored to the user's emotions.

[1179] System Configuration

[1180] The system consists of the following elements:

[1181] Braille display

[1182] Device (smartphone)

[1183] server

[1184] Emotion recognition engine

[1185] Generation AI

[1186] Speech synthesis engine

[1187] Operation overview

[1188] The user first inputs text using a braille display. For example, if the user types "What products do you recommend?" on the braille display, this braille data is sent to the terminal in real time.

[1189] The terminal converts the received braille data into text data. This conversion uses a conversion algorithm that converts the braille data "⠕⠽⠗⠕⠕⠫" into the text data "What products do you recommend?".

[1190] The converted text data is sent to the server using an HTTP POST request. The server receives this text data via the specified endpoint.

[1191] The server analyzes the received text data and calls a generation AI to generate a response text. For example, in response to the text data "What products do you recommend?", the generation AI generates the response "These are the products we recommend for you."

[1192] Next, the server sends the generated response text back to the terminal via the network. The returned response text is received by the terminal.

[1193] The device uses a speech synthesis engine to convert this response text into speech data. In this process, the text "Here are some products we recommend for you" is converted into speech.

[1194] Finally, the generated audio data is played to the user through speakers or headphones.

[1195] Furthermore, the system uses an emotion recognition engine to analyze the user's emotions in real time. The emotion recognition engine acquires emotional data from the user's voice, facial expressions, and body movements, and analyzes it when the user makes input or when a response is received. This emotional data is sent to the server, and the generating AI optimizes the response. For example, if the emotion recognition engine determines that the user is tired, the generated response will also change to a gentler tone, such as "Here are some easy-to-purchase products that we recommend for you."

[1196] Specific example

[1197] For example, if a user types "What products do you recommend?" on a braille display, and the emotion recognition engine detects the user's fatigue level, an example of the prompt message sent to the server would be as follows:

[1198] What are today's recommended products? The user seems a little tired.

[1199] Based on this prompt, the AI ​​generates a response saying, "Here are some easy-to-purchase products recommended for you," and communicates it to the user via voice. This allows visually impaired individuals to shop online efficiently and comfortably through a braille display and voice response.

[1200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1201] Step 1:

[1202] The user inputs data using a braille display. This input data is provided in braille format. Specifically, when the user inputs "What products do you recommend?" into the braille display, braille data is generated. The braille display then transmits this data to the terminal.

[1203] Input: Braille data entered on a Braille display.

[1204] Output: Braille data sent to the terminal

[1205] Step 2:

[1206] The terminal converts the braille data received from the braille display into text data. The braille data "⠕⠽⠗⠕⠕⠫" is converted into the text data "What products do you recommend?". This conversion is performed by an algorithm that replaces braille characters with their corresponding characters.

[1207] Input: Braille data

[1208] Output: Text data "What products do you recommend?"

[1209] Step 3:

[1210] The terminal sends the converted text data to the server using an HTTP POST request. This request contains the converted text data.

[1211] Input: Text data "What products would you recommend?"

[1212] Output: HTTP POST request sent to the server

[1213] Step 4:

[1214] The server receives text data sent from the terminal and generates response text using a generation AI. Based on the prompt text corresponding to the input text "What products do you recommend?", the generation AI generates the response text "Here are the products we recommend for you."

[1215] Input: Text data sent from the device: "What products do you recommend?"

[1216] Output: Generated response text "Here are some products we recommend for you."

[1217] Step 5:

[1218] The server sends the generated response text back to the terminal. This return is also done via an HTTP request, and the response text is sent to the terminal.

[1219] Input: Generated response text "Here are some products we recommend for you."

[1220] Output: Response text sent back to the terminal

[1221] Step 6:

[1222] The device uses a speech synthesis engine to convert the returned response text into speech data. It performs the process of converting the text data "Here are some products we recommend for you" into speech data.

[1223] Input: Response text "Here are some products we recommend for you."

[1224] Output: Converted audio data

[1225] Step 7:

[1226] The device plays the generated audio data to the user through a speaker or headphones. This allows visually impaired individuals to confirm responses by voice.

[1227] Input: Converted audio data

[1228] Output: Audio data played from speakers or headphones: "Here are some products we recommend for you."

[1229] Step 8:

[1230] The device uses an emotion recognition engine to analyze the user's emotional data. Emotional data such as voice tone, facial expressions, and body movements are acquired in real time, and the user's emotional state is determined based on this. For example, the emotion recognition engine might determine that the user is tired.

[1231] Input: User's real-time sentiment data

[1232] Output: User's emotional state as an analysis result (e.g., tired)

[1233] Step 9:

[1234] The server optimizes the AI's response based on the received emotional data. If the AI ​​determines that the user is tired, it will generate a gentler response, such as, "Here are some easy-to-purchase products that we recommend for you."

[1235] Input: Sentiment data analysis results

[1236] Output: Optimized response text

[1237] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1238] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1239] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1240] [Fourth Embodiment]

[1241] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1242] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1243] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1244] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1245] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1246] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1247] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1248] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1249] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1250] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1251] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1252] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1253] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1254] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display. The following describes in detail each component of the system and its operation.

[1255] System Overview

[1256] The system consists of three main elements: a braille display, a terminal, and a server. The user inputs text using the braille display, the AI ​​processes that text data to generate a response, and finally provides that response to the user in voice.

[1257] Braille display input reception (terminal)

[1258] The user inputs text using a braille display. The terminal receives the input data from the braille display. For example, if the user inputs "hello" into the braille display, the terminal receives that braille data.

[1259] Next, the terminal converts the received braille data into text data. The braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello".

