System

Abstract

A system is provided.SOLUTION: A communication support system comprising: means for capturing a voice of a user; means for converting the captured voice into text data; means for converting the text data into sign language video data; means for displaying the sign language video data; means for capturing a sign language action of the user; means for converting the captured sign language action into text data; and means for displaying the text data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In order for the hearing impaired to communicate smoothly, sign language is necessary, but many hearing-impaired people have not mastered sign language techniques. Furthermore, there is a shortage of sign language interpreters, making it difficult for the hearing impaired to communicate smoothly. This creates a communication barrier between the hearing impaired and hearing-able people. The present invention aims to solve this problem by providing a system that allows hearing impaired people and hearing-able people who do not know sign language to easily communicate. [Means for solving the problem]

[0005] The present invention provides a communication support system including a means for capturing a user's voice, a means for converting the captured voice into text data, a means for converting the text data into sign language video data, a means for displaying the sign language video data, a means for capturing a user's sign language actions, a means for converting the captured sign language actions into text data, and a means for displaying the text data. Specifically, by combining the stages of capturing voice and converting it into text, converting the text into sign language video and displaying it, and capturing sign language actions and converting it into text and displaying it, smooth two-way communication is realized between hearing-impaired people and able-bodied people who do not know sign language.

[0006] A "user" is a person who communicates using the system.

[0007] "Sound" refers to auditory information generated by air vibrations, etc., including language.

[0008] "Capture" refers to taking in data such as audio or images and making it available for recording or transmission.

[0009] "Means" refers to a device or method for achieving a particular function.

[0010] "Text data" refers to data that represents character information in digital form.

[0011] "Sign language video data" is video data that visually expresses sign language actions.

[0012] A "sign language database" refers to an information source that stores text and corresponding sign language video data.

[0013] A "camera" is a device that captures visual information and has the ability to take images and videos.

[0014] "Real-time" refers to data processing and information provision occurring immediately and without delay.

[0015] "Display" refers to providing captured or generated data visually to a user.

[0016] "Conversion" refers to the replacement of one form or type of data with another form or type of data.

[0017] A "communication support system" refers to a system that facilitates the exchange of information among multiple users. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. The specific operation of the program for this system is explained below.

[0040] Program Overview

[0041] This system is mainly composed of a terminal and a server, each of which functions according to its own role. In particular, the terminal captures voice and sign language, and the server analyzes and converts them.

[0042] Audio to sign language video conversion

[0043] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm. This text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0044] Specific examples

[0045] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lenses of the smart glasses. In this way, the user can understand what the other person is saying by watching the sign language video of "hello."

[0046] Sign language to text conversion

[0047] When a user responds in sign language, the device's camera captures the sign in real time. The captured data is sent to a server, which uses a machine learning algorithm to analyze the sign and generate corresponding text data. This text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand what the user is saying in sign language as text.

[0048] Specific examples

[0049] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[0050] In this way, the communication support system of the present invention realizes smooth communication between hearing-impaired and hearing-normal people by converting speech to sign language and sign language to text in real time.

[0051] The processing flow will be explained below.

[0052] Audio to sign language video conversion

[0053] Step 1:

[0054] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[0055] Step 2:

[0056] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0057] Step 3:

[0058] The server then passes the received voice data through speech recognition software to convert it into text, using natural language processing algorithms to accurately convert the speech into text.

[0059] Step 4:

[0060] The server compares the text data with a sign language database and extracts the corresponding sign language video data.

[0061] Step 5:

[0062] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[0063] Step 6:

[0064] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing the user to visually confirm the sign language video.

[0065] Sign language to text conversion

[0066] Step 1:

[0067] The user responds in sign language, and the device's camera captures this sign language action in real time.

[0068] Step 2:

[0069] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0070] Step 3:

[0071] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[0072] Step 4:

[0073] The server generates text data based on the analysis results, accurately converting the meaning of the sign language into text.

[0074] Step 5:

[0075] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[0076] Step 6:

[0077] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person you are talking to to see the meaning of your sign language as text.

[0078] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, ensuring smooth communication.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Conventional communication support systems have had the problem of making it difficult for hearing-impaired people and hearing-savvy people who do not know sign language to communicate smoothly. In particular, the lack of technology to convert speech into sign language in real time and sign language into text in real time makes rapid communication difficult.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes means for converting received voice data into text data, means for converting the text data into sign language video data based on a sign language database, and means for converting received sign language action data into text data, thereby making it possible to convert voice into sign language video in real time and sign language actions into text in real time.

[0084] "User" refers to a person who uses the system to convert audio into sign language video or sign language actions into text.

[0085] "Audio capture means" refers to a device such as a microphone for recording the user's voice.

[0086] "Audio compression means" refers to a technique for compressing recorded audio data to reduce the data size.

[0087] "Transmission means" refers to the communication technology used to transmit compressed audio data and captured sign language movement data to the server.

[0088] A "server" refers to a computer system or software that analyzes and converts received data.

[0089] "Natural language processing algorithm" refers to an algorithm for analyzing voice data and converting it into text data.

[0090] "Sign language database" refers to a database that stores sign language information for converting text data into corresponding sign language video.

[0091] "Sign language video generation means" refers to a technology that converts text data into sign language video data based on a sign language database.

[0092] "Sign language video display means" refers to technology for displaying the generated sign language video data on smart glasses, displays, etc.

[0093] The "sign language action capture means" refers to a device such as a camera for recording a user's sign language actions in real time.

[0094] "Machine learning algorithm" refers to an algorithm for analyzing received sign language movement data and converting it into text data.

[0095] "Text display means" refers to technology for displaying converted text data on smart glasses, displays, etc.

[0096] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. This system consists of a terminal and a server, each of which plays a different role.

[0097] Audio to sign language video conversion

[0098] When a user begins a conversation, the device uses a microphone to capture audio. The captured audio data is compressed and sent to a server. The server then converts the received audio data into text data using a natural language processing algorithm. This text data is compared with a sign language database, and corresponding sign language video data is generated. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lenses of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0099] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lens of the smart glasses. In this way, the user can visually confirm the sign language video of "hello."

[0100] Sign language to text conversion

[0101] When the user responds in sign language, the device's camera captures the sign language movements in real time. The captured movement data is sent to a server. The server uses a machine learning algorithm to analyze the sign language movement data and generate corresponding text data. The generated text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand the user's sign language as text.

[0102] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[0103] Specific examples

[0104] Example prompt sentence:

[0105] Please translate and explain the following sentences in natural Japanese. Please make sure the subject is either server, terminal, or user. Please use the plain voice (da / dearu style) for endings.

[0106] ---

[0107] {Technical explanation of how the system works}

[0108] ---

[0109] This system is a communication support system designed for use by users, converting audio to sign language video and sign language to text in real time.

[0110] In this way, the communication support system of the present invention realizes smooth communication between the hearing impaired and the hearing-impaired by converting speech to sign language and sign language to text in real time.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Processing steps for audio to sign language video conversion

[0113] Step 1:

[0114] The device uses a microphone to capture the user's voice.

[0115] Specific operation: The user says "Hello" and the voice is recorded by the device's microphone.

[0116] Input: User's voice

[0117] Output: Captured audio data

[0118] Step 2:

[0119] The captured audio data is compressed and sent to the server.

[0120] Specific operation: The recorded audio data is reduced in size using a data compression algorithm and sent over the network to a server.

[0121] Input: Captured audio data

[0122] Output: Compressed audio data

[0123] Step 3:

[0124] The server converts the received voice data into text data using a natural language processing algorithm.

[0125] Specific operation: The compressed voice data is decompressed and converted into the text data "Hello" using a voice recognition algorithm.

[0126] Input: Compressed audio data

[0127] Output: Converted text data

[0128] Step 4:

[0129] The server compares the generated text data with a sign language database and generates corresponding sign language video data.

[0130] Specific operation: The generated text data "Hello" is sent to a sign language database, and the corresponding sign language video data is searched and retrieved.

[0131] Input: Converted text data

[0132] Output: Sign language video data

[0133] Step 5:

[0134] The generated sign language video data is transmitted to the terminal.

[0135] Specific operation: Sign language video data is transmitted to the terminal in real time via the network.

[0136] Input: Sign language video data

[0137] Output: Transmitted sign language video data

[0138] Step 6:

[0139] The sign language video data received by the device is displayed on the lenses of the smart glasses.

[0140] Specific operation: The device displays the received sign language video data on the smart glasses display for the user to see.

[0141] Input: Received sign language video data

[0142] Output: Sign language video displayed on smart glasses

[0143] Sign language to text conversion processing steps

[0144] Step 1:

[0145] When the user responds in sign language, the device's camera captures the sign movements in real time.

[0146] Specific actions: The user signs "thank you" and the action is recorded by the device's camera.

[0147] Input: User sign language gesture

[0148] Output: Captured sign language movement data

[0149] Step 2:

[0150] The captured sign language action data is sent to a server.

[0151] Specific actions: The recorded sign language action data is sent to a server via a network.

[0152] Input: Captured sign language movement data

[0153] Output: Transmitted sign language movement data

[0154] Step 3:

[0155] The server analyzes the received sign language movement data using a machine learning algorithm and generates corresponding text data.

[0156] Specific action: The transmitted sign language movement data is analyzed by a machine learning algorithm, and the text data "Thank you" is generated.

[0157] Input: Received sign language movement data

[0158] Output: Generated text data

[0159] Step 4:

[0160] The generated text data is sent to the terminal.

[0161] Specific operation: Text data is sent to the terminal via the network.

[0162] Input: Generated text data

[0163] Output: The text data sent

[0164] Step 5:

[0165] The text data received by the device is displayed on the lenses of the smart glasses.

[0166] Specific operation: The device displays the received text data on the smart glasses display for the other party to see.

[0167] Input: Received text data

[0168] Output: Text displayed on the smart glasses

[0169] Through the above processing steps, the system converts audio into sign language video and sign language actions into text, enabling users to communicate smoothly in real time.

[0170] (Application example 1)

[0171] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0172] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-speaking people in brick-and-mortar stores. In situations where a sign language interpreter is needed, it is difficult for hearing-impaired people to obtain information independently, and there are only a limited number of professional sign language interpreters, so there is a need for faster response. Another issue is that if store staff do not understand sign language, communication takes time, resulting in a decline in service quality.

[0173] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0174] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for referencing a database specialized in generating sign language video data, and means having an interface for supporting customer service in a real-world store. This enables fast and efficient communication between hearing-impaired people and hearing-controlling people in a real-world store through real-time mutual conversion of text, sign language, and voice.

[0175] A "means for capturing user voice" is a part of the system that captures voice in digital form using a microphone or other voice input device.

[0176] The "means for converting captured voice into text data" is a function that converts acquired voice data into corresponding text data using voice recognition technology.

[0177] The "means for converting text data into sign language video data" is a conversion system for visualizing text data as sign language video based on a sign language database.

[0178] "Means for displaying sign language video data" refers to a function that outputs the generated sign language video to a display device such as a display or smart glasses.

[0179] A "means for capturing a user's sign language movements" is a part of a system that uses a camera or other image capture device to capture sign language movements as digital data.

[0180] The "means for converting captured sign language actions into text data" is a function that converts acquired sign language actions into corresponding text data using machine learning algorithms or image analysis technology.

[0181] "Means for displaying text data" refers to a function that outputs the converted text data to a display device such as a display or smart glasses.

[0182] "Means for referencing a database specialized in generating sign language video data" is a function for referencing a specialized database that stores the data necessary to convert text data into corresponding sign language video.

[0183] "Means with an interface to support customer service in a real-world store" refers to part of a system that includes a user interface and operation panel to facilitate communication between customers and staff in a real-world store.

[0184] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-normal people in brick-and-mortar stores. Specifically, this system converts a user's voice into sign language video and sign language actions into text, and is implemented using a terminal and a server.

[0185] Audio to sign language video conversion

[0186] The server uses the device's microphone to capture the user's voice. The captured voice data is converted into text data using the speech recognition library "SpeechRecognition." This text data is then converted into sign language video data based on a sign language database. This conversion uses an API that references the sign language database and generates the corresponding sign language video. The generated sign language video data is sent to the device in real time and displayed as a sign language video on a display device such as smart glasses. This process allows the user to see what the other person is saying in sign language video.

[0187] For example, if the person you are talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," and then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the audio 'hello' into a sign language video."

[0188] Sign language to text conversion

[0189] When a user responds in sign language, the device's camera captures the sign language in real time. The captured sign language data is sent to a server, which analyzes it using the image analysis library "pytesseract" and machine learning algorithms. The resulting text data is sent back to the device and displayed on a display device such as smart glasses, allowing the other person to understand what the user is saying in sign language as text.

[0190] For example, if a user signs "thank you," the device's camera captures the action and sends it to the server. The server analyzes it and generates the text "thank you," which is then sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the sign language video into the text 'thank you'."

[0191] This will enable real-time communication between hearing-impaired and hearing-savvy customers in brick-and-mortar stores. The system integrates multiple technologies, including voice recognition, sign language video generation, and image analysis, to provide fast and efficient customer service.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] The device captures the user's voice.

[0195] Input: User's voice data

[0196] Specific operation: The device's microphone captures the audio and converts it into digital audio data.

[0197] Output: Audio data

[0198] Step 2:

[0199] The server converts the voice data into text data.

[0200] Input: Audio data

[0201] Specific operation: The server uses a speech recognition library (SpeechRecognition) to convert the voice data into text data.

[0202] Output: Text data

[0203] Step 3:

[0204] The server converts the text data into sign language video data.

[0205] Input: Text data

[0206] Specific operation: The server references the sign language database and generates sign language video data corresponding to the text data. The sign language video generation API is used to obtain the sign language video data.

[0207] Output: Sign language video data

[0208] Step 4:

[0209] The device displays the sign language video data.

[0210] Input: Sign language video data

[0211] Specific operation: Display sign language videos on the device display or smart glasses, allowing users to watch sign language videos.

[0212] Output: Display of sign language video

[0213] Step 5:

[0214] The device captures the user's sign language actions.

[0215] Input: User's sign language actions

[0216] Specific operation: The device's camera captures sign language movements in real time and saves them as digital video data.

[0217] Output: Sign language video data

[0218] Step 6:

[0219] The server converts the sign language video data into text data.

[0220] Input: Sign language video data

[0221] Specific operation: The server uses an image analysis library (pytesseract) and a machine learning algorithm to convert sign language video data into text data.

[0222] Output: Text data

[0223] Step 7:

[0224] The terminal displays the text data.

[0225] Input: Text data

[0226] Specific operation: By displaying text data on the device display or smart glasses, the person you are speaking with can understand the content of the sign language.