[1260] Sending text data to the server (terminal)

[1261] The terminal sends the converted text data to the server. This is done using network communication. The text data is sent to a specific endpoint on the server side.

[1262] Response generation by AI (server)

[1263] The server receives text data sent from the terminal. Based on the received text data, the generation AI generates a response text.

[1264] For example, when the text data "Hello" is received, the generating AI will produce the response "Hello! How are you?".

[1265] Sending response text back to the terminal (server)

[1266] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[1267] Speech conversion and reading aloud of response text (on the device)

[1268] The terminal receives the response text sent back from the server. The received response text is then converted into audio data. This step utilizes a text-to-speech engine or similar technology.

[1269] For example, when the response text "Hello! How are you?" is received, it is converted into speech. The generated speech data is then read aloud to the user using a speaker or headphones.

[1270] Specific example

[1271] The process from input to response

[1272] The user enters "Hello" into the braille display.

[1273] The device receives the Braille data and converts it into the text data "Hello".

[1274] The device sends this text data to the server.

[1275] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[1276] The server sends the generated response back to the terminal.

[1277] The terminal converts the returned response into audio data and reads it aloud to the user.

[1278] In this way, based on data entered by a visually impaired person using a Braille display, the generating AI generates an appropriate response and provides it as audio, enabling a seamless process from information acquisition to response. The system of the present invention makes it possible for visually impaired people to learn and communicate more efficiently.

[1279] The following describes the processing flow.

[1280] Step 1:

[1281] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[1282] Step 2:

[1283] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[1284] Step 3:

[1285] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[1286] Step 4:

[1287] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[1288] Step 5:

[1289] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[1290] Step 6:

[1291] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[1292] Step 7:

[1293] The server sends the generated response text back to the terminal. This return is also done as an HTTP response, and the data is sent in a format that the terminal can receive.

[1294] Step 8:

[1295] The terminal receives the response text sent back from the server. The terminal analyzes the received data and extracts the response text "Hello! How are you?".

[1296] Step 9:

[1297] The device converts the received response text into audio data. It uses a text-to-speech engine to perform the process of converting the text "Hello! How are you?" into speech.

[1298] Step 10:

[1299] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[1300] In this way, the process is completed in which the generating AI processes the input from the braille display and provides feedback to the user as audio.

[1301] (Example 1)

[1302] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1303] Currently, there are limited methods and systems for visually impaired individuals to efficiently acquire digital information. Therefore, visually impaired individuals face many more difficulties in information acquisition compared to sighted individuals. In particular, information acquisition using generative AI involves a complex process from text data input to output, and an efficient system is needed to enable visually impaired individuals to perform this process smoothly. This invention aims to enable visually impaired individuals to efficiently acquire information from generative AI using a braille display.

[1304] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1305] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, software means for converting braille data, means for inputting text data as a prompt to the generation AI, means for the generation AI model to generate a response based on the prompt, and encryption means for securely sending and receiving text data. This makes it possible for visually impaired people to efficiently perform a series of operations from information acquisition to response through a braille display.

[1306] A "Braille display" is a device that allows visually impaired individuals to input and output information in Braille.

[1307] "Input data" refers to information entered by the user via a braille display and represented in braille format.

[1308] "Text data" refers to information obtained by converting braille data into text format, and is represented as a string of characters.

[1309] A "server" refers to a computer system that receives and transmits data over a network and generates response text using a generative AI.

[1310] "Generative AI" refers to artificial intelligence that uses natural language processing to generate appropriate responses to input text data.

[1311] "Response text" refers to text data generated by a generative AI as a response to the input text.

[1312] "Audio data" refers to information obtained by converting text data into an audio format, and is then played back as sound.

[1313] "Conversion means" refers to software or hardware used to convert received braille data into text data.

[1314] "Transmission means" refers to the function for sending the converted text data to the server.

[1315] "Receiving means" refers to the function that allows a server to receive data sent from a terminal.

[1316] "Playback means" refers to devices such as speakers and headphones that allow users to listen to audio data.

[1317] "Encryption methods" refer to technologies that encrypt data to maintain security when sending and receiving data.

[1318] This invention relates to a system for visually impaired individuals to efficiently obtain information generated by AI using a braille display. The system consists of three main components: a braille display, a terminal, and a server.

[1319] System Configuration

[1320] Braille display

[1321] The user inputs text using a braille display. When the user types "hello" on the braille display, the braille data is sent to the terminal.

[1322] terminal

[1323] The terminal receives braille data transmitted from the braille display. For example, when a user enters "hello," this is sent to the terminal as braille data ("⠓⠑⠇⠇⠕"). This braille data is converted into text data using braille reading software (e.g., Liblouis). For example, the braille data "⠓⠑⠇⠇⠕" is converted into the text data "hello."

[1324] server

[1325] The terminal sends the converted text data to the server. Here, the text data is sent to the server using a network protocol such as HTTPS. The server processes the text data received from the terminal and uses a generative AI (natural language generation model) to generate a response text. For example, if "hello" is sent to the server, the generative AI will generate the response "Hello! How are you?".

[1326] Sending a response

[1327] The server sends the generated response text back to the terminal. The returned response text is then sent back to the terminal via HTTPS or another method. The terminal receives the response text returned from the server and uses a text-to-speech engine (e.g., Google Cloud Text-to-Speech) to convert the response text into speech data.

[1328] Output of audio data

[1329] The converted audio data is read aloud to the user using an audio playback device such as a speaker or headphones. For example, the response "Hello! How are you?" is conveyed to the user verbally.

[1330] Specific example

[1331] The following are specific examples of how visually impaired individuals use the system.

[1332] The user enters "Hello" into the braille display.

[1333] The terminal receives the braille data and uses braille reading software to convert it into text data that says "Hello".

[1334] The terminal sends the converted text data "Hello" to the server.

[1335] The server receives text data, and a generation AI generates the response text "Hello! How are you?".

[1336] The server sends the generated response back to the terminal.

[1337] The device converts the received response text into audio data and reads it aloud to the user through the speaker.

[1338] Example of a prompt

[1339] The following are examples of prompt statements that are input to the generative AI model in this system:

[1340] When the user enters "Hello" into the Braille display

[1341] User: Hello

[1342] AI: Hello! How are you?

[1343] If the user enters "Tell me today's weather" into the braille display

[1344] User: Tell me today's weather.

[1345] AI: Today's weather is sunny. The high temperature will be 25 degrees Celsius and the low temperature will be 18 degrees Celsius.

[1346] This invention enables visually impaired individuals to efficiently acquire information through a Braille display and receive appropriate responses via voice generated by AI. By seamlessly facilitating the process from information acquisition to response, this system significantly contributes to the daily lives, learning, and communication of visually impaired individuals.

[1347] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1348] Step 1:

[1349] The user enters text into the braille display. For example, the input might be the braille text "Hello" (⠓⠑⠇⠇⠕). The input data is then transmitted to the terminal via the braille display.

[1350] Step 2:

[1351] The terminal converts the braille data received from the braille display into text data using braille reading software. Specifically, it uses braille reading software (e.g., Liblouis) to convert the braille data "⠓⠑⠇⠇⠕" into the text data "こんにちは" (hello).

[1352] Input: Braille data (⠓⠑⠇⠇⠕)

[1353] Output: Text data (Hello)

[1354] Step 3:

[1355] The terminal sends the converted text data to the server. The HTTPS protocol is used for communication, and the text data is sent to a specific endpoint on the server.

[1356] Input: Text data (Hello)

[1357] Output: Send to server

[1358] Step 4:

[1359] The server receives text data sent from the terminal. Based on the received data, it inputs prompts into the generating AI model. For example, if it receives the text data "Hello", it inputs the prompt into the generating AI model in the format "User:Hello\nAI:".

[1360] Input: Text data (Hello)

[1361] Output: Prompt input to the generated AI model

[1362] Step 5:

[1363] The server retrieves the response text from the generating AI. The generating AI model generates an appropriate response based on the prompt. For example, in response to the prompt "User: Hello\nAI:", it generates the response "Hello! How are you?".

[1364] Input: Prompt to generated AI

[1365] Output: Response text (Hello! How are you?)

[1366] Step 6:

[1367] The server sends the generated response text back to the terminal. The HTTPS protocol is used again for communication, and the response text is sent to the terminal.

[1368] Input: Response text (Hello! How are you?)

[1369] Output: Send to terminal

[1370] Step 7:

[1371] The terminal receives the response text sent back from the server and converts it into speech data using a text-to-speech engine. Specifically, it uses a text-to-speech engine (e.g., Google Cloud Text-to-Speech) to convert the text data "Hello! How are you?" into speech data.

[1372] Input: Response text (Hello! How are you?)

[1373] Output: Audio data

[1374] Step 8:

[1375] The generated audio data is played back to the user using an audio playback device such as a speaker or headphones. The user can listen to the audio data, "Hello! How are you?", and obtain the information.

[1376] Input: Audio data

[1377] Output: Audio playback

[1378] (Application Example 1)

[1379] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1380] Conventional support systems for the visually impaired have many limitations in efficiently obtaining information and communicating. Furthermore, visually impaired individuals often find it difficult to operate food delivery services or confirm their orders. Therefore, there is a need to develop a system that allows visually impaired individuals to use food delivery services simply and reliably.

[1381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1382] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generating AI, means for sending the generated response text back to the terminal, means for converting the sent response text into audio data, means for playing the audio data, and means for inputting an order for a food delivery service from a braille display, with the generating AI confirming and responding to the order. This makes it possible for visually impaired people to use food delivery services easily and reliably.

[1383] A "Braille display" is a device that allows visually impaired people to input and read information using Braille.

[1384] "Input data" refers to data in Braille that is transmitted from the Braille display to the terminal.

[1385] "Text data" refers to the received braille data converted into character data.

[1386] A "server" is a computer device that communicates with terminals via a network and generates response text based on text data using generative AI.

[1387] "Generative AI" is artificial intelligence that automatically generates appropriate response text based on received text data.

[1388] "Response text" refers to the response generated by the AI ​​related to the order details.

[1389] A "terminal" is a device that receives braille data from a braille display, converts it into text data, communicates with a server, and converts the returned response text into audio data.

[1390] "Audio data" refers to the conversion of response text into speech.

[1391] A "food delivery service" is a service that allows users to order food online and have it delivered to a specified location.

[1392] This invention relates to a system that allows visually impaired individuals to efficiently use food delivery services using a Braille display. The system's configuration and operation are described in detail below.

[1393] System Overview

[1394] The system consists of three main components: a braille display, a terminal, and a server. Users input their food delivery order details using the braille display, this data is processed by a generating AI, and the final response is provided to the user in voice.

[1395] Terminal configuration and operation

[1396] 1. Braille input reception

[1397] The user enters their food delivery order details into a braille display. The terminal receives the input data from the braille display. For example, if the user enters "I want to order a pizza" into the braille display, that braille data is transmitted to the terminal.

[1398] 2. Text data conversion

[1399] The terminal converts the received braille data into text data. Here, a braille-to-text conversion API is used. The braille data "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" is converted into the text data "I want to order a pizza".