[0227] Output: Display of text data

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

[0229] This invention relates to a communication support system that uses voice and sign language to enable smooth communication between hearing-impaired and hearing-normal people, and by combining it with an emotion engine that recognizes the user's emotional state, it achieves higher quality communication. The specific operation of the program for this system is explained below.

[0230] Program Overview

[0231] The system captures the user's voice and sign language actions, analyzes them, and converts them into corresponding sign language video and text data. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[0232] Audio to sign language video conversion

[0233] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm and an emotion engine. The text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0234] Specific examples

[0235] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, it retrieves the sign language video corresponding to "hello" from a sign language database and makes fine adjustments based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[0236] Sign language to text conversion

[0237] When a user responds in sign language, the device's camera captures the sign in real time. The captured movement data is sent to the server. The server then uses a machine learning algorithm and an emotion engine to analyze the sign data and generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the conversation partner to not only understand the user's sign language utterances as text, but also understand their emotional state.

[0238] Specific examples

[0239] For example, if a user sign "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[0240] In this way, the communication support system of the present invention not only converts speech to sign language and sign language to text, but also recognizes emotions using an emotion engine, thereby realizing richer communication.

[0241] The processing flow will be explained below.

[0242] Audio to sign language video conversion

[0243] Step 1:

[0244] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[0245] Step 2:

[0246] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0247] Step 3:

[0248] The server passes the received voice data through speech recognition software and converts it into text data using natural language processing algorithms.

[0249] Step 4:

[0250] The server passes the text data through an emotion engine to analyze the emotional state in the voice, generating text data with emotional information added.

[0251] Step 5:

[0252] The server compares the text data with a sign language database and extracts the corresponding sign language video data, and also performs fine-tuning based on emotional information.

[0253] Step 6:

[0254] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[0255] Step 7:

[0256] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing users to visually confirm the sign language video and its emotional information.

[0257] Sign language to text conversion

[0258] Step 1:

[0259] The user responds in sign language, and the device's camera captures this sign language action in real time.

[0260] Step 2:

[0261] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0262] Step 3:

[0263] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[0264] Step 4:

[0265] The server passes the sign language movement data through an emotion engine to analyze the emotional state of the sign language, and generates text data with emotional information added.

[0266] Step 5:

[0267] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[0268] Step 6:

[0269] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person speaking to see the meaning of the user's sign language and its emotional information as text.

[0270] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, enabling smooth communication that also includes emotional information.

[0271] Example 2

[0272] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0273] While existing communication support systems provide functions for converting speech to sign language and sign language to text for communication between hearing-impaired and hearing-disabled people, they have a problem in that they are unable to improve the quality of communication by taking into account the emotional state of the user.In addition, there is a lack of means to accurately recognize the emotional state and modify the sign language video based on that, which means that the nuances of actual conversation cannot be fully conveyed.

[0274] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0275] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing the user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing the user's emotional state from the captured voice and sign language actions, and means for modifying the sign language video data based on the emotional state. This enables conversion of the sign language video and text data that reflects the user's emotional state, making it possible to more accurately convey the nuances of actual conversation.

[0276] "User" refers to an individual or group that communicates using the System.

[0277] "Means for capturing audio" refers to a microphone or other audio input device for collecting the user's voice.

[0278] "Text data conversion means" refers to software or algorithms for converting speech or sign language into a corresponding text format.

[0279] "Means for converting into sign language video data" refers to software or algorithms for converting text data into a corresponding sign language video format.

[0280] "Means for displaying sign language video data" refers to a display device or projector for presenting the generated sign language video to a user.

[0281] "Means for capturing sign language actions" refers to a camera or other video input device for photographing or recording a user's sign language actions.

[0282] "Means for recognizing emotional state" refers to software or algorithms for analyzing and recognizing a user's emotions from speech or sign language actions.

[0283] "Means for modifying sign language video data based on emotional state" refers to software or algorithms that adjust or modify the generated sign language video based on recognized emotional information.

[0284] "Server" means a centralized computer system for processing and storing data.

[0285] "System" refers to the overall mechanism in which the above means operate in conjunction with each other.

[0286] This invention relates to a system that enables smooth communication between hearing-impaired and hearing-suffering people, and aims to deepen mutual understanding by using voice and sign language. Furthermore, by combining it with an emotion engine, it recognizes the user's emotional state and achieves higher quality communication.

[0287] Audio to sign language video conversion

[0288] The device captures the user's voice through a microphone. It then compresses the captured voice data and sends it to a server via the Internet. The server receives this voice data and converts it into text data using a natural language processing algorithm (e.g., Google Cloud Speech-to-Text API) and an emotion engine. The converted text data is then compared with a sign language database (e.g., Sign Language API) to generate corresponding sign language video data. This sign language video data is then fine-tuned by the emotion engine based on the user's emotional state. Finally, the generated sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0289] Sign language to text conversion

[0290] When a user responds in sign language, the device's camera (for example, Microsoft's Azure Kinect DK) captures the sign language in real time. The captured movement data is sent to a server, which analyzes it using machine learning algorithms (TensorFlow or PyTorch) and an emotion engine to generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the person speaking not only to understand the user's sign language utterances as text, but also to understand their emotional state.

[0291] Specific operation example

[0292] Audio to sign language video conversion example

[0293] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, the server retrieves the sign language video corresponding to "hello" from a sign language database and fine-tunes it based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[0294] Sign language to text example

[0295] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[0296] Example prompts to input to the generative AI model

[0297] An example of a prompt sentence that can be input to the generative AI model would be, "Please convert the content and emotion expressed by the user in sign language into text."

[0298] With the above-described configuration and processing, the present invention realizes smooth communication via voice and sign language, and further improves the quality of communication by taking emotional states into consideration.

[0299] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0300] Audio to sign language video conversion

[0301] Step 1:

[0302] A user initiates a conversation.

[0303] Input: Voice of the person you are talking to.

[0304] Action: The user says "Good morning" to the other person.

[0305] Output: Voice data of the conversation partner.

[0306] Step 2:

[0307] The device captures the audio.

[0308] Input: Voice data of the conversation partner.

[0309] How it works: The built-in microphone on your smartphone or dedicated device picks up sound.

[0310] Output: The captured audio data.

[0311] Step 3:

[0312] The device sends the captured audio to the server.

[0313] Input: Captured audio data.

[0314] How it works: The device compresses the audio data and sends it over the internet to a server using an HTTP POST request.

[0315] Output: The audio data sent to the server.

[0316] Step 4:

[0317] The server converts the speech to text.

[0318] Input: The audio data sent to the server.

[0319] How it works: The received audio data is converted to text using the Google Cloud Speech-to-Text API, with the emotion engine also analyzing the tone and pitch of the voice.

[0320] Output: The converted text data.

[0321] Step 5:

[0322] The server converts the text into sign language video.

[0323] Input: Converted text data and emotional information contained in the speech.

[0324] How it works: The text data is matched against a sign language database using the Sign Language API, and the corresponding sign language video data is generated.

[0325] Output: Generated sign language video data.

[0326] Step 6:

[0327] The server sends the sign language video to the device.

[0328] Input: Generated sign language video data.

[0329] How it works: The generated sign language video data is sent to the device in real time, again using an HTTP POST request.

[0330] Output: Sign language video data sent to the device.

[0331] Step 7:

[0332] The device displays the sign language video.

[0333] Input: Sign language video data sent to the device.

[0334] How it works: The device displays the received sign language video on the lenses of the smart glasses.

[0335] Output: Visualized sign language video data.

[0336] Sign language to text conversion

[0337] Step 1:

[0338] The user responds in sign language.

[0339] Input: A sign language response.

[0340] Action: For example, perform an action to express "thank you" in sign language.

[0341] Output: Beginning of sign language action.

[0342] Step 2:

[0343] The device captures the sign language gestures.

[0344] Input: Sign language actions.

[0345] Actions: Smart glasses and camera devices capture sign language actions in real time. Azure Kinect DK is used.

[0346] Output: Captured sign language data.

[0347] Step 3:

[0348] The terminal transmits the captured sign language data to the server.

[0349] Input: Captured sign language data.

[0350] How it works: The device compresses the captured sign language data and sends it over the internet to a server.

[0351] Output: Sign language data sent to the server.

[0352] Step 4:

[0353] The server converts the sign language data into text.

[0354] Input: Sign language data sent to the server.

[0355] How it works: The received sign language data is analyzed using TensorFlow or PyTorch, and the corresponding text data is generated. At the same time, the emotion engine also analyzes the emotions conveyed in the sign language.

[0356] Output: The converted text data.

[0357] Step 5:

[0358] The server transmits the generated text data to the terminal.

[0359] Input: Transformed text data and sentiment information.

[0360] Operation: The generated text data and emotion information are sent to the device in real time.

[0361] Output: Text data and emotion information sent to the device.

[0362] Step 6:

[0363] The terminal displays the text.

[0364] Input: Text data and emotional information sent to the device.

[0365] Operation: The device displays the received text data and emotional information on the lenses of the smart glasses.

[0366] Output: Visualized text data and sentiment information.

[0367] Through these specific processing steps, the system enables smooth, high-quality communication via voice and sign language.

[0368] (Application example 2)

[0369] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0370] Conventional communication support systems lack support for smooth communication between hearing-impaired and hearing-disabled people. Furthermore, the lack of emotion recognition can lead to a decline in the quality of communication. Furthermore, no sophisticated communication support using smart glasses is available in brick-and-mortar stores. To address these issues, the present invention aims to achieve higher quality communication by capturing voice and sign language movements, converting them into text data, and displaying sign language videos and text data, as well as using an emotion engine.

[0371] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0372] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing a user's emotional state and improving the quality of communication based on that information, and means for integrating the above means and supporting smooth communication using smart glasses in a physical store. This enables hearing-impaired and hearing-disabled people to understand each other's emotions and communicate smoothly in a physical store.

[0373] The "means for capturing the user's voice" is a device for picking up the voice emitted by the user and recording it as digital data.

[0374] The "means for converting captured audio into text data" refers to software or hardware for analyzing audio data and converting it into corresponding text format data.

[0375] The "means for converting text data into sign language animation data" is a process for generating animation of corresponding sign language actions based on the text data.

[0376] The "means for displaying sign language video data" refers to a display device for visually presenting the generated sign language video to the user.

[0377] The "means for capturing the user's sign language actions" is a device for capturing the user's sign language actions in real time and recording them as digital data.

[0378] The "means for converting the captured sign language actions into text data" refers to software or hardware for analyzing the sign language action data and converting it into corresponding text format data.

[0379] The "means for displaying text data" is a display device for visually presenting the converted text data to the user.

[0380] "Means for recognizing the user's emotional state and improving the quality of communication based on that information" refers to a system that analyzes the user's emotions from voice and sign language movement data, and provides appropriate responses and feedback based on that emotional information.

[0381] "Means for supporting smooth communication using smart glasses in physical stores" refers to devices and systems that use smart glasses in a physical store environment to enable users to communicate smoothly.

[0382] This invention is a system that supports smooth communication between hearing-impaired and hearing-savvy people in brick-and-mortar stores, and improves the quality of communication by converting and displaying speech and sign language using smart glasses, and by recognizing emotional states. This system is mainly composed of a server, a terminal (smart glasses), and user interaction.

[0383] Overall system configuration

[0384] The server captures the user's voice and sign language actions, analyzes them, and converts them into text data and sign language videos. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[0385] The device displays the sign language video and text data sent from the server in real time through the smart glasses, which are equipped with a microphone for capturing audio, a camera for capturing sign language movements, and a display device.

[0386] Program Overview

[0387] 1. Audio to Sign Language Video Conversion:

[0388] The server captures the user's voice through the device's microphone and converts it into text data. The generated text data is compared with a sign language video database to obtain the corresponding sign language video. An emotion engine is then used to add emotional information to the sign language video, which is then sent to the device. On the device side, the sign language video is displayed on the lenses of the smart glasses.

[0389] Examples:

[0390] For example, when a person with normal hearing says "Welcome," the microphone in the smart glasses captures the voice and sends it to the server. The server analyzes the voice and recognizes the text and the emotion contained in the voice. It then retrieves the corresponding sign language video from a sign language database and adjusts it based on the emotion information. This sign language video is then sent to the device and displayed on the smart glasses.

[0391] Example prompt sentence:

[0392] Voice input: "Welcome"

[0393] Sentiment Analysis: Joy

[0394] 2. Sign Language to Text Conversion:

[0395] When a user responds in sign language, the camera captures the sign in real time and sends it to the server. The server analyzes the sign and generates corresponding text data and emotion information. The generated text data and emotion information are sent to the device and displayed on the lens of the smart glasses.

[0396] Examples:

[0397] For example, if a user expresses "thank you" in sign language, the camera in the smart glasses captures the gesture and sends it to the server. The server analyzes it and recognizes the text data and the emotion of gratitude. This information is then sent to the device and displayed on the smart glasses.

[0398] Example prompt sentence:

[0399] Sign language input: "Thank you"

[0400] Sentiment Analysis: Gratitude

[0401] Hardware and software used

[0402] Hardware:

[0403] Smart glasses (e.g., AR glasses)

[0404] High-performance microphone

[0405] Cameras (e.g. smart glasses with high-resolution cameras)

[0406] software:

[0407] Natural language processing algorithms (e.g., speech recognition software)

[0408] Sentiment engines (e.g., sentiment analysis tools)

[0409] Sign language database (e.g., sign language conversion module)

[0410] Real-time image processing library (e.g. OpenCV)

[0411] This will enable hearing-impaired and hearing-sighted people to understand each other's emotions and communicate smoothly in physical stores.

[0412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0413] Step 1:

[0414] The device's microphone captures the user's voice. The captured voice data is converted into digital format and sent to the server. The input is the user's voice, and the output is digital voice data.

[0415] Step 2:

[0416] The server analyzes the received voice data and converts it into text data using a natural language processing algorithm. At the same time, it also uses an emotion engine to extract emotions from the voice. The input is digital voice data, and the output is text data and emotional information.

[0417] Step 3:

[0418] The server compares the text data with a sign language database and retrieves the corresponding sign language video data. It then fine-tunes the sign language video based on the extracted emotional information. The input is text data and emotional information, and the output is fine-tuned sign language video data.

[0419] Step 4:

[0420] The server transmits the sign language video data to the device in real time. The device displays the received sign language video data on the smart glasses display. The input is finely adjusted sign language video data, and the output is the sign language video displayed on the smart glasses.

[0421] Step 5:

[0422] When a user responds in sign language, the device's camera captures the sign language in real time, converts it into digital format, and sends it to the server. The input is the user's sign language, and the output is digital sign language data.