[1400] 3. Sending text data to the server

[1401] The terminal sends the converted text data to the server. The HTTP protocol is used for communication. For example, the text data "I want to order a pizza" is sent to the server as an HTTP POST request.

[1402] Server configuration and operation

[1403] 4. Response generation by generative AI

[1404] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4) generates a response text. For example, a response such as "Hello! Please choose a pizza from the menu" is generated.

[1405] Example of a prompt:

[1406] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[1407] 5. Sending a response text back to the terminal

[1408] The server sends the generated response text back to the terminal. For example, the response text "Hello! Please choose a pizza from the menu" is sent back to the terminal as an HTTP response.

[1409] Terminal reconfiguration and operation

[1410] 6. Audio Data Conversion

[1411] The terminal receives the response text sent back from the server. The received response text is converted into speech data. A text-to-speech engine (e.g., Google Cloud Text-to-Speech) is used in this step. For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech data.

[1412] 7. Audio data playback

[1413] The device reads the generated audio data aloud to the user using a speaker or headphones. For example, the device might say, "Hello! Please choose a pizza from the menu."

[1414] Specific example

[1415] The user enters "I want to order a pizza" into the braille display.

[1416] The terminal receives the Braille data and converts it into text data that says, "I want to order a pizza."

[1417] The device sends this text data to the server.

[1418] The server receives text data and a generating AI produces the response, "Hello! Please choose a pizza from the menu."

[1419] The server sends the generated response back to the terminal.

[1420] The terminal converts the returned response into audio data and reads it aloud to the user.

[1421] In this way, visually impaired individuals can place food delivery orders using a Braille display, and the AI ​​generates appropriate responses in voice, allowing for seamless order confirmation and use of the food delivery service.

[1422] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1423] Step 1:

[1424] The user enters their food delivery order details on a braille display. For example, the braille data entered here might be "I want to order a pizza." This data is then transmitted directly from the braille display to the terminal. Input: braille data. Output: braille data.

[1425] Step 2:

[1426] The terminal converts the braille data received from the braille display into text data. Specifically, it uses a braille-to-text conversion API to convert the braille "⠏⠊⠵⠁⠕⠳⠒⠆⠠⠞⠝⠭⠥⠔" into the text "I want to order a pizza". Input: braille data. Output: text data.

[1427] Step 3:

[1428] The terminal sends the converted text data to the server. The HTTP protocol is used for this communication. The text data "I want to order a pizza" is sent to the specified endpoint as an HTTP POST request. Input: Text data. Output: HTTP request to the server.

[1429] Step 4:

[1430] The server receives text data sent from the terminal. Based on the received text data, a generative AI (e.g., GPT-4) generates a response text. This response may include something like, "Hello! Please choose a pizza from the menu." The generative AI generates the response using the following prompt:

[1431] Example of a prompt:

[1432] Order Inquiry: The user says, "I want to order a pizza." Generate a response to allow the user to select a pizza from the menu.

[1433] Input: Text data. Output: Response text.

[1434] Step 5:

[1435] The server sends a response text back to the terminal. The generated response text is sent to the terminal as an HTTP response. Input: Response text. Output: HTTP response from the server.

[1436] Step 6:

[1437] The device receives the response text sent back from the server. The received response text is converted into speech data using a text-to-speech engine (e.g., Google Cloud Text-to-Speech). For example, the response text "Hello! Please choose a pizza from the menu" is converted into speech. Input: Response text. Output: Speech data.

[1438] Step 7:

[1439] The device plays the generated audio data and provides a voice response to the user. Specifically, the voice is read aloud to the user through the device's speaker or headphones. Input: Audio data. Output: Voice response.

[1440] The above describes the processing flow of the system program that implements the application example.

[1441] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1442] This invention relates to a system for visually impaired individuals to efficiently acquire information generated by AI using a Braille display, and further to recognize the user's emotions and optimize the response. The following describes in detail each component of the system and its operation.

[1443] System Overview

[1444] The system consists of four main elements: a braille display, a terminal, a server, and an emotion engine. The user inputs text using the braille display, and the generating AI processes this text data to generate a response, which is then provided to the user in voice. In addition, the emotion engine recognizes the user's emotions, and the generating AI generates a response based on those emotions.

[1445] Braille display input reception (terminal)

[1446] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[1447] Next, the terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[1448] Text data conversion and server transmission (terminal)

[1449] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[1450] Next, the terminal sends the converted text data to the server. This is done using an HTTP POST request, and the text data is sent to the specified server endpoint.

[1451] Text data analysis and response generation (server)

[1452] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[1453] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[1454] Sending response text back to the terminal (server)

[1455] The server sends the response text generated by the AI ​​back to the terminal. The response text is transmitted to the terminal via the network.

[1456] Emotion engine operation (device)

[1457] The device uses an emotion engine to recognize the user's emotions. The emotion engine acquires emotion data from the user's voice, facial expressions, body movements, etc. This emotion data is analyzed in real time when the user makes input or receives a response.

[1458] Optimization of response text (server)

[1459] The server optimizes the response generated by the AI ​​based on the received emotional data. For example, if the emotional engine recognizes that the user is tired, the AI ​​will generate a gentle response such as, "Hi! What's up today?"

[1460] Speech conversion and reading aloud of response text (on the device)

[1461] The terminal receives the response text sent back from the server. The received text data is converted into audio data. A text-to-speech engine is used to perform the process of converting the text "Hello! How are you?" into speech.

[1462] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[1463] Specific example

[1464] The process from input to response

[1465] The user enters "Hello" into the braille display.

[1466] The device receives the Braille data and converts it into the text data "Hello".

[1467] The device sends this text data to the server.

[1468] The server receives text data, and a generation AI generates the response, "Hello! How are you?"

[1469] The server sends the generated response back to the terminal.

[1470] The terminal converts the returned response into audio data and reads it aloud to the user.

[1471] Furthermore, the emotion engine recognizes the user's emotions, and if it determines that the user is tired, the generated response will change to something like, "Hello, you look tired today. How can I help you?" This allows for dialogue that is more tailored to the user's state.

[1472] In this way, the generation AI processes the input from the braille display and completes a series of processes that provide the optimal response in voice, tailored to the user's emotions.

[1473] The following describes the processing flow.

[1474] Step 1:

[1475] The user inputs text using a braille display. For example, they might type "Hello." This braille input is performed using specific buttons or keys on the braille display.

[1476] Step 2:

[1477] The terminal receives input data from the braille display. The braille display is connected to the terminal and transmits the input braille data to the terminal in real time.

[1478] Step 3:

[1479] The terminal converts the received braille data into text data. A conversion algorithm is used to convert the braille data "⠓⠑⠇⠇⠕" into the text data "hello".

[1480] Step 4:

[1481] The terminal sends the converted text data to the server. This transmission is performed using an HTTP POST request, and the text data is sent to the specified server endpoint.

[1482] Step 5:

[1483] The server receives text data sent from the terminal. The server parses the received text data and converts it to an appropriate format.

[1484] Step 6:

[1485] The server invokes a generation AI to generate response text based on the received text data. For example, in response to the text data "Hello," it generates the response "Hello! How are you?"

[1486] Step 7:

[1487] The server invokes the emotion engine and requests data from the terminal necessary to recognize the user's emotions. This includes requesting a detailed analysis of emotional information such as cheek texture, tone of voice, and facial expressions.

[1488] Step 8:

[1489] The device activates its camera and microphone to collect user emotional information, gathering data in real time. For example, it might detect if the user's voice tone is low and their facial expression is tired.

[1490] Step 9:

[1491] The device collects emotional data and sends it to the server. The emotional information is encoded as audio or video data and sent to the server.

[1492] Step 10:

[1493] The server analyzes the received emotional data using an emotion engine to determine the user's emotional state. For example, it might determine that the user is tired.

[1494] Step 11:

[1495] The server optimizes the AI's response text based on the analysis results from the emotion engine. For example, if the user is tired, it might generate a response like, "Hello! You must be tired. How was your day?"

[1496] Step 12:

[1497] The server sends an optimized response text back to the terminal. This response is also sent as an HTTP response, and the data is sent in a format that the terminal can receive.

[1498] Step 13:

[1499] The terminal receives the response text sent back from the server. The terminal analyzes the received data and extracts the response text "Hello! Thank you for your hard work. What happened today?".

[1500] Step 14:

[1501] The terminal converts the received response text into audio data. Using a text-to-speech engine, it performs the process of converting the text "Hello! Good work today. What happened today?" into speech.

[1502] Step 15:

[1503] The device plays the generated audio data. The audio is output through speakers or headphones for the user to hear. The user can receive the AI's response via voice.

[1504] In this way, the generation AI processes the input from the braille display and completes a series of processes that provide the optimal response in voice, tailored to the user's emotions.

[1505] (Example 2)

[1506] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1507] Braille displays are widely used as a means for visually impaired people to efficiently acquire information. However, the simple text input and output of Braille displays alone is insufficient to complement visual information. Furthermore, obtaining responses using generative AI models has limitations in providing optimal communication tailored to the user's emotional state. Therefore, a system is needed that recognizes the user's emotions and optimizes responses based on those emotions.

[1508] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for generating response text based on the received text data using an AI model generated by the server, means for acquiring user emotion data using an emotion engine that recognizes the user's emotions, means for optimizing the response text generated based on the acquired emotion data, means for returning the optimized response text to the terminal, means for converting the returned response text into audio data, and means for playing the audio data. This makes it possible for visually impaired people using a braille display to efficiently acquire AI information and receive optimal responses in real time that correspond to their emotions.

[1509] A "Braille display" is a device that allows visually impaired people to input and read Braille.

[1510] "Input data" refers to information entered by the user using a braille display.

[1511] A "terminal" is a device that is connected to a braille display and receives and processes input data.

[1512] "Text data" refers to character information obtained by converting Braille data.

[1513] A "server" is a computer system that receives data transmitted from terminals via a network and performs analysis and response generation.

[1514] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate appropriate response text based on received text data.

[1515] An "emotion engine" is a system that acquires emotional data from the user's voice and facial expressions and analyzes that data.

[1516] "Emotional data" refers to data that indicates the user's emotional state, acquired by the emotion engine.

[1517] "Response text" refers to the text data of the response to user input, generated by a generative AI model.

[1518] "Optimization" refers to the process of adjusting the content and tone of response text based on acquired sentiment data.

[1519] "Audio data" refers to data obtained by converting text data into speech using a speech synthesis engine.

[1520] "Playback means" refers to devices used to allow users to listen to the generated audio data, specifically speakers and headphones.

[1521] This invention provides a system that enables visually impaired individuals to efficiently obtain information from AI-generated using a Braille display, while recognizing the user's emotions and optimizing the response accordingly. The system consists of four main components: a Braille display, a terminal, a server, and an emotion engine.

[1522] Basic System Configuration

[1523] Braille display

[1524] Users input text using a braille display. For example, typing "hello" is done by pressing a specific button or key on the braille display. The braille display connects to the terminal via Bluetooth or USB and transmits the input data to the terminal in real time.