[0423] Step 6:

[0424] The server analyzes the received sign language motion data and converts it into text data using a machine learning algorithm. At the same time, it also uses an emotion engine to extract emotions from the sign language motion data. The input is digital sign language motion data, and the output is text data and emotion information.

[0425] Step 7:

[0426] The server sends the generated text data and emotional information to the terminal in real time. The terminal displays the received text data and emotional information on the smart glasses display. The input is text data and emotional information, and the output is the text data and emotional information displayed on the smart glasses.

[0427] Through these processing steps, hearing-impaired and hearing-speaking people can communicate effectively and smoothly in physical stores while understanding emotions.

[0428] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0429] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0430] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0431] [Second embodiment]

[0432] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0433] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0434] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0435] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0436] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0437] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0438] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0439] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0440] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0441] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0442] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0443] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0444] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. The specific operation of the program for this system is explained below.

[0445] Program Overview

[0446] This system is mainly composed of a terminal and a server, each of which functions according to its own role. In particular, the terminal captures voice and sign language, and the server analyzes and converts them.

[0447] Audio to sign language video conversion

[0448] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm. This text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0449] Specific examples

[0450] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lenses of the smart glasses. In this way, the user can understand what the other person is saying by watching the sign language video of "hello."

[0451] Sign language to text conversion

[0452] When a user responds in sign language, the device's camera captures the sign in real time. The captured data is sent to a server, which uses a machine learning algorithm to analyze the sign and generate corresponding text data. This text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand what the user is saying in sign language as text.

[0453] Specific examples

[0454] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[0455] In this way, the communication support system of the present invention realizes smooth communication between hearing-impaired and hearing-normal people by converting speech to sign language and sign language to text in real time.

[0456] The processing flow will be explained below.

[0457] Audio to sign language video conversion

[0458] Step 1:

[0459] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[0460] Step 2:

[0461] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0462] Step 3:

[0463] The server then passes the received voice data through speech recognition software to convert it into text, using natural language processing algorithms to accurately convert the speech into text.

[0464] Step 4:

[0465] The server compares the text data with a sign language database and extracts the corresponding sign language video data.

[0466] Step 5:

[0467] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[0468] Step 6:

[0469] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing the user to visually confirm the sign language video.

[0470] Sign language to text conversion

[0471] Step 1:

[0472] The user responds in sign language, and the device's camera captures this sign language action in real time.

[0473] Step 2:

[0474] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0475] Step 3:

[0476] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[0477] Step 4:

[0478] The server generates text data based on the analysis results, accurately converting the meaning of the sign language into text.

[0479] Step 5:

[0480] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[0481] Step 6:

[0482] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person you are talking to to see the meaning of your sign language as text.

[0483] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, ensuring smooth communication.

[0484] Example 1

[0485] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0486] Conventional communication support systems have had the problem of making it difficult for hearing-impaired people and hearing-savvy people who do not know sign language to communicate smoothly. In particular, the lack of technology to convert speech into sign language in real time and sign language into text in real time makes rapid communication difficult.

[0487] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0488] In this invention, the server includes means for converting received voice data into text data, means for converting the text data into sign language video data based on a sign language database, and means for converting received sign language action data into text data, thereby making it possible to convert voice into sign language video in real time and sign language actions into text in real time.

[0489] "User" refers to a person who uses the system to convert audio into sign language video or sign language actions into text.

[0490] "Audio capture means" refers to a device such as a microphone for recording the user's voice.

[0491] "Audio compression means" refers to a technique for compressing recorded audio data to reduce the data size.

[0492] "Transmission means" refers to the communication technology used to transmit compressed audio data and captured sign language movement data to the server.

[0493] A "server" refers to a computer system or software that analyzes and converts received data.

[0494] "Natural language processing algorithm" refers to an algorithm for analyzing voice data and converting it into text data.

[0495] "Sign language database" refers to a database that stores sign language information for converting text data into corresponding sign language video.

[0496] "Sign language video generation means" refers to a technology that converts text data into sign language video data based on a sign language database.

[0497] "Sign language video display means" refers to technology for displaying the generated sign language video data on smart glasses, displays, etc.

[0498] The "sign language action capture means" refers to a device such as a camera for recording a user's sign language actions in real time.

[0499] "Machine learning algorithm" refers to an algorithm for analyzing received sign language movement data and converting it into text data.

[0500] "Text display means" refers to technology for displaying converted text data on smart glasses, displays, etc.

[0501] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. This system consists of a terminal and a server, each of which plays a different role.

[0502] Audio to sign language video conversion

[0503] When a user begins a conversation, the device uses a microphone to capture audio. The captured audio data is compressed and sent to a server. The server then converts the received audio data into text data using a natural language processing algorithm. This text data is compared with a sign language database, and corresponding sign language video data is generated. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lenses of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0504] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lens of the smart glasses. In this way, the user can visually confirm the sign language video of "hello."

[0505] Sign language to text conversion

[0506] When the user responds in sign language, the device's camera captures the sign language movements in real time. The captured movement data is sent to a server. The server uses a machine learning algorithm to analyze the sign language movement data and generate corresponding text data. The generated text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand the user's sign language as text.

[0507] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[0508] Specific examples

[0509] Example prompt sentence:

[0510] Please translate and explain the following sentences in natural Japanese. Please make sure the subject is either server, terminal, or user. Please use the plain voice (da / dearu style) for endings.

[0511] ---

[0512] {Technical explanation of how the system works}

[0513] ---

[0514] This system is a communication support system designed for use by users, converting audio to sign language video and sign language to text in real time.

[0515] In this way, the communication support system of the present invention realizes smooth communication between the hearing impaired and the hearing-impaired by converting speech to sign language and sign language to text in real time.

[0516] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0517] Processing steps for audio to sign language video conversion

[0518] Step 1:

[0519] The device uses a microphone to capture the user's voice.

[0520] Specific operation: The user says "Hello" and the voice is recorded by the device's microphone.

[0521] Input: User's voice

[0522] Output: Captured audio data

[0523] Step 2:

[0524] The captured audio data is compressed and sent to the server.

[0525] Specific operation: The recorded audio data is reduced in size using a data compression algorithm and sent over the network to a server.

[0526] Input: Captured audio data

[0527] Output: Compressed audio data

[0528] Step 3:

[0529] The server converts the received voice data into text data using a natural language processing algorithm.

[0530] Specific operation: The compressed voice data is decompressed and converted into the text data "Hello" using a voice recognition algorithm.

[0531] Input: Compressed audio data

[0532] Output: Converted text data

[0533] Step 4:

[0534] The server compares the generated text data with a sign language database and generates corresponding sign language video data.

[0535] Specific operation: The generated text data "Hello" is sent to a sign language database, and the corresponding sign language video data is searched and retrieved.

[0536] Input: Converted text data

[0537] Output: Sign language video data

[0538] Step 5:

[0539] The generated sign language video data is transmitted to the terminal.

[0540] Specific operation: Sign language video data is transmitted to the terminal in real time via the network.

[0541] Input: Sign language video data

[0542] Output: Transmitted sign language video data

[0543] Step 6:

[0544] The sign language video data received by the device is displayed on the lenses of the smart glasses.

[0545] Specific operation: The device displays the received sign language video data on the smart glasses display for the user to see.

[0546] Input: Received sign language video data

[0547] Output: Sign language video displayed on smart glasses

[0548] Sign language to text conversion processing steps

[0549] Step 1:

[0550] When the user responds in sign language, the device's camera captures the sign movements in real time.

[0551] Specific actions: The user signs "thank you" and the action is recorded by the device's camera.

[0552] Input: User sign language gesture

[0553] Output: Captured sign language movement data

[0554] Step 2:

[0555] The captured sign language action data is sent to a server.

[0556] Specific actions: The recorded sign language action data is sent to a server via a network.

[0557] Input: Captured sign language movement data

[0558] Output: Transmitted sign language movement data

[0559] Step 3:

[0560] The server analyzes the received sign language movement data using a machine learning algorithm and generates corresponding text data.

[0561] Specific action: The transmitted sign language movement data is analyzed by a machine learning algorithm, and the text data "Thank you" is generated.

[0562] Input: Received sign language movement data

[0563] Output: Generated text data

[0564] Step 4:

[0565] The generated text data is sent to the terminal.

[0566] Specific operation: Text data is sent to the terminal via the network.

[0567] Input: Generated text data

[0568] Output: The text data sent

[0569] Step 5:

[0570] The text data received by the device is displayed on the lenses of the smart glasses.

[0571] Specific operation: The device displays the received text data on the smart glasses display for the other party to see.

[0572] Input: Received text data

[0573] Output: Text displayed on the smart glasses

[0574] Through the above processing steps, the system converts audio into sign language video and sign language actions into text, enabling users to communicate smoothly in real time.

[0575] (Application example 1)

[0576] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0577] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-speaking people in brick-and-mortar stores. In situations where a sign language interpreter is needed, it is difficult for hearing-impaired people to obtain information independently, and there are only a limited number of professional sign language interpreters, so there is a need for faster response. Another issue is that if store staff do not understand sign language, communication takes time, resulting in a decline in service quality.

[0578] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0579] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for referencing a database specialized in generating sign language video data, and means having an interface for supporting customer service in a real-world store. This enables fast and efficient communication between hearing-impaired people and hearing-controlling people in a real-world store through real-time mutual conversion of text, sign language, and voice.

[0580] A "means for capturing user voice" is a part of the system that captures voice in digital form using a microphone or other voice input device.

[0581] The "means for converting captured voice into text data" is a function that converts acquired voice data into corresponding text data using voice recognition technology.

[0582] The "means for converting text data into sign language video data" is a conversion system for visualizing text data as sign language video based on a sign language database.

[0583] "Means for displaying sign language video data" refers to a function that outputs the generated sign language video to a display device such as a display or smart glasses.

[0584] A "means for capturing a user's sign language movements" is a part of a system that uses a camera or other image capture device to capture sign language movements as digital data.

[0585] The "means for converting captured sign language actions into text data" is a function that converts acquired sign language actions into corresponding text data using machine learning algorithms or image analysis technology.

[0586] "Means for displaying text data" refers to a function that outputs the converted text data to a display device such as a display or smart glasses.

[0587] "Means for referencing a database specialized in generating sign language video data" is a function for referencing a specialized database that stores the data necessary to convert text data into corresponding sign language video.

[0588] "Means with an interface to support customer service in a real-world store" refers to part of a system that includes a user interface and operation panel to facilitate communication between customers and staff in a real-world store.

[0589] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-normal people in brick-and-mortar stores. Specifically, this system converts a user's voice into sign language video and sign language actions into text, and is implemented using a terminal and a server.

[0590] Audio to sign language video conversion

[0591] The server uses the device's microphone to capture the user's voice. The captured voice data is converted into text data using the speech recognition library "SpeechRecognition." This text data is then converted into sign language video data based on a sign language database. This conversion uses an API that references the sign language database and generates the corresponding sign language video. The generated sign language video data is sent to the device in real time and displayed as a sign language video on a display device such as smart glasses. This process allows the user to see what the other person is saying in sign language video.

[0592] For example, if the person you are talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," and then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the audio 'hello' into a sign language video."

[0593] Sign language to text conversion

[0594] When a user responds in sign language, the device's camera captures the sign language in real time. The captured sign language data is sent to a server, which analyzes it using the image analysis library "pytesseract" and machine learning algorithms. The resulting text data is sent back to the device and displayed on a display device such as smart glasses, allowing the other person to understand what the user is saying in sign language as text.

[0595] For example, if a user signs "thank you," the device's camera captures the action and sends it to the server. The server analyzes it and generates the text "thank you," which is then sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the sign language video into the text 'thank you'."

[0596] This will enable real-time communication between hearing-impaired and hearing-savvy customers in brick-and-mortar stores. The system integrates multiple technologies, including voice recognition, sign language video generation, and image analysis, to provide fast and efficient customer service.

[0597] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0598] Step 1:

[0599] The device captures the user's voice.

[0600] Input: User's voice data

[0601] Specific operation: The device's microphone captures the audio and converts it into digital audio data.

[0602] Output: Audio data

[0603] Step 2:

[0604] The server converts the voice data into text data.

[0605] Input: Audio data

[0606] Specific operation: The server uses a speech recognition library (SpeechRecognition) to convert the voice data into text data.

[0607] Output: Text data

[0608] Step 3:

[0609] The server converts the text data into sign language video data.

[0610] Input: Text data

[0611] Specific operation: The server references the sign language database and generates sign language video data corresponding to the text data. The sign language video generation API is used to obtain the sign language video data.

[0612] Output: Sign language video data

[0613] Step 4:

[0614] The device displays the sign language video data.

[0615] Input: Sign language video data

[0616] Specific operation: Display sign language videos on the device display or smart glasses, allowing users to watch sign language videos.

[0617] Output: Display of sign language video

[0618] Step 5:

[0619] The device captures the user's sign language actions.

[0620] Input: User's sign language actions

[0621] Specific operation: The device's camera captures sign language movements in real time and saves them as digital video data.

[0622] Output: Sign language video data

[0623] Step 6:

[0624] The server converts the sign language video data into text data.

[0625] Input: Sign language video data

[0626] Specific operation: The server uses an image analysis library (pytesseract) and a machine learning algorithm to convert sign language video data into text data.

[0627] Output: Text data

[0628] Step 7:

[0629] The terminal displays the text data.

[0630] Input: Text data

[0631] Specific operation: By displaying text data on the device display or smart glasses, the person you are speaking with can understand the content of the sign language.

[0632] Output: Display of text data

[0633] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0634] This invention relates to a communication support system that uses voice and sign language to enable smooth communication between hearing-impaired and hearing-normal people, and by combining it with an emotion engine that recognizes the user's emotional state, it achieves higher quality communication. The specific operation of the program for this system is explained below.

[0635] Program Overview

[0636] The system captures the user's voice and sign language actions, analyzes them, and converts them into corresponding sign language video and text data. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[0637] Audio to sign language video conversion

[0638] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm and an emotion engine. The text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0639] Specific examples

[0640] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, it retrieves the sign language video corresponding to "hello" from a sign language database and makes fine adjustments based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[0641] Sign language to text conversion

[0642] When a user responds in sign language, the device's camera captures the sign in real time. The captured movement data is sent to the server. The server then uses a machine learning algorithm and an emotion engine to analyze the sign data and generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the conversation partner to not only understand the user's sign language utterances as text, but also understand their emotional state.

[0643] Specific examples

[0644] For example, if a user sign "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[0645] In this way, the communication support system of the present invention not only converts speech to sign language and sign language to text, but also recognizes emotions using an emotion engine, thereby realizing richer communication.