[1525] terminal

[1526] The terminal is responsible for receiving braille data from a braille display, converting it into text data, and sending that text data to the server. Using a conversion algorithm, it converts the braille data "⠓⠑⠇⠇⠕" into the text data "hello". It also uses a text-to-speech engine to convert the response text sent back from the server into audio data and play it back.

[1527] server

[1528] The server receives text data sent from the terminal, analyzes the received data, and generates response text using a generative AI model. Furthermore, it optimizes the response based on sentiment data from the sentiment engine and sends the optimized response text back to the terminal. As an example of response generation, the response "Hello! How are you?" is generated in response to the text "Hello".

[1529] Emotional Engine

[1530] The emotion engine built into the device analyzes the user's voice tone, facial expressions, and body movements to recognize their emotions. Emotional data is acquired in real time, sent to the server, and used to generate responses. For example, if the emotion engine detects that the user is tired, the server will generate a gentle response such as, "You look tired today. What's the matter?"

[1531] Specific example

[1532] The user inputs "hello" using a braille display. The data transmitted from the braille display is converted to the text "hello" by the terminal and sent to the server. The server generates a response, "Hello! How are you?" and then the emotion engine recognizes the user's emotions. If it determines, for example, that the user is tired, the response changes to "Hello, you look tired today. What's the matter?" Finally, this response is converted into audio data and transmitted to the user through speakers or headphones.

[1533] Example of a prompt

[1534] The user typed "Hello" using a braille display. The generated response was "Hello! How are you?". If the system determined the user was tired, the response changed to "Hello, you look tired today. What's the matter?".

[1535] In this way, the AI ​​processes input from the braille display and provides an optimal response in voice that reflects the user's emotions, completing a series of processes. This makes it possible for visually impaired people to acquire information and communicate more comfortably.

[1536] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1537] Step 1:

[1538] The user inputs "Hello" using a braille display. The braille display transmits the input data to the terminal in real time, and the terminal receives this data. Specifically, by performing certain button or key operations on the braille display, the braille data "⠓⠑⠇⠇⠕" is generated. This braille data is then transmitted to the terminal.

[1539] Input: User's Braille input data

[1540] Output: Data transmission from braille display to terminal

[1541] Step 2:

[1542] The terminal receives braille data "⠓⠑⠇⠇⠕" and converts it to text data "hello". Specifically, it applies a braille-to-corresponding text conversion algorithm to convert the braille data to text data. This converted text data is then sent to the server endpoint specified in the HTTP POST request.

[1543] Input: Received braille data "⠓⠑⠇⠇⠕"

[1544] Output: Converted text data "hello", and transmission to the server.

[1545] Step 3:

[1546] The server receives the text data "hello" sent from the terminal. The server analyzes the received data and calls a generative AI model to generate an appropriate response, "Hello! How are you?". Specifically, the process involves extracting text data from the HTTP request and inputting it into the generative AI model to generate the response text.

[1547] Input: Text data "hello" sent from the terminal.

[1548] Output: Generated response text "Hello! How are you?"

[1549] Step 4:

[1550] The server sends the generated response text back to the terminal via the network. Specifically, it structures the response text in JSON format or similar and sends it to the terminal as an HTTP response.

[1551] Input: Generated response text "Hello! How are you?"

[1552] Output: Send response text to the terminal as an HTTP response.

[1553] Step 5:

[1554] The device receives a response text sent back from the server. The device uses an emotion engine to recognize the user's emotional state. Specifically, it analyzes the user's tone of voice, facial expressions, body movements, etc., to obtain emotional data.

[1555] Input: Response text from the server, and user emotion input data (voice, facial expressions, etc.)

[1556] Output: Acquired sentiment data

[1557] Step 6:

[1558] The server receives emotion data sent from the terminal and optimizes the response text based on it. If the server detects that the user is tired, it reflects the parameters in the generating AI model and changes the response to a gentler tone, such as, "Hello, you look tired today. How can I help you?"

[1559] Input: Acquired sentiment data

[1560] Output: Optimized response text "Hello, you look tired today. How can I help you?"

[1561] Step 7:

[1562] The device converts the optimized response text into audio data. Specifically, it uses a text-to-speech engine to convert the response text "Hello! How are you?" into audio data. The generated audio data is then played back to the user through speakers or headphones.

[1563] Input: Optimized response text

[1564] Output: Generated audio data, playback of audio data

[1565] Through the steps described above, user input from the braille display is processed by a generative AI, and a response optimized for the user's emotions is provided as voice.

[1566] (Application Example 2)

[1567] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1568] When visually impaired individuals shop online, they face challenges such as inefficiently obtaining text information or receiving responses that reflect their emotions. Furthermore, there is a growing need for a more comfortable shopping experience by providing responses optimized based on the user's emotional state.

[1569] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1570] In this invention, the server includes means for receiving input data from a braille display, means for converting the received braille data into text data, means for transmitting the converted text data to the server, means for the server to generate response text based on the received text data using a generation AI, means for returning the generated response text to the terminal, means for converting the returned response text into audio data, means for playing the audio data, and means for analyzing the user's emotional data using an emotion recognition engine and optimizing the response by the generation AI based on the received emotional data. This enables visually impaired people to efficiently shop online using a braille display and to provide an optimal response based on the user's emotional state.

[1571] A "braille display" is a device that allows visually impaired people to input and output information using braille.

[1572] "Means for receiving input data" refers to a function or device for acquiring braille input data from a braille display.

[1573] "Means for converting to text data" refers to a process or device for converting Braille data into corresponding character data.

[1574] "Means of sending to the server" refers to a function or device for sending the converted text data to a server via a network.

[1575] "Generative AI" is an artificial intelligence technology that generates appropriate responses based on received text data.

[1576] "Means for generating response text" refers to a function or device for creating response text for input text data using a generation AI.

[1577] "Means of returning to the terminal" refers to a function or device for sending the generated response text back to the terminal via the network.

[1578] "Means for converting to audio data" refers to a process or device for converting the returned response text into an audio format.

[1579] "Means for playing audio data" refers to a function or device that allows the user to hear the converted audio data through a speaker or similar device.

[1580] An "emotion recognition engine" is a technology or device that analyzes and recognizes a user's emotional state from their voice, biosignals, etc.

[1581] "Means for analyzing emotional data" refers to a function or device that uses an emotional recognition engine to analyze a user's emotional state and acquire specific emotional data.

[1582] "Means for optimizing responses by generative AI" refers to a function or device for optimizing the responses generated by generative AI to match the user's emotional state, based on analyzed emotional data.

[1583] This invention relates to a system that enables visually impaired individuals to efficiently conduct online shopping using a Braille display, and further provides optimal responses tailored to the user's emotions.

[1584] System Configuration

[1585] The system consists of the following elements:

[1586] Braille display

[1587] Device (smartphone)

[1588] server

[1589] Emotion recognition engine

[1590] Generation AI

[1591] Speech synthesis engine

[1592] Operation overview

[1593] The user first inputs text using a braille display. For example, if the user types "What products do you recommend?" on the braille display, this braille data is sent to the terminal in real time.

[1594] The terminal converts the received braille data into text data. This conversion uses a conversion algorithm that converts the braille data "⠕⠽⠗⠕⠕⠫" into the text data "What products do you recommend?".

[1595] The converted text data is sent to the server using an HTTP POST request. The server receives this text data via the specified endpoint.

[1596] The server analyzes the received text data and calls a generation AI to generate a response text. For example, in response to the text data "What products do you recommend?", the generation AI generates the response "These are the products we recommend for you."

[1597] Next, the server sends the generated response text back to the terminal via the network. The returned response text is received by the terminal.

[1598] The device uses a speech synthesis engine to convert this response text into speech data. In this process, the text "Here are some products we recommend for you" is converted into speech.

[1599] Finally, the generated audio data is played to the user through speakers or headphones.

[1600] Furthermore, the system uses an emotion recognition engine to analyze the user's emotions in real time. The emotion recognition engine acquires emotional data from the user's voice, facial expressions, and body movements, and analyzes it when the user makes input or when a response is received. This emotional data is sent to the server, and the generating AI optimizes the response. For example, if the emotion recognition engine determines that the user is tired, the generated response will also change to a gentler tone, such as "Here are some easy-to-purchase products that we recommend for you."

[1601] Specific example

[1602] For example, if a user types "What products do you recommend?" on a braille display, and the emotion recognition engine detects the user's fatigue level, an example of the prompt message sent to the server would be as follows:

[1603] What are today's recommended products? The user seems a little tired.

[1604] Based on this prompt, the AI ​​generates a response saying, "Here are some easy-to-purchase products recommended for you," and communicates it to the user via voice. This allows visually impaired individuals to shop online efficiently and comfortably through a braille display and voice response.

[1605] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1606] Step 1:

[1607] The user inputs data using a braille display. This input data is provided in braille format. Specifically, when the user inputs "What products do you recommend?" into the braille display, braille data is generated. The braille display then transmits this data to the terminal.

[1608] Input: Braille data entered on a Braille display.

[1609] Output: Braille data sent to the terminal

[1610] Step 2:

[1611] The terminal converts the braille data received from the braille display into text data. The braille data "⠕⠽⠗⠕⠕⠫" is converted into the text data "What products do you recommend?". This conversion is performed by an algorithm that replaces braille characters with their corresponding characters.

[1612] Input: Braille data

[1613] Output: Text data "What products do you recommend?"

[1614] Step 3:

[1615] The terminal sends the converted text data to the server using an HTTP POST request. This request contains the converted text data.

[1616] Input: Text data "What products would you recommend?"

[1617] Output: HTTP POST request sent to the server

[1618] Step 4:

[1619] The server receives text data sent from the terminal and generates response text using a generation AI. Based on the prompt text corresponding to the input text "What products do you recommend?", the generation AI generates the response text "Here are the products we recommend for you."

[1620] Input: Text data sent from the device: "What products do you recommend?"

[1621] Output: Generated response text "Here are some products we recommend for you."

[1622] Step 5:

[1623] The server sends the generated response text back to the terminal. This return is also done via an HTTP request, and the response text is sent to the terminal.

[1624] Input: Generated response text "Here are some products we recommend for you."

[1625] Output: Response text sent back to the terminal

[1626] Step 6:

[1627] The device uses a speech synthesis engine to convert the returned response text into speech data. It performs the process of converting the text data "Here are some products we recommend for you" into speech data.

[1628] Input: Response text "Here are some products we recommend for you."

[1629] Output: Converted audio data

[1630] Step 7:

[1631] The device plays the generated audio data to the user through a speaker or headphones. This allows visually impaired individuals to confirm responses by voice.

[1632] Input: Converted audio data

[1633] Output: Audio data played from speakers or headphones: "Here are some products we recommend for you."

[1634] Step 8:

[1635] The device uses an emotion recognition engine to analyze the user's emotional data. Emotional data such as voice tone, facial expressions, and body movements are acquired in real time, and the user's emotional state is determined based on this. For example, the emotion recognition engine might determine that the user is tired.