[0646] The processing flow will be explained below.

[0647] Audio to sign language video conversion

[0648] Step 1:

[0649] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[0650] Step 2:

[0651] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0652] Step 3:

[0653] The server passes the received voice data through speech recognition software and converts it into text data using natural language processing algorithms.

[0654] Step 4:

[0655] The server passes the text data through an emotion engine to analyze the emotional state in the voice, generating text data with emotional information added.

[0656] Step 5:

[0657] The server compares the text data with a sign language database and extracts the corresponding sign language video data, and also performs fine-tuning based on emotional information.

[0658] Step 6:

[0659] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[0660] Step 7:

[0661] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing users to visually confirm the sign language video and its emotional information.

[0662] Sign language to text conversion

[0663] Step 1:

[0664] The user responds in sign language, and the device's camera captures this sign language action in real time.

[0665] Step 2:

[0666] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0667] Step 3:

[0668] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[0669] Step 4:

[0670] The server passes the sign language movement data through an emotion engine to analyze the emotional state of the sign language, and generates text data with emotional information added.

[0671] Step 5:

[0672] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[0673] Step 6:

[0674] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person speaking to see the meaning of the user's sign language and its emotional information as text.

[0675] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, enabling smooth communication that also includes emotional information.

[0676] Example 2

[0677] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0678] While existing communication support systems provide functions for converting speech to sign language and sign language to text for communication between hearing-impaired and hearing-disabled people, they have a problem in that they are unable to improve the quality of communication by taking into account the emotional state of the user.In addition, there is a lack of means to accurately recognize the emotional state and modify the sign language video based on that, which means that the nuances of actual conversation cannot be fully conveyed.

[0679] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0680] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing the user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing the user's emotional state from the captured voice and sign language actions, and means for modifying the sign language video data based on the emotional state. This enables conversion of the sign language video and text data that reflects the user's emotional state, making it possible to more accurately convey the nuances of actual conversation.

[0681] "User" refers to an individual or group that communicates using the System.

[0682] "Means for capturing audio" refers to a microphone or other audio input device for collecting the user's voice.

[0683] "Text data conversion means" refers to software or algorithms for converting speech or sign language into a corresponding text format.

[0684] "Means for converting into sign language video data" refers to software or algorithms for converting text data into a corresponding sign language video format.

[0685] "Means for displaying sign language video data" refers to a display device or projector for presenting the generated sign language video to a user.

[0686] "Means for capturing sign language actions" refers to a camera or other video input device for photographing or recording a user's sign language actions.

[0687] "Means for recognizing emotional state" refers to software or algorithms for analyzing and recognizing a user's emotions from speech or sign language actions.

[0688] "Means for modifying sign language video data based on emotional state" refers to software or algorithms that adjust or modify the generated sign language video based on recognized emotional information.

[0689] "Server" means a centralized computer system for processing and storing data.

[0690] "System" refers to the overall mechanism in which the above means operate in conjunction with each other.

[0691] This invention relates to a system that enables smooth communication between hearing-impaired and hearing-suffering people, and aims to deepen mutual understanding by using voice and sign language. Furthermore, by combining it with an emotion engine, it recognizes the user's emotional state and achieves higher quality communication.

[0692] Audio to sign language video conversion

[0693] The device captures the user's voice through a microphone. It then compresses the captured voice data and sends it to a server via the Internet. The server receives this voice data and converts it into text data using a natural language processing algorithm (e.g., Google Cloud Speech-to-Text API) and an emotion engine. The converted text data is then compared with a sign language database (e.g., Sign Language API) to generate corresponding sign language video data. This sign language video data is then fine-tuned by the emotion engine based on the user's emotional state. Finally, the generated sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0694] Sign language to text conversion

[0695] When a user responds in sign language, the device's camera (for example, Microsoft's Azure Kinect DK) captures the sign language in real time. The captured movement data is sent to a server, which analyzes it using machine learning algorithms (TensorFlow or PyTorch) and an emotion engine to generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the person speaking not only to understand the user's sign language utterances as text, but also to understand their emotional state.

[0696] Specific operation example

[0697] Audio to sign language video conversion example

[0698] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, the server retrieves the sign language video corresponding to "hello" from a sign language database and fine-tunes it based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[0699] Sign language to text example

[0700] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[0701] Example prompts to input to the generative AI model

[0702] An example of a prompt sentence that can be input to the generative AI model would be, "Please convert the content and emotion expressed by the user in sign language into text."

[0703] With the above-described configuration and processing, the present invention realizes smooth communication via voice and sign language, and further improves the quality of communication by taking emotional states into consideration.

[0704] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0705] Audio to sign language video conversion

[0706] Step 1:

[0707] A user initiates a conversation.

[0708] Input: Voice of the person you are talking to.

[0709] Action: The user says "Good morning" to the other person.

[0710] Output: Voice data of the conversation partner.

[0711] Step 2:

[0712] The device captures the audio.

[0713] Input: Voice data of the conversation partner.

[0714] How it works: The built-in microphone on your smartphone or dedicated device picks up sound.

[0715] Output: The captured audio data.

[0716] Step 3:

[0717] The device sends the captured audio to the server.

[0718] Input: Captured audio data.

[0719] How it works: The device compresses the audio data and sends it over the internet to a server using an HTTP POST request.

[0720] Output: The audio data sent to the server.

[0721] Step 4:

[0722] The server converts the speech to text.

[0723] Input: The audio data sent to the server.

[0724] How it works: The received audio data is converted to text using the Google Cloud Speech-to-Text API, with the emotion engine also analyzing the tone and pitch of the voice.

[0725] Output: The converted text data.

[0726] Step 5:

[0727] The server converts the text into sign language video.

[0728] Input: Converted text data and emotional information contained in the speech.

[0729] How it works: The text data is matched against a sign language database using the Sign Language API, and the corresponding sign language video data is generated.

[0730] Output: Generated sign language video data.

[0731] Step 6:

[0732] The server sends the sign language video to the device.

[0733] Input: Generated sign language video data.

[0734] How it works: The generated sign language video data is sent to the device in real time, again using an HTTP POST request.

[0735] Output: Sign language video data sent to the device.

[0736] Step 7:

[0737] The device displays the sign language video.

[0738] Input: Sign language video data sent to the device.

[0739] How it works: The device displays the received sign language video on the lenses of the smart glasses.

[0740] Output: Visualized sign language video data.

[0741] Sign language to text conversion

[0742] Step 1:

[0743] The user responds in sign language.

[0744] Input: A sign language response.

[0745] Action: For example, perform an action to express "thank you" in sign language.

[0746] Output: Beginning of sign language action.

[0747] Step 2:

[0748] The device captures the sign language gestures.

[0749] Input: Sign language actions.

[0750] Actions: Smart glasses and camera devices capture sign language actions in real time. Azure Kinect DK is used.

[0751] Output: Captured sign language data.

[0752] Step 3:

[0753] The terminal transmits the captured sign language data to the server.

[0754] Input: Captured sign language data.

[0755] How it works: The device compresses the captured sign language data and sends it over the internet to a server.

[0756] Output: Sign language data sent to the server.

[0757] Step 4:

[0758] The server converts the sign language data into text.

[0759] Input: Sign language data sent to the server.

[0760] How it works: The received sign language data is analyzed using TensorFlow or PyTorch, and the corresponding text data is generated. At the same time, the emotion engine also analyzes the emotions conveyed in the sign language.

[0761] Output: The converted text data.

[0762] Step 5:

[0763] The server transmits the generated text data to the terminal.

[0764] Input: Transformed text data and sentiment information.

[0765] Operation: The generated text data and emotion information are sent to the device in real time.

[0766] Output: Text data and emotion information sent to the device.

[0767] Step 6:

[0768] The terminal displays the text.

[0769] Input: Text data and emotional information sent to the device.

[0770] Operation: The device displays the received text data and emotional information on the lenses of the smart glasses.

[0771] Output: Visualized text data and sentiment information.

[0772] Through these specific processing steps, the system enables smooth, high-quality communication via voice and sign language.

[0773] (Application example 2)

[0774] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0775] Conventional communication support systems lack support for smooth communication between hearing-impaired and hearing-disabled people. Furthermore, the lack of emotion recognition can lead to a decline in the quality of communication. Furthermore, no sophisticated communication support using smart glasses is available in brick-and-mortar stores. To address these issues, the present invention aims to achieve higher quality communication by capturing voice and sign language movements, converting them into text data, and displaying sign language videos and text data, as well as using an emotion engine.

[0776] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0777] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing a user's emotional state and improving the quality of communication based on that information, and means for integrating the above means and supporting smooth communication using smart glasses in a physical store. This enables hearing-impaired and hearing-disabled people to understand each other's emotions and communicate smoothly in a physical store.

[0778] The "means for capturing the user's voice" is a device for picking up the voice emitted by the user and recording it as digital data.

[0779] The "means for converting captured audio into text data" refers to software or hardware for analyzing audio data and converting it into corresponding text format data.

[0780] The "means for converting text data into sign language animation data" is a process for generating animation of corresponding sign language actions based on the text data.

[0781] The "means for displaying sign language video data" refers to a display device for visually presenting the generated sign language video to the user.

[0782] The "means for capturing the user's sign language actions" is a device for capturing the user's sign language actions in real time and recording them as digital data.

[0783] The "means for converting the captured sign language actions into text data" refers to software or hardware for analyzing the sign language action data and converting it into corresponding text format data.

[0784] The "means for displaying text data" is a display device for visually presenting the converted text data to the user.

[0785] "Means for recognizing the user's emotional state and improving the quality of communication based on that information" refers to a system that analyzes the user's emotions from voice and sign language movement data, and provides appropriate responses and feedback based on that emotional information.

[0786] "Means for supporting smooth communication using smart glasses in physical stores" refers to devices and systems that use smart glasses in a physical store environment to enable users to communicate smoothly.

[0787] This invention is a system that supports smooth communication between hearing-impaired and hearing-savvy people in brick-and-mortar stores, and improves the quality of communication by converting and displaying speech and sign language using smart glasses, and by recognizing emotional states. This system is mainly composed of a server, a terminal (smart glasses), and user interaction.

[0788] Overall system configuration

[0789] The server captures the user's voice and sign language actions, analyzes them, and converts them into text data and sign language videos. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[0790] The device displays the sign language video and text data sent from the server in real time through the smart glasses, which are equipped with a microphone for capturing audio, a camera for capturing sign language movements, and a display device.

[0791] Program Overview

[0792] 1. Audio to Sign Language Video Conversion:

[0793] The server captures the user's voice through the device's microphone and converts it into text data. The generated text data is compared with a sign language video database to obtain the corresponding sign language video. An emotion engine is then used to add emotional information to the sign language video, which is then sent to the device. On the device side, the sign language video is displayed on the lenses of the smart glasses.

[0794] Examples:

[0795] For example, when a person with normal hearing says "Welcome," the microphone in the smart glasses captures the voice and sends it to the server. The server analyzes the voice and recognizes the text and the emotion contained in the voice. It then retrieves the corresponding sign language video from a sign language database and adjusts it based on the emotion information. This sign language video is then sent to the device and displayed on the smart glasses.

[0796] Example prompt sentence:

[0797] Voice input: "Welcome"

[0798] Sentiment Analysis: Joy

[0799] 2. Sign Language to Text Conversion:

[0800] When a user responds in sign language, the camera captures the sign in real time and sends it to the server. The server analyzes the sign and generates corresponding text data and emotion information. The generated text data and emotion information are sent to the device and displayed on the lens of the smart glasses.

[0801] Examples:

[0802] For example, if a user expresses "thank you" in sign language, the camera in the smart glasses captures the gesture and sends it to the server. The server analyzes it and recognizes the text data and the emotion of gratitude. This information is then sent to the device and displayed on the smart glasses.

[0803] Example prompt sentence:

[0804] Sign language input: "Thank you"

[0805] Sentiment Analysis: Gratitude

[0806] Hardware and software used

[0807] Hardware:

[0808] Smart glasses (e.g., AR glasses)

[0809] High-performance microphone

[0810] Cameras (e.g. smart glasses with high-resolution cameras)

[0811] software:

[0812] Natural language processing algorithms (e.g., speech recognition software)

[0813] Sentiment engines (e.g., sentiment analysis tools)

[0814] Sign language database (e.g., sign language conversion module)

[0815] Real-time image processing library (e.g. OpenCV)

[0816] This will enable hearing-impaired and hearing-sighted people to understand each other's emotions and communicate smoothly in physical stores.

[0817] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0818] Step 1:

[0819] The device's microphone captures the user's voice. The captured voice data is converted into digital format and sent to the server. The input is the user's voice, and the output is digital voice data.

[0820] Step 2:

[0821] The server analyzes the received voice data and converts it into text data using a natural language processing algorithm. At the same time, it also uses an emotion engine to extract emotions from the voice. The input is digital voice data, and the output is text data and emotional information.

[0822] Step 3:

[0823] The server compares the text data with a sign language database and retrieves the corresponding sign language video data. It then fine-tunes the sign language video based on the extracted emotional information. The input is text data and emotional information, and the output is fine-tuned sign language video data.

[0824] Step 4:

[0825] The server transmits the sign language video data to the device in real time. The device displays the received sign language video data on the smart glasses display. The input is finely adjusted sign language video data, and the output is the sign language video displayed on the smart glasses.

[0826] Step 5:

[0827] When a user responds in sign language, the device's camera captures the sign language in real time, converts it into digital format, and sends it to the server. The input is the user's sign language, and the output is digital sign language data.

[0828] Step 6:

[0829] The server analyzes the received sign language motion data and converts it into text data using a machine learning algorithm. At the same time, it also uses an emotion engine to extract emotions from the sign language motion data. The input is digital sign language motion data, and the output is text data and emotion information.

[0830] Step 7:

[0831] The server sends the generated text data and emotional information to the terminal in real time. The terminal displays the received text data and emotional information on the smart glasses display. The input is text data and emotional information, and the output is the text data and emotional information displayed on the smart glasses.

[0832] Through these processing steps, hearing-impaired and hearing-speaking people can communicate effectively and smoothly in physical stores while understanding emotions.

[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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0834] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

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

[0836] [Third embodiment]

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

[0838] 5, the data processing system 310 includes the 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 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0841] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

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

[0843] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0844] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0847] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0849] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. The specific operation of the program for this system is explained below.

[0850] Program Overview

[0851] This system is mainly composed of a terminal and a server, each of which functions according to its own role. In particular, the terminal captures voice and sign language, and the server analyzes and converts them.