[1636] Input: User's real-time sentiment data

[1637] Output: User's emotional state as an analysis result (e.g., tired)

[1638] Step 9:

[1639] The server optimizes the AI's response based on the received emotional data. If the AI ​​determines that the user is tired, it will generate a gentler response, such as, "Here are some easy-to-purchase products that we recommend for you."

[1640] Input: Sentiment data analysis results

[1641] Output: Optimized response text

[1642] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1643] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1644] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1645] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1646] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1647] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1648] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1649] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1650] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1651] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1652] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1653] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1654] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1655] 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.

[1656] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1657] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1658] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1659] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1660] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1661] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1662] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1663] The following is further disclosed regarding the embodiments described above.

[1664] (Claim 1)

[1665] A means for receiving input data from a braille display,

[1666] A means of converting received braille data into text data,

[1667] A means of sending the converted text data to the server,

[1668] A means for generating response text based on text data received by a server using AI generation,

[1669] A means of sending the generated response text back to the terminal,

[1670] A means of converting the returned response text into audio data,

[1671] A means of playing audio data,

[1672] A system that includes this.

[1673] (Claim 2)

[1674] The system according to claim 1, further comprising means for receiving input data from a braille display and converting the received braille data into text data.

[1675] (Claim 3)

[1676] The system according to claim 1, further comprising means for generating response text using a generative AI and converting the generated response text into audio data.

[1677] "Example 1"

[1678] (Claim 1)

[1679] A means for receiving input data from a braille display,

[1680] A means of converting received braille data into text data,

[1681] A means of sending the converted text data to the server,

[1682] A means for generating response text based on text data received by a server using AI generation,

[1683] A means of sending the generated response text back to the terminal,

[1684] A means of converting the returned response text into audio data,

[1685] A means of playing audio data,

[1686] Software means for converting Braille data,

[1687] A method for inputting text data as a prompt to the AI ​​that generates it,

[1688] A means by which a generative AI model generates a response based on a prompt,

[1689] Encryption methods for securely sending and receiving text data,

[1690] A system that includes this.

[1691] (Claim 2)

[1692] The system according to claim 1, wherein the means for receiving input data from a braille display and converting the received braille data into text data includes software means for converting braille to text.

[1693] (Claim 3)

[1694] The system according to claim 1, comprising means for generating response text using a generative AI and inputting a prompt sentence to a generative AI model in order to convert the generated response text into speech data.

[1695] "Application Example 1"

[1696] (Claim 1)

[1697] A means for receiving input data from a braille display,

[1698] A means of converting received braille data into text data,

[1699] A means of sending the converted text data to the server,

[1700] A means for generating response text based on text data received by a server using AI generation,

[1701] A means of sending the generated response text back to the terminal,

[1702] A means of converting the returned response text into audio data,

[1703] A means of playing audio data,

[1704] A means by which orders for food delivery services are entered via a braille display, and a generating AI confirms and responds to the order details,

[1705] A system that includes this.

[1706] (Claim 2)

[1707] The system according to claim 1, comprising means for receiving input data from a braille display and converting the received braille data into text data.

[1708] (Claim 3)

[1709] The system according to claim 1, comprising means for generating response text based on food delivery order details using a generative AI, and converting the generated response text into voice data.

[1710] "Example 2 of combining an emotion engine"

[1711] (Claim 1)

[1712] A means for receiving input data from a braille display,

[1713] A means of converting received braille data into text data,

[1714] A means of sending the converted text data to the server,

[1715] A server generates response text based on received text data using a generated AI model,

[1716] A means of acquiring user emotion data using an emotion engine that recognizes user emotions,

[1717] A means for optimizing response text generated based on acquired sentiment data,

[1718] A means of sending an optimized response text back to the terminal,

[1719] A means of converting the returned response text into audio data,

[1720] A means of playing audio data,

[1721] A system that includes this.

[1722] (Claim 2)

[1723] The system according to claim 1, comprising means for receiving input data from a braille display and converting the received braille data into text data.

[1724] (Claim 3)

[1725] The system according to claim 1, comprising means for generating response text using a generative AI model and converting the optimized response text, based on acquired sentiment data, into speech data.

[1726] "Application example 2 when combining with an emotional engine"

[1727] (Claim 1)

[1728] A means for receiving input data from a braille display,

[1729] A means of converting received braille data into text data,

[1730] A means of sending the converted text data to the server,

[1731] A means for generating response text based on text data received by a server using AI generation,

[1732] A means of sending the generated response text back to the terminal,

[1733] A means of converting the returned response text into audio data,

[1734] A means of playing audio data,

[1735] A means for analyzing user emotional data using an emotion recognition engine and optimizing the response generated by AI based on the received emotional data,

[1736] A system that includes this.

[1737] (Claim 2)

[1738] The system according to claim 1, further comprising means for receiving input data from a braille display and converting the received braille data into text data.

[1739] (Claim 3)

[1740] The system according to claim 1, further comprising means for generating response text using a generative AI and converting the generated response text into audio data. [Explanation of symbols]

[1741] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving input data from a braille display, A means of converting received braille data into text data, A means of sending the converted text data to the server, A means for generating response text based on text data received by a server using AI generation, A means of sending the generated response text back to the terminal, A means of converting the returned response text into audio data, A means of playing audio data, A system that includes this.

2. The system according to claim 1, further comprising means for receiving input data from a braille display and converting the received braille data into text data.

3. The system according to claim 1, further comprising means for generating response text using a generative AI and converting the generated response text into audio data.

Images