[0852] Audio to sign language video conversion

[0853] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm. This text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0854] Specific examples

[0855] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lenses of the smart glasses. In this way, the user can understand what the other person is saying by watching the sign language video of "hello."

[0856] Sign language to text conversion

[0857] When a user responds in sign language, the device's camera captures the sign in real time. The captured data is sent to a server, which uses a machine learning algorithm to analyze the sign and generate corresponding text data. This text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand what the user is saying in sign language as text.

[0858] Specific examples

[0859] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[0860] In this way, the communication support system of the present invention realizes smooth communication between hearing-impaired and hearing-normal people by converting speech to sign language and sign language to text in real time.

[0861] The processing flow will be explained below.

[0862] Audio to sign language video conversion

[0863] Step 1:

[0864] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[0865] Step 2:

[0866] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0867] Step 3:

[0868] The server then passes the received voice data through speech recognition software to convert it into text, using natural language processing algorithms to accurately convert the speech into text.

[0869] Step 4:

[0870] The server compares the text data with a sign language database and extracts the corresponding sign language video data.

[0871] Step 5:

[0872] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[0873] Step 6:

[0874] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing the user to visually confirm the sign language video.

[0875] Sign language to text conversion

[0876] Step 1:

[0877] The user responds in sign language, and the device's camera captures this sign language action in real time.

[0878] Step 2:

[0879] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[0880] Step 3:

[0881] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[0882] Step 4:

[0883] The server generates text data based on the analysis results, accurately converting the meaning of the sign language into text.

[0884] Step 5:

[0885] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[0886] Step 6:

[0887] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person you are talking to to see the meaning of your sign language as text.

[0888] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, ensuring smooth communication.

[0889] Example 1

[0890] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0891] Conventional communication support systems have had the problem of making it difficult for hearing-impaired people and hearing-savvy people who do not know sign language to communicate smoothly. In particular, the lack of technology to convert speech into sign language in real time and sign language into text in real time makes rapid communication difficult.

[0892] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0893] In this invention, the server includes means for converting received voice data into text data, means for converting the text data into sign language video data based on a sign language database, and means for converting received sign language action data into text data, thereby making it possible to convert voice into sign language video in real time and sign language actions into text in real time.

[0894] "User" refers to a person who uses the system to convert audio into sign language video or sign language actions into text.

[0895] "Audio capture means" refers to a device such as a microphone for recording the user's voice.

[0896] "Audio compression means" refers to a technique for compressing recorded audio data to reduce the data size.

[0897] "Transmission means" refers to the communication technology used to transmit compressed audio data and captured sign language movement data to the server.

[0898] A "server" refers to a computer system or software that analyzes and converts received data.

[0899] "Natural language processing algorithm" refers to an algorithm for analyzing voice data and converting it into text data.

[0900] "Sign language database" refers to a database that stores sign language information for converting text data into corresponding sign language video.

[0901] "Sign language video generation means" refers to a technology that converts text data into sign language video data based on a sign language database.

[0902] "Sign language video display means" refers to technology for displaying the generated sign language video data on smart glasses, displays, etc.

[0903] The "sign language action capture means" refers to a device such as a camera for recording a user's sign language actions in real time.

[0904] "Machine learning algorithm" refers to an algorithm for analyzing received sign language movement data and converting it into text data.

[0905] "Text display means" refers to technology for displaying converted text data on smart glasses, displays, etc.

[0906] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. This system consists of a terminal and a server, each of which plays a different role.

[0907] Audio to sign language video conversion

[0908] When a user begins a conversation, the device uses a microphone to capture audio. The captured audio data is compressed and sent to a server. The server then converts the received audio data into text data using a natural language processing algorithm. This text data is compared with a sign language database, and corresponding sign language video data is generated. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lenses of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[0909] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lens of the smart glasses. In this way, the user can visually confirm the sign language video of "hello."

[0910] Sign language to text conversion

[0911] When the user responds in sign language, the device's camera captures the sign language movements in real time. The captured movement data is sent to a server. The server uses a machine learning algorithm to analyze the sign language movement data and generate corresponding text data. The generated text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand the user's sign language as text.

[0912] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[0913] Specific examples

[0914] Example prompt sentence:

[0915] Please translate and explain the following sentences in natural Japanese. Please make sure the subject is either server, terminal, or user. Please use the plain voice (da / dearu style) for endings.

[0916] ---

[0917] {Technical explanation of how the system works}

[0918] ---

[0919] This system is a communication support system designed for use by users, converting audio to sign language video and sign language to text in real time.

[0920] In this way, the communication support system of the present invention realizes smooth communication between the hearing impaired and the hearing-impaired by converting speech to sign language and sign language to text in real time.

[0921] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0922] Processing steps for audio to sign language video conversion

[0923] Step 1:

[0924] The device uses a microphone to capture the user's voice.

[0925] Specific operation: The user says "Hello" and the voice is recorded by the device's microphone.

[0926] Input: User's voice

[0927] Output: Captured audio data

[0928] Step 2:

[0929] The captured audio data is compressed and sent to the server.

[0930] Specific operation: The recorded audio data is reduced in size using a data compression algorithm and sent over the network to a server.

[0931] Input: Captured audio data

[0932] Output: Compressed audio data

[0933] Step 3:

[0934] The server converts the received voice data into text data using a natural language processing algorithm.

[0935] Specific operation: The compressed voice data is decompressed and converted into the text data "Hello" using a voice recognition algorithm.

[0936] Input: Compressed audio data

[0937] Output: Converted text data

[0938] Step 4:

[0939] The server compares the generated text data with a sign language database and generates corresponding sign language video data.

[0940] Specific operation: The generated text data "Hello" is sent to a sign language database, and the corresponding sign language video data is searched and retrieved.

[0941] Input: Converted text data

[0942] Output: Sign language video data

[0943] Step 5:

[0944] The generated sign language video data is transmitted to the terminal.

[0945] Specific operation: Sign language video data is transmitted to the terminal in real time via the network.

[0946] Input: Sign language video data

[0947] Output: Transmitted sign language video data

[0948] Step 6:

[0949] The sign language video data received by the device is displayed on the lenses of the smart glasses.

[0950] Specific operation: The device displays the received sign language video data on the smart glasses display for the user to see.

[0951] Input: Received sign language video data

[0952] Output: Sign language video displayed on smart glasses

[0953] Sign language to text conversion processing steps

[0954] Step 1:

[0955] When the user responds in sign language, the device's camera captures the sign movements in real time.

[0956] Specific actions: The user signs "thank you" and the action is recorded by the device's camera.

[0957] Input: User sign language gesture

[0958] Output: Captured sign language movement data

[0959] Step 2:

[0960] The captured sign language action data is sent to a server.

[0961] Specific actions: The recorded sign language action data is sent to a server via a network.

[0962] Input: Captured sign language movement data

[0963] Output: Transmitted sign language movement data

[0964] Step 3:

[0965] The server analyzes the received sign language movement data using a machine learning algorithm and generates corresponding text data.

[0966] Specific action: The transmitted sign language movement data is analyzed by a machine learning algorithm, and the text data "Thank you" is generated.

[0967] Input: Received sign language movement data

[0968] Output: Generated text data

[0969] Step 4:

[0970] The generated text data is sent to the terminal.

[0971] Specific operation: Text data is sent to the terminal via the network.

[0972] Input: Generated text data

[0973] Output: The text data sent

[0974] Step 5:

[0975] The text data received by the device is displayed on the lenses of the smart glasses.

[0976] Specific operation: The device displays the received text data on the smart glasses display for the other party to see.

[0977] Input: Received text data

[0978] Output: Text displayed on the smart glasses

[0979] Through the above processing steps, the system converts audio into sign language video and sign language actions into text, enabling users to communicate smoothly in real time.

[0980] (Application example 1)

[0981] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0982] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-speaking people in brick-and-mortar stores. In situations where a sign language interpreter is needed, it is difficult for hearing-impaired people to obtain information independently, and there are only a limited number of professional sign language interpreters, so there is a need for faster response. Another issue is that if store staff do not understand sign language, communication takes time, resulting in a decline in service quality.

[0983] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0984] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for referencing a database specialized in generating sign language video data, and means having an interface for supporting customer service in a real-world store. This enables fast and efficient communication between hearing-impaired people and hearing-controlling people in a real-world store through real-time mutual conversion of text, sign language, and voice.

[0985] A "means for capturing user voice" is a part of the system that captures voice in digital form using a microphone or other voice input device.

[0986] The "means for converting captured voice into text data" is a function that converts acquired voice data into corresponding text data using voice recognition technology.

[0987] The "means for converting text data into sign language video data" is a conversion system for visualizing text data as sign language video based on a sign language database.

[0988] "Means for displaying sign language video data" refers to a function that outputs the generated sign language video to a display device such as a display or smart glasses.

[0989] A "means for capturing a user's sign language movements" is a part of a system that uses a camera or other image capture device to capture sign language movements as digital data.

[0990] The "means for converting captured sign language actions into text data" is a function that converts acquired sign language actions into corresponding text data using machine learning algorithms or image analysis technology.

[0991] "Means for displaying text data" refers to a function that outputs the converted text data to a display device such as a display or smart glasses.

[0992] "Means for referencing a database specialized in generating sign language video data" is a function for referencing a specialized database that stores the data necessary to convert text data into corresponding sign language video.

[0993] "Means with an interface to support customer service in a real-world store" refers to part of a system that includes a user interface and operation panel to facilitate communication between customers and staff in a real-world store.

[0994] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-normal people in brick-and-mortar stores. Specifically, this system converts a user's voice into sign language video and sign language actions into text, and is implemented using a terminal and a server.

[0995] Audio to sign language video conversion

[0996] The server uses the device's microphone to capture the user's voice. The captured voice data is converted into text data using the speech recognition library "SpeechRecognition." This text data is then converted into sign language video data based on a sign language database. This conversion uses an API that references the sign language database and generates the corresponding sign language video. The generated sign language video data is sent to the device in real time and displayed as a sign language video on a display device such as smart glasses. This process allows the user to see what the other person is saying in sign language video.

[0997] For example, if the person you are talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," and then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the audio 'hello' into a sign language video."

[0998] Sign language to text conversion

[0999] When a user responds in sign language, the device's camera captures the sign language in real time. The captured sign language data is sent to a server, which analyzes it using the image analysis library "pytesseract" and machine learning algorithms. The resulting text data is sent back to the device and displayed on a display device such as smart glasses, allowing the other person to understand what the user is saying in sign language as text.

[1000] For example, if a user signs "thank you," the device's camera captures the action and sends it to the server. The server analyzes it and generates the text "thank you," which is then sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the sign language video into the text 'thank you'."

[1001] This will enable real-time communication between hearing-impaired and hearing-savvy customers in brick-and-mortar stores. The system integrates multiple technologies, including voice recognition, sign language video generation, and image analysis, to provide fast and efficient customer service.

[1002] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1003] Step 1:

[1004] The device captures the user's voice.

[1005] Input: User's voice data

[1006] Specific operation: The device's microphone captures the audio and converts it into digital audio data.

[1007] Output: Audio data

[1008] Step 2:

[1009] The server converts the voice data into text data.

[1010] Input: Audio data

[1011] Specific operation: The server uses a speech recognition library (SpeechRecognition) to convert the voice data into text data.

[1012] Output: Text data

[1013] Step 3:

[1014] The server converts the text data into sign language video data.

[1015] Input: Text data

[1016] Specific operation: The server references the sign language database and generates sign language video data corresponding to the text data. The sign language video generation API is used to obtain the sign language video data.

[1017] Output: Sign language video data

[1018] Step 4:

[1019] The device displays the sign language video data.

[1020] Input: Sign language video data

[1021] Specific operation: Display sign language videos on the device display or smart glasses, allowing users to watch sign language videos.

[1022] Output: Display of sign language video

[1023] Step 5:

[1024] The device captures the user's sign language actions.

[1025] Input: User's sign language actions

[1026] Specific operation: The device's camera captures sign language movements in real time and saves them as digital video data.

[1027] Output: Sign language video data

[1028] Step 6:

[1029] The server converts the sign language video data into text data.

[1030] Input: Sign language video data

[1031] Specific operation: The server uses an image analysis library (pytesseract) and a machine learning algorithm to convert sign language video data into text data.

[1032] Output: Text data

[1033] Step 7:

[1034] The terminal displays the text data.

[1035] Input: Text data

[1036] Specific operation: By displaying text data on the device display or smart glasses, the person you are speaking with can understand the content of the sign language.

[1037] Output: Display of text data

[1038] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1039] This invention relates to a communication support system that uses voice and sign language to enable smooth communication between hearing-impaired and hearing-normal people, and by combining it with an emotion engine that recognizes the user's emotional state, it achieves higher quality communication. The specific operation of the program for this system is explained below.

[1040] Program Overview

[1041] The system captures the user's voice and sign language actions, analyzes them, and converts them into corresponding sign language video and text data. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[1042] Audio to sign language video conversion

[1043] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm and an emotion engine. The text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[1044] Specific examples

[1045] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, it retrieves the sign language video corresponding to "hello" from a sign language database and makes fine adjustments based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[1046] Sign language to text conversion

[1047] When a user responds in sign language, the device's camera captures the sign in real time. The captured movement data is sent to the server. The server then uses a machine learning algorithm and an emotion engine to analyze the sign data and generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the conversation partner to not only understand the user's sign language utterances as text, but also understand their emotional state.

[1048] Specific examples

[1049] For example, if a user sign "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[1050] In this way, the communication support system of the present invention not only converts speech to sign language and sign language to text, but also recognizes emotions using an emotion engine, thereby realizing richer communication.

[1051] The processing flow will be explained below.

[1052] Audio to sign language video conversion

[1053] Step 1:

[1054] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[1055] Step 2:

[1056] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[1057] Step 3:

[1058] The server passes the received voice data through speech recognition software and converts it into text data using natural language processing algorithms.

[1059] Step 4:

[1060] The server passes the text data through an emotion engine to analyze the emotional state in the voice, generating text data with emotional information added.

[1061] Step 5:

[1062] The server compares the text data with a sign language database and extracts the corresponding sign language video data, and also performs fine-tuning based on emotional information.

[1063] Step 6:

[1064] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[1065] Step 7:

[1066] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing users to visually confirm the sign language video and its emotional information.

[1067] Sign language to text conversion

[1068] Step 1:

[1069] The user responds in sign language, and the device's camera captures this sign language action in real time.

[1070] Step 2:

[1071] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[1072] Step 3:

[1073] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[1074] Step 4:

[1075] The server passes the sign language movement data through an emotion engine to analyze the emotional state of the sign language, and generates text data with emotional information added.

[1076] Step 5:

[1077] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[1078] Step 6:

[1079] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person speaking to see the meaning of the user's sign language and its emotional information as text.

[1080] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, enabling smooth communication that also includes emotional information.

[1081] Example 2

[1082] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1083] While existing communication support systems provide functions for converting speech to sign language and sign language to text for communication between hearing-impaired and hearing-disabled people, they have a problem in that they are unable to improve the quality of communication by taking into account the emotional state of the user.In addition, there is a lack of means to accurately recognize the emotional state and modify the sign language video based on that, which means that the nuances of actual conversation cannot be fully conveyed.

[1084] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1085] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing the user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing the user's emotional state from the captured voice and sign language actions, and means for modifying the sign language video data based on the emotional state. This enables conversion of the sign language video and text data that reflects the user's emotional state, making it possible to more accurately convey the nuances of actual conversation.

[1086] "User" refers to an individual or group that communicates using the System.

[1087] "Means for capturing audio" refers to a microphone or other audio input device for collecting the user's voice.

[1088] "Text data conversion means" refers to software or algorithms for converting speech or sign language into a corresponding text format.

[1089] "Means for converting into sign language video data" refers to software or algorithms for converting text data into a corresponding sign language video format.

[1090] "Means for displaying sign language video data" refers to a display device or projector for presenting the generated sign language video to a user.

[1091] "Means for capturing sign language actions" refers to a camera or other video input device for photographing or recording a user's sign language actions.

[1092] "Means for recognizing emotional state" refers to software or algorithms for analyzing and recognizing a user's emotions from speech or sign language actions.

[1093] "Means for modifying sign language video data based on emotional state" refers to software or algorithms that adjust or modify the generated sign language video based on recognized emotional information.

[1094] "Server" means a centralized computer system for processing and storing data.

[1095] "System" refers to the overall mechanism in which the above means operate in conjunction with each other.

[1096] This invention relates to a system that enables smooth communication between hearing-impaired and hearing-suffering people, and aims to deepen mutual understanding by using voice and sign language. Furthermore, by combining it with an emotion engine, it recognizes the user's emotional state and achieves higher quality communication.

[1097] Audio to sign language video conversion

[1098] The device captures the user's voice through a microphone. It then compresses the captured voice data and sends it to a server via the Internet. The server receives this voice data and converts it into text data using a natural language processing algorithm (e.g., Google Cloud Speech-to-Text API) and an emotion engine. The converted text data is then compared with a sign language database (e.g., Sign Language API) to generate corresponding sign language video data. This sign language video data is then fine-tuned by the emotion engine based on the user's emotional state. Finally, the generated sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[1099] Sign language to text conversion

[1100] When a user responds in sign language, the device's camera (for example, Microsoft's Azure Kinect DK) captures the sign language in real time. The captured movement data is sent to a server, which analyzes it using machine learning algorithms (TensorFlow or PyTorch) and an emotion engine to generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the person speaking not only to understand the user's sign language utterances as text, but also to understand their emotional state.

[1101] Specific operation example

[1102] Audio to sign language video conversion example

[1103] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, the server retrieves the sign language video corresponding to "hello" from a sign language database and fine-tunes it based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[1104] Sign language to text example

[1105] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[1106] Example prompts to input to the generative AI model

[1107] An example of a prompt sentence that can be input to the generative AI model would be, "Please convert the content and emotion expressed by the user in sign language into text."

[1108] With the above-described configuration and processing, the present invention realizes smooth communication via voice and sign language, and further improves the quality of communication by taking emotional states into consideration.

[1109] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1110] Audio to sign language video conversion

[1111] Step 1:

[1112] A user initiates a conversation.

[1113] Input: Voice of the person you are talking to.

[1114] Action: The user says "Good morning" to the other person.

[1115] Output: Voice data of the conversation partner.

[1116] Step 2:

[1117] The device captures the audio.

[1118] Input: Voice data of the conversation partner.

[1119] How it works: The built-in microphone on your smartphone or dedicated device picks up sound.

[1120] Output: The captured audio data.

[1121] Step 3:

[1122] The device sends the captured audio to the server.

[1123] Input: Captured audio data.

[1124] How it works: The device compresses the audio data and sends it over the internet to a server using an HTTP POST request.

[1125] Output: The audio data sent to the server.

[1126] Step 4:

[1127] The server converts the speech to text.

[1128] Input: The audio data sent to the server.

[1129] How it works: The received audio data is converted to text using the Google Cloud Speech-to-Text API, with the emotion engine also analyzing the tone and pitch of the voice.

[1130] Output: The converted text data.

[1131] Step 5:

[1132] The server converts the text into sign language video.

[1133] Input: Converted text data and emotional information contained in the speech.

[1134] How it works: The text data is matched against a sign language database using the Sign Language API, and the corresponding sign language video data is generated.

[1135] Output: Generated sign language video data.

[1136] Step 6:

[1137] The server sends the sign language video to the device.

[1138] Input: Generated sign language video data.

[1139] How it works: The generated sign language video data is sent to the device in real time, again using an HTTP POST request.

[1140] Output: Sign language video data sent to the device.

[1141] Step 7:

[1142] The device displays the sign language video.

[1143] Input: Sign language video data sent to the device.

[1144] How it works: The device displays the received sign language video on the lenses of the smart glasses.

[1145] Output: Visualized sign language video data.

[1146] Sign language to text conversion

[1147] Step 1:

[1148] The user responds in sign language.

[1149] Input: A sign language response.

[1150] Action: For example, perform an action to express "thank you" in sign language.

[1151] Output: Beginning of sign language action.

[1152] Step 2:

[1153] The device captures the sign language gestures.

[1154] Input: Sign language actions.

[1155] Actions: Smart glasses and camera devices capture sign language actions in real time. Azure Kinect DK is used.

[1156] Output: Captured sign language data.

[1157] Step 3:

[1158] The terminal transmits the captured sign language data to the server.

[1159] Input: Captured sign language data.

[1160] How it works: The device compresses the captured sign language data and sends it over the internet to a server.

[1161] Output: Sign language data sent to the server.

[1162] Step 4:

[1163] The server converts the sign language data into text.

[1164] Input: Sign language data sent to the server.

[1165] How it works: The received sign language data is analyzed using TensorFlow or PyTorch, and the corresponding text data is generated. At the same time, the emotion engine also analyzes the emotions conveyed in the sign language.

[1166] Output: The converted text data.

[1167] Step 5:

[1168] The server transmits the generated text data to the terminal.

[1169] Input: Transformed text data and sentiment information.

[1170] Operation: The generated text data and emotion information are sent to the device in real time.

[1171] Output: Text data and emotion information sent to the device.

[1172] Step 6:

[1173] The terminal displays the text.

[1174] Input: Text data and emotional information sent to the device.

[1175] Operation: The device displays the received text data and emotional information on the lenses of the smart glasses.

[1176] Output: Visualized text data and sentiment information.

[1177] Through these specific processing steps, the system enables smooth, high-quality communication via voice and sign language.

[1178] (Application example 2)

[1179] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1180] Conventional communication support systems lack support for smooth communication between hearing-impaired and hearing-disabled people. Furthermore, the lack of emotion recognition can lead to a decline in the quality of communication. Furthermore, no sophisticated communication support using smart glasses is available in brick-and-mortar stores. To address these issues, the present invention aims to achieve higher quality communication by capturing voice and sign language movements, converting them into text data, and displaying sign language videos and text data, as well as using an emotion engine.

[1181] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1182] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing a user's emotional state and improving the quality of communication based on that information, and means for integrating the above means and supporting smooth communication using smart glasses in a physical store. This enables hearing-impaired and hearing-disabled people to understand each other's emotions and communicate smoothly in a physical store.

[1183] The "means for capturing the user's voice" is a device for picking up the voice emitted by the user and recording it as digital data.

[1184] The "means for converting captured audio into text data" refers to software or hardware for analyzing audio data and converting it into corresponding text format data.

[1185] The "means for converting text data into sign language animation data" is a process for generating animation of corresponding sign language actions based on the text data.

[1186] The "means for displaying sign language video data" refers to a display device for visually presenting the generated sign language video to the user.

[1187] The "means for capturing the user's sign language actions" is a device for capturing the user's sign language actions in real time and recording them as digital data.

[1188] The "means for converting the captured sign language actions into text data" refers to software or hardware for analyzing the sign language action data and converting it into corresponding text format data.

[1189] The "means for displaying text data" is a display device for visually presenting the converted text data to the user.

[1190] "Means for recognizing the user's emotional state and improving the quality of communication based on that information" refers to a system that analyzes the user's emotions from voice and sign language movement data, and provides appropriate responses and feedback based on that emotional information.

[1191] "Means for supporting smooth communication using smart glasses in physical stores" refers to devices and systems that use smart glasses in a physical store environment to enable users to communicate smoothly.

[1192] This invention is a system that supports smooth communication between hearing-impaired and hearing-savvy people in brick-and-mortar stores, and improves the quality of communication by converting and displaying speech and sign language using smart glasses, and by recognizing emotional states. This system is mainly composed of a server, a terminal (smart glasses), and user interaction.

[1193] Overall system configuration

[1194] The server captures the user's voice and sign language actions, analyzes them, and converts them into text data and sign language videos. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[1195] The device displays the sign language video and text data sent from the server in real time through the smart glasses, which are equipped with a microphone for capturing audio, a camera for capturing sign language movements, and a display device.

[1196] Program Overview

[1197] 1. Audio to Sign Language Video Conversion:

[1198] The server captures the user's voice through the device's microphone and converts it into text data. The generated text data is compared with a sign language video database to obtain the corresponding sign language video. An emotion engine is then used to add emotional information to the sign language video, which is then sent to the device. On the device side, the sign language video is displayed on the lenses of the smart glasses.

[1199] Examples:

[1200] For example, when a person with normal hearing says "Welcome," the microphone in the smart glasses captures the voice and sends it to the server. The server analyzes the voice and recognizes the text and the emotion contained in the voice. It then retrieves the corresponding sign language video from a sign language database and adjusts it based on the emotion information. This sign language video is then sent to the device and displayed on the smart glasses.

[1201] Example prompt sentence:

[1202] Voice input: "Welcome"

[1203] Sentiment Analysis: Joy

[1204] 2. Sign Language to Text Conversion:

[1205] When a user responds in sign language, the camera captures the sign in real time and sends it to the server. The server analyzes the sign and generates corresponding text data and emotion information. The generated text data and emotion information are sent to the device and displayed on the lens of the smart glasses.

[1206] Examples:

[1207] For example, if a user expresses "thank you" in sign language, the camera in the smart glasses captures the gesture and sends it to the server. The server analyzes it and recognizes the text data and the emotion of gratitude. This information is then sent to the device and displayed on the smart glasses.

[1208] Example prompt sentence:

[1209] Sign language input: "Thank you"

[1210] Sentiment Analysis: Gratitude

[1211] Hardware and software used

[1212] Hardware:

[1213] Smart glasses (e.g., AR glasses)

[1214] High-performance microphone

[1215] Cameras (e.g. smart glasses with high-resolution cameras)

[1216] software:

[1217] Natural language processing algorithms (e.g., speech recognition software)

[1218] Sentiment engines (e.g., sentiment analysis tools)

[1219] Sign language database (e.g., sign language conversion module)

[1220] Real-time image processing library (e.g. OpenCV)

[1221] This will enable hearing-impaired and hearing-sighted people to understand each other's emotions and communicate smoothly in physical stores.

[1222] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1223] Step 1:

[1224] The device's microphone captures the user's voice. The captured voice data is converted into digital format and sent to the server. The input is the user's voice, and the output is digital voice data.

[1225] Step 2:

[1226] The server analyzes the received voice data and converts it into text data using a natural language processing algorithm. At the same time, it also uses an emotion engine to extract emotions from the voice. The input is digital voice data, and the output is text data and emotional information.

[1227] Step 3:

[1228] The server compares the text data with a sign language database and retrieves the corresponding sign language video data. It then fine-tunes the sign language video based on the extracted emotional information. The input is text data and emotional information, and the output is fine-tuned sign language video data.

[1229] Step 4:

[1230] The server transmits the sign language video data to the device in real time. The device displays the received sign language video data on the smart glasses display. The input is finely adjusted sign language video data, and the output is the sign language video displayed on the smart glasses.

[1231] Step 5:

[1232] When a user responds in sign language, the device's camera captures the sign language in real time, converts it into digital format, and sends it to the server. The input is the user's sign language, and the output is digital sign language data.

[1233] Step 6:

[1234] The server analyzes the received sign language motion data and converts it into text data using a machine learning algorithm. At the same time, it also uses an emotion engine to extract emotions from the sign language motion data. The input is digital sign language motion data, and the output is text data and emotion information.

[1235] Step 7:

[1236] The server sends the generated text data and emotional information to the terminal in real time. The terminal displays the received text data and emotional information on the smart glasses display. The input is text data and emotional information, and the output is the text data and emotional information displayed on the smart glasses.

[1237] Through these processing steps, hearing-impaired and hearing-speaking people can communicate effectively and smoothly in physical stores while understanding emotions.

[1238] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1239] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1240] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1241] [Fourth embodiment]

[1242] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1243] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1244] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1245] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1246] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1247] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1248] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1249] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1250] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1251] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1252] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1253] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1254] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1255] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. The specific operation of the program for this system is explained below.

[1256] Program Overview

[1257] This system is mainly composed of a terminal and a server, each of which functions according to its own role. In particular, the terminal captures voice and sign language, and the server analyzes and converts them.

[1258] Audio to sign language video conversion

[1259] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm. This text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[1260] Specific examples

[1261] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lenses of the smart glasses. In this way, the user can understand what the other person is saying by watching the sign language video of "hello."

[1262] Sign language to text conversion

[1263] When a user responds in sign language, the device's camera captures the sign in real time. The captured data is sent to a server, which uses a machine learning algorithm to analyze the sign and generate corresponding text data. This text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand what the user is saying in sign language as text.

[1264] Specific examples

[1265] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[1266] In this way, the communication support system of the present invention realizes smooth communication between hearing-impaired and hearing-normal people by converting speech to sign language and sign language to text in real time.

[1267] The processing flow will be explained below.

[1268] Audio to sign language video conversion

[1269] Step 1:

[1270] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[1271] Step 2:

[1272] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[1273] Step 3:

[1274] The server then passes the received voice data through speech recognition software to convert it into text, using natural language processing algorithms to accurately convert the speech into text.

[1275] Step 4:

[1276] The server compares the text data with a sign language database and extracts the corresponding sign language video data.

[1277] Step 5:

[1278] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[1279] Step 6:

[1280] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing the user to visually confirm the sign language video.

[1281] Sign language to text conversion

[1282] Step 1:

[1283] The user responds in sign language, and the device's camera captures this sign language action in real time.

[1284] Step 2:

[1285] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[1286] Step 3:

[1287] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[1288] Step 4:

[1289] The server generates text data based on the analysis results, accurately converting the meaning of the sign language into text.

[1290] Step 5:

[1291] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[1292] Step 6:

[1293] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person you are talking to to see the meaning of your sign language as text.

[1294] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, ensuring smooth communication.

[1295] Example 1

[1296] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1297] Conventional communication support systems have had the problem of making it difficult for hearing-impaired people and hearing-savvy people who do not know sign language to communicate smoothly. In particular, the lack of technology to convert speech into sign language in real time and sign language into text in real time makes rapid communication difficult.

[1298] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1299] In this invention, the server includes means for converting received voice data into text data, means for converting the text data into sign language video data based on a sign language database, and means for converting received sign language action data into text data, thereby making it possible to convert voice into sign language video in real time and sign language actions into text in real time.

[1300] "User" refers to a person who uses the system to convert audio into sign language video or sign language actions into text.

[1301] "Audio capture means" refers to a device such as a microphone for recording the user's voice.

[1302] "Audio compression means" refers to a technique for compressing recorded audio data to reduce the data size.

[1303] "Transmission means" refers to the communication technology used to transmit compressed audio data and captured sign language movement data to the server.

[1304] A "server" refers to a computer system or software that analyzes and converts received data.

[1305] "Natural language processing algorithm" refers to an algorithm for analyzing voice data and converting it into text data.

[1306] "Sign language database" refers to a database that stores sign language information for converting text data into corresponding sign language video.

[1307] "Sign language video generation means" refers to a technology that converts text data into sign language video data based on a sign language database.

[1308] "Sign language video display means" refers to technology for displaying the generated sign language video data on smart glasses, displays, etc.

[1309] The "sign language action capture means" refers to a device such as a camera for recording a user's sign language actions in real time.

[1310] "Machine learning algorithm" refers to an algorithm for analyzing received sign language movement data and converting it into text data.

[1311] "Text display means" refers to technology for displaying converted text data on smart glasses, displays, etc.

[1312] This invention is a communication support system that enables smooth communication between hearing-impaired people and hearing-savvy people who do not know sign language by converting the user's voice into sign language video and converting sign language actions into text. This system consists of a terminal and a server, each of which plays a different role.

[1313] Audio to sign language video conversion

[1314] When a user begins a conversation, the device uses a microphone to capture audio. The captured audio data is compressed and sent to a server. The server then converts the received audio data into text data using a natural language processing algorithm. This text data is compared with a sign language database, and corresponding sign language video data is generated. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lenses of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[1315] For example, if the person you're talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the lens of the smart glasses. In this way, the user can visually confirm the sign language video of "hello."

[1316] Sign language to text conversion

[1317] When the user responds in sign language, the device's camera captures the sign language movements in real time. The captured movement data is sent to a server. The server uses a machine learning algorithm to analyze the sign language movement data and generate corresponding text data. The generated text data is then sent back to the device and displayed on the lenses of the smart glasses. This allows the person speaking to understand the user's sign language as text.

[1318] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and generates the text "thank you." This text is sent to the device and displayed on the lens of the smart glasses. This allows the person you're talking to to read the text.

[1319] Specific examples

[1320] Example prompt sentence:

[1321] Please translate and explain the following sentences in natural Japanese. Please make sure the subject is either server, terminal, or user. Please use the plain voice (da / dearu style) for endings.

[1322] ---

[1323] {Technical explanation of how the system works}

[1324] ---

[1325] This system is a communication support system designed for use by users, converting audio to sign language video and sign language to text in real time.

[1326] In this way, the communication support system of the present invention realizes smooth communication between the hearing impaired and the hearing-impaired by converting speech to sign language and sign language to text in real time.

[1327] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1328] Processing steps for audio to sign language video conversion

[1329] Step 1:

[1330] The device uses a microphone to capture the user's voice.

[1331] Specific operation: The user says "Hello" and the voice is recorded by the device's microphone.

[1332] Input: User's voice

[1333] Output: Captured audio data

[1334] Step 2:

[1335] The captured audio data is compressed and sent to the server.

[1336] Specific operation: The recorded audio data is reduced in size using a data compression algorithm and sent over the network to a server.

[1337] Input: Captured audio data

[1338] Output: Compressed audio data

[1339] Step 3:

[1340] The server converts the received voice data into text data using a natural language processing algorithm.

[1341] Specific operation: The compressed voice data is decompressed and converted into the text data "Hello" using a voice recognition algorithm.

[1342] Input: Compressed audio data

[1343] Output: Converted text data

[1344] Step 4:

[1345] The server compares the generated text data with a sign language database and generates corresponding sign language video data.

[1346] Specific operation: The generated text data "Hello" is sent to a sign language database, and the corresponding sign language video data is searched and retrieved.

[1347] Input: Converted text data

[1348] Output: Sign language video data

[1349] Step 5:

[1350] The generated sign language video data is transmitted to the terminal.

[1351] Specific operation: Sign language video data is transmitted to the terminal in real time via the network.

[1352] Input: Sign language video data

[1353] Output: Transmitted sign language video data

[1354] Step 6:

[1355] The sign language video data received by the device is displayed on the lenses of the smart glasses.

[1356] Specific operation: The device displays the received sign language video data on the smart glasses display for the user to see.

[1357] Input: Received sign language video data

[1358] Output: Sign language video displayed on smart glasses

[1359] Sign language to text conversion processing steps

[1360] Step 1:

[1361] When the user responds in sign language, the device's camera captures the sign movements in real time.

[1362] Specific actions: The user signs "thank you" and the action is recorded by the device's camera.

[1363] Input: User sign language gesture

[1364] Output: Captured sign language movement data

[1365] Step 2:

[1366] The captured sign language action data is sent to a server.

[1367] Specific actions: The recorded sign language action data is sent to a server via a network.

[1368] Input: Captured sign language movement data

[1369] Output: Transmitted sign language movement data

[1370] Step 3:

[1371] The server analyzes the received sign language movement data using a machine learning algorithm and generates corresponding text data.

[1372] Specific action: The transmitted sign language movement data is analyzed by a machine learning algorithm, and the text data "Thank you" is generated.

[1373] Input: Received sign language movement data

[1374] Output: Generated text data

[1375] Step 4:

[1376] The generated text data is sent to the terminal.

[1377] Specific operation: Text data is sent to the terminal via the network.

[1378] Input: Generated text data

[1379] Output: The text data sent

[1380] Step 5:

[1381] The text data received by the device is displayed on the lenses of the smart glasses.

[1382] Specific operation: The device displays the received text data on the smart glasses display for the other party to see.

[1383] Input: Received text data

[1384] Output: Text displayed on the smart glasses

[1385] Through the above processing steps, the system converts audio into sign language video and sign language actions into text, enabling users to communicate smoothly in real time.

[1386] (Application example 1)

[1387] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1388] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-speaking people in brick-and-mortar stores. In situations where a sign language interpreter is needed, it is difficult for hearing-impaired people to obtain information independently, and there are only a limited number of professional sign language interpreters, so there is a need for faster response. Another issue is that if store staff do not understand sign language, communication takes time, resulting in a decline in service quality.

[1389] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1390] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for referencing a database specialized in generating sign language video data, and means having an interface for supporting customer service in a real-world store. This enables fast and efficient communication between hearing-impaired people and hearing-controlling people in a real-world store through real-time mutual conversion of text, sign language, and voice.

[1391] A "means for capturing user voice" is a part of the system that captures voice in digital form using a microphone or other voice input device.

[1392] The "means for converting captured voice into text data" is a function that converts acquired voice data into corresponding text data using voice recognition technology.

[1393] The "means for converting text data into sign language video data" is a conversion system for visualizing text data as sign language video based on a sign language database.

[1394] "Means for displaying sign language video data" refers to a function that outputs the generated sign language video to a display device such as a display or smart glasses.

[1395] A "means for capturing a user's sign language movements" is a part of a system that uses a camera or other image capture device to capture sign language movements as digital data.

[1396] The "means for converting captured sign language actions into text data" is a function that converts acquired sign language actions into corresponding text data using machine learning algorithms or image analysis technology.

[1397] "Means for displaying text data" refers to a function that outputs the converted text data to a display device such as a display or smart glasses.

[1398] "Means for referencing a database specialized in generating sign language video data" is a function for referencing a specialized database that stores the data necessary to convert text data into corresponding sign language video.

[1399] "Means with an interface to support customer service in a real-world store" refers to part of a system that includes a user interface and operation panel to facilitate communication between customers and staff in a real-world store.

[1400] This invention relates to a system for supporting smooth communication between hearing-impaired and hearing-normal people in brick-and-mortar stores. Specifically, this system converts a user's voice into sign language video and sign language actions into text, and is implemented using a terminal and a server.

[1401] Audio to sign language video conversion

[1402] The server uses the device's microphone to capture the user's voice. The captured voice data is converted into text data using the speech recognition library "SpeechRecognition." This text data is then converted into sign language video data based on a sign language database. This conversion uses an API that references the sign language database and generates the corresponding sign language video. The generated sign language video data is sent to the device in real time and displayed as a sign language video on a display device such as smart glasses. This process allows the user to see what the other person is saying in sign language video.

[1403] For example, if the person you are talking to says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to generate the text "hello," and then compares it with a sign language database to create a sign language video corresponding to "hello." This sign language video is sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the audio 'hello' into a sign language video."

[1404] Sign language to text conversion

[1405] When a user responds in sign language, the device's camera captures the sign language in real time. The captured sign language data is sent to a server, which analyzes it using the image analysis library "pytesseract" and machine learning algorithms. The resulting text data is sent back to the device and displayed on a display device such as smart glasses, allowing the other person to understand what the user is saying in sign language as text.

[1406] For example, if a user signs "thank you," the device's camera captures the action and sends it to the server. The server analyzes it and generates the text "thank you," which is then sent to the device and displayed on the smart glasses' display. An example of a prompt sentence is "Please convert the sign language video into the text 'thank you'."

[1407] This will enable real-time communication between hearing-impaired and hearing-savvy customers in brick-and-mortar stores. The system integrates multiple technologies, including voice recognition, sign language video generation, and image analysis, to provide fast and efficient customer service.

[1408] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1409] Step 1:

[1410] The device captures the user's voice.

[1411] Input: User's voice data

[1412] Specific operation: The device's microphone captures the audio and converts it into digital audio data.

[1413] Output: Audio data

[1414] Step 2:

[1415] The server converts the voice data into text data.

[1416] Input: Audio data

[1417] Specific operation: The server uses a speech recognition library (SpeechRecognition) to convert the voice data into text data.

[1418] Output: Text data

[1419] Step 3:

[1420] The server converts the text data into sign language video data.

[1421] Input: Text data

[1422] Specific operation: The server references the sign language database and generates sign language video data corresponding to the text data. The sign language video generation API is used to obtain the sign language video data.

[1423] Output: Sign language video data

[1424] Step 4:

[1425] The device displays the sign language video data.

[1426] Input: Sign language video data

[1427] Specific operation: Display sign language videos on the device display or smart glasses, allowing users to watch sign language videos.

[1428] Output: Display of sign language video

[1429] Step 5:

[1430] The device captures the user's sign language actions.

[1431] Input: User's sign language actions

[1432] Specific operation: The device's camera captures sign language movements in real time and saves them as digital video data.

[1433] Output: Sign language video data

[1434] Step 6:

[1435] The server converts the sign language video data into text data.

[1436] Input: Sign language video data

[1437] Specific operation: The server uses an image analysis library (pytesseract) and a machine learning algorithm to convert sign language video data into text data.

[1438] Output: Text data

[1439] Step 7:

[1440] The terminal displays the text data.

[1441] Input: Text data

[1442] Specific operation: By displaying text data on the device display or smart glasses, the person you are speaking with can understand the content of the sign language.

[1443] Output: Display of text data

[1444] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1445] This invention relates to a communication support system that uses voice and sign language to enable smooth communication between hearing-impaired and hearing-normal people, and by combining it with an emotion engine that recognizes the user's emotional state, it achieves higher quality communication. The specific operation of the program for this system is explained below.

[1446] Program Overview

[1447] The system captures the user's voice and sign language actions, analyzes them, and converts them into corresponding sign language video and text data. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[1448] Audio to sign language video conversion

[1449] When a user starts a conversation, the device captures the other person's voice through a microphone. The captured voice data is compressed and sent to a server. The server receives this voice data and converts it into text data using a natural language processing algorithm and an emotion engine. The text data is compared with a sign language database to generate corresponding sign language video data. The generated sign language video data is sent to the device in real time and displayed as a sign language video on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[1450] Specific examples

[1451] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, it retrieves the sign language video corresponding to "hello" from a sign language database and makes fine adjustments based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[1452] Sign language to text conversion

[1453] When a user responds in sign language, the device's camera captures the sign in real time. The captured movement data is sent to the server. The server then uses a machine learning algorithm and an emotion engine to analyze the sign data and generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the conversation partner to not only understand the user's sign language utterances as text, but also understand their emotional state.

[1454] Specific examples

[1455] For example, if a user sign "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[1456] In this way, the communication support system of the present invention not only converts speech to sign language and sign language to text, but also recognizes emotions using an emotion engine, thereby realizing richer communication.

[1457] The processing flow will be explained below.

[1458] Audio to sign language video conversion

[1459] Step 1:

[1460] The device captures the voice of the person you are talking to through a microphone, and the voice data is collected in real time.

[1461] Step 2:

[1462] The audio data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[1463] Step 3:

[1464] The server passes the received voice data through speech recognition software and converts it into text data using natural language processing algorithms.

[1465] Step 4:

[1466] The server passes the text data through an emotion engine to analyze the emotional state in the voice, generating text data with emotional information added.

[1467] Step 5:

[1468] The server compares the text data with a sign language database and extracts the corresponding sign language video data, and also performs fine-tuning based on emotional information.

[1469] Step 6:

[1470] The server encodes the extracted sign language video data into an appropriate format and sends it back to the terminal.

[1471] Step 7:

[1472] The device receives the sign language video data and displays it on the lenses of the smart glasses, allowing users to visually confirm the sign language video and its emotional information.

[1473] Sign language to text conversion

[1474] Step 1:

[1475] The user responds in sign language, and the device's camera captures this sign language action in real time.

[1476] Step 2:

[1477] The sign language movement data captured by the terminal is converted into a compressed format and sent to the server while reducing communication costs.

[1478] Step 3:

[1479] The server analyzes the sign language movement data it receives using a machine learning algorithm to understand the meaning of the sign language.

[1480] Step 4:

[1481] The server passes the sign language movement data through an emotion engine to analyze the emotional state of the sign language, and generates text data with emotional information added.

[1482] Step 5:

[1483] The server encodes the generated text data into an appropriate format and sends it to the terminal.

[1484] Step 6:

[1485] The device receives the text data and displays it on the lenses of the smart glasses, allowing the person speaking to see the meaning of the user's sign language and its emotional information as text.

[1486] In this way, each step works in tandem, allowing for real-time conversion from speech to sign language and from sign language to text, enabling smooth communication that also includes emotional information.

[1487] Example 2

[1488] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1489] While existing communication support systems provide functions for converting speech to sign language and sign language to text for communication between hearing-impaired and hearing-disabled people, they have a problem in that they are unable to improve the quality of communication by taking into account the emotional state of the user.In addition, there is a lack of means to accurately recognize the emotional state and modify the sign language video based on that, which means that the nuances of actual conversation cannot be fully conveyed.

[1490] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1491] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing the user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing the user's emotional state from the captured voice and sign language actions, and means for modifying the sign language video data based on the emotional state. This enables conversion of the sign language video and text data that reflects the user's emotional state, making it possible to more accurately convey the nuances of actual conversation.

[1492] "User" refers to an individual or group that communicates using the System.

[1493] "Means for capturing audio" refers to a microphone or other audio input device for collecting the user's voice.

[1494] "Text data conversion means" refers to software or algorithms for converting speech or sign language into a corresponding text format.

[1495] "Means for converting into sign language video data" refers to software or algorithms for converting text data into a corresponding sign language video format.

[1496] "Means for displaying sign language video data" refers to a display device or projector for presenting the generated sign language video to a user.

[1497] "Means for capturing sign language actions" refers to a camera or other video input device for photographing or recording a user's sign language actions.

[1498] "Means for recognizing emotional state" refers to software or algorithms for analyzing and recognizing a user's emotions from speech or sign language actions.

[1499] "Means for modifying sign language video data based on emotional state" refers to software or algorithms that adjust or modify the generated sign language video based on recognized emotional information.

[1500] "Server" means a centralized computer system for processing and storing data.

[1501] "System" refers to the overall mechanism in which the above means operate in conjunction with each other.

[1502] This invention relates to a system that enables smooth communication between hearing-impaired and hearing-suffering people, and aims to deepen mutual understanding by using voice and sign language. Furthermore, by combining it with an emotion engine, it recognizes the user's emotional state and achieves higher quality communication.

[1503] Audio to sign language video conversion

[1504] The device captures the user's voice through a microphone. It then compresses the captured voice data and sends it to a server via the Internet. The server receives this voice data and converts it into text data using a natural language processing algorithm (e.g., Google Cloud Speech-to-Text API) and an emotion engine. The converted text data is then compared with a sign language database (e.g., Sign Language API) to generate corresponding sign language video data. This sign language video data is then fine-tuned by the emotion engine based on the user's emotional state. Finally, the generated sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to see what the other person is saying in sign language video.

[1505] Sign language to text conversion

[1506] When a user responds in sign language, the device's camera (for example, Microsoft's Azure Kinect DK) captures the sign language in real time. The captured movement data is sent to a server, which analyzes it using machine learning algorithms (TensorFlow or PyTorch) and an emotion engine to generate corresponding text data and emotional state. The generated text data and emotional information are sent to the device and displayed on the lenses of the smart glasses. This allows the person speaking not only to understand the user's sign language utterances as text, but also to understand their emotional state.

[1507] Specific operation example

[1508] Audio to sign language video conversion example

[1509] For example, if a conversation partner says "hello," the device's microphone captures the audio and sends it to the server. The server analyzes the audio to recognize the text "hello" and the emotion contained in the audio (e.g., joy or surprise). Using this information, the server retrieves the sign language video corresponding to "hello" from a sign language database and fine-tunes it based on the emotion. The corrected sign language video is sent to the device and displayed on the lens of the smart glasses. This allows the user to not only see the sign language video for "hello," but also the emotion behind it.

[1510] Sign language to text example

[1511] For example, if a user signs "thank you," the device's camera captures the gesture and sends it to the server. The server analyzes it and recognizes the text "thank you" and the emotion conveyed in the sign (e.g., gratitude or emotion). This information is sent to the device and displayed on the lens of the smart glasses. The person you're talking to can simultaneously read the emotion behind the words "thank you."

[1512] Example prompts to input to the generative AI model

[1513] An example of a prompt sentence that can be input to the generative AI model would be, "Please convert the content and emotion expressed by the user in sign language into text."

[1514] With the above-described configuration and processing, the present invention realizes smooth communication via voice and sign language, and further improves the quality of communication by taking emotional states into consideration.

[1515] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1516] Audio to sign language video conversion

[1517] Step 1:

[1518] A user initiates a conversation.

[1519] Input: Voice of the person you are talking to.

[1520] Action: The user says "Good morning" to the other person.

[1521] Output: Voice data of the conversation partner.

[1522] Step 2:

[1523] The device captures the audio.

[1524] Input: Voice data of the conversation partner.

[1525] How it works: The built-in microphone on your smartphone or dedicated device picks up sound.

[1526] Output: The captured audio data.

[1527] Step 3:

[1528] The device sends the captured audio to the server.

[1529] Input: Captured audio data.

[1530] How it works: The device compresses the audio data and sends it over the internet to a server using an HTTP POST request.

[1531] Output: The audio data sent to the server.

[1532] Step 4:

[1533] The server converts the speech to text.

[1534] Input: The audio data sent to the server.

[1535] How it works: The received audio data is converted to text using the Google Cloud Speech-to-Text API, with the emotion engine also analyzing the tone and pitch of the voice.

[1536] Output: The converted text data.

[1537] Step 5:

[1538] The server converts the text into sign language video.

[1539] Input: Converted text data and emotional information contained in the speech.

[1540] How it works: The text data is matched against a sign language database using the Sign Language API, and the corresponding sign language video data is generated.

[1541] Output: Generated sign language video data.

[1542] Step 6:

[1543] The server sends the sign language video to the device.

[1544] Input: Generated sign language video data.

[1545] How it works: The generated sign language video data is sent to the device in real time, again using an HTTP POST request.

[1546] Output: Sign language video data sent to the device.

[1547] Step 7:

[1548] The device displays the sign language video.

[1549] Input: Sign language video data sent to the device.

[1550] How it works: The device displays the received sign language video on the lenses of the smart glasses.

[1551] Output: Visualized sign language video data.

[1552] Sign language to text conversion

[1553] Step 1:

[1554] The user responds in sign language.

[1555] Input: A sign language response.

[1556] Action: For example, perform an action to express "thank you" in sign language.

[1557] Output: Beginning of sign language action.

[1558] Step 2:

[1559] The device captures the sign language gestures.

[1560] Input: Sign language actions.

[1561] Actions: Smart glasses and camera devices capture sign language actions in real time. Azure Kinect DK is used.

[1562] Output: Captured sign language data.

[1563] Step 3:

[1564] The terminal transmits the captured sign language data to the server.

[1565] Input: Captured sign language data.

[1566] How it works: The device compresses the captured sign language data and sends it over the internet to a server.

[1567] Output: Sign language data sent to the server.

[1568] Step 4:

[1569] The server converts the sign language data into text.

[1570] Input: Sign language data sent to the server.

[1571] How it works: The received sign language data is analyzed using TensorFlow or PyTorch, and the corresponding text data is generated. At the same time, the emotion engine also analyzes the emotions conveyed in the sign language.

[1572] Output: The converted text data.

[1573] Step 5:

[1574] The server transmits the generated text data to the terminal.

[1575] Input: Transformed text data and sentiment information.

[1576] Operation: The generated text data and emotion information are sent to the device in real time.

[1577] Output: Text data and emotion information sent to the device.

[1578] Step 6:

[1579] The terminal displays the text.

[1580] Input: Text data and emotional information sent to the device.

[1581] Operation: The device displays the received text data and emotional information on the lenses of the smart glasses.

[1582] Output: Visualized text data and sentiment information.

[1583] Through these specific processing steps, the system enables smooth, high-quality communication via voice and sign language.

[1584] (Application example 2)

[1585] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1586] Conventional communication support systems lack support for smooth communication between hearing-impaired and hearing-disabled people. Furthermore, the lack of emotion recognition can lead to a decline in the quality of communication. Furthermore, no sophisticated communication support using smart glasses is available in brick-and-mortar stores. To address these issues, the present invention aims to achieve higher quality communication by capturing voice and sign language movements, converting them into text data, and displaying sign language videos and text data, as well as using an emotion engine.

[1587] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1588] In this invention, the server includes means for capturing a user's voice, means for converting the captured voice into text data, means for converting the text data into sign language video data, means for displaying the sign language video data, means for capturing a user's sign language actions, means for converting the captured sign language actions into text data, means for displaying the text data, means for recognizing a user's emotional state and improving the quality of communication based on that information, and means for integrating the above means and supporting smooth communication using smart glasses in a physical store. This enables hearing-impaired and hearing-disabled people to understand each other's emotions and communicate smoothly in a physical store.

[1589] The "means for capturing the user's voice" is a device for picking up the voice emitted by the user and recording it as digital data.

[1590] The "means for converting captured audio into text data" refers to software or hardware for analyzing audio data and converting it into corresponding text format data.

[1591] The "means for converting text data into sign language animation data" is a process for generating animation of corresponding sign language actions based on the text data.

[1592] The "means for displaying sign language video data" refers to a display device for visually presenting the generated sign language video to the user.

[1593] The "means for capturing the user's sign language actions" is a device for capturing the user's sign language actions in real time and recording them as digital data.

[1594] The "means for converting the captured sign language actions into text data" refers to software or hardware for analyzing the sign language action data and converting it into corresponding text format data.

[1595] The "means for displaying text data" is a display device for visually presenting the converted text data to the user.

[1596] "Means for recognizing the user's emotional state and improving the quality of communication based on that information" refers to a system that analyzes the user's emotions from voice and sign language movement data, and provides appropriate responses and feedback based on that emotional information.

[1597] "Means for supporting smooth communication using smart glasses in physical stores" refers to devices and systems that use smart glasses in a physical store environment to enable users to communicate smoothly.

[1598] This invention is a system that supports smooth communication between hearing-impaired and hearing-savvy people in brick-and-mortar stores, and improves the quality of communication by converting and displaying speech and sign language using smart glasses, and by recognizing emotional states. This system is mainly composed of a server, a terminal (smart glasses), and user interaction.

[1599] Overall system configuration

[1600] The server captures the user's voice and sign language actions, analyzes them, and converts them into text data and sign language videos. It also uses an emotion engine to recognize the user's emotional state and use that information to improve the quality of communication.

[1601] The device displays the sign language video and text data sent from the server in real time through the smart glasses, which are equipped with a microphone for capturing audio, a camera for capturing sign language movements, and a display device.

[1602] Program Overview

[1603] 1. Audio to Sign Language Video Conversion:

[1604] The server captures the user's voice through the device's microphone and converts it into text data. The generated text data is compared with a sign language video database to obtain the corresponding sign language video. An emotion engine is then used to add emotional information to the sign language video, which is then sent to the device. On the device side, the sign language video is displayed on the lenses of the smart glasses.

[1605] Examples:

[1606] For example, when a person with normal hearing says "Welcome," the microphone in the smart glasses captures the voice and sends it to the server. The server analyzes the voice and recognizes the text and the emotion contained in the voice. It then retrieves the corresponding sign language video from a sign language database and adjusts it based on the emotion information. This sign language video is then sent to the device and displayed on the smart glasses.

[1607] Example prompt sentence:

[1608] Voice input: "Welcome"

[1609] Sentiment Analysis: Joy

[1610] 2. Sign Language to Text Conversion:

[1611] When a user responds in sign language, the camera captures the sign in real time and sends it to the server. The server analyzes the sign and generates corresponding text data and emotion information. The generated text data and emotion information are sent to the device and displayed on the lens of the smart glasses.

[1612] Examples:

[1613] For example, if a user expresses "thank you" in sign language, the camera in the smart glasses captures the gesture and sends it to the server. The server analyzes it and recognizes the text data and the emotion of gratitude. This information is then sent to the device and displayed on the smart glasses.

[1614] Example prompt sentence:

[1615] Sign language input: "Thank you"

[1616] Sentiment Analysis: Gratitude

[1617] Hardware and software used

[1618] Hardware:

[1619] Smart glasses (e.g., AR glasses)

[1620] High-performance microphone

[1621] Cameras (e.g. smart glasses with high-resolution cameras)

[1622] software:

[1623] Natural language processing algorithms (e.g., speech recognition software)

[1624] Sentiment engines (e.g., sentiment analysis tools)

[1625] Sign language database (e.g., sign language conversion module)

[1626] Real-time image processing library (e.g. OpenCV)

[1627] This will enable hearing-impaired and hearing-sighted people to understand each other's emotions and communicate smoothly in physical stores.

[1628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1629] Step 1:

[1630] The device's microphone captures the user's voice. The captured voice data is converted into digital format and sent to the server. The input is the user's voice, and the output is digital voice data.

[1631] Step 2:

[1632] The server analyzes the received voice data and converts it into text data using a natural language processing algorithm. At the same time, it also uses an emotion engine to extract emotions from the voice. The input is digital voice data, and the output is text data and emotional information.

[1633] Step 3:

[1634] The server compares the text data with a sign language database and retrieves the corresponding sign language video data. It then fine-tunes the sign language video based on the extracted emotional information. The input is text data and emotional information, and the output is fine-tuned sign language video data.

[1635] Step 4:

[1636] The server transmits the sign language video data to the device in real time. The device displays the received sign language video data on the smart glasses display. The input is finely adjusted sign language video data, and the output is the sign language video displayed on the smart glasses.

[1637] Step 5:

[1638] When a user responds in sign language, the device's camera captures the sign language in real time, converts it into digital format, and sends it to the server. The input is the user's sign language, and the output is digital sign language data.

[1639] Step 6:

[1640] The server analyzes the received sign language motion data and converts it into text data using a machine learning algorithm. At the same time, it also uses an emotion engine to extract emotions from the sign language motion data. The input is digital sign language motion data, and the output is text data and emotion information.

[1641] Step 7:

[1642] The server sends the generated text data and emotional information to the terminal in real time. The terminal displays the received text data and emotional information on the smart glasses display. The input is text data and emotional information, and the output is the text data and emotional information displayed on the smart glasses.

[1643] Through these processing steps, hearing-impaired and hearing-speaking people can communicate effectively and smoothly in physical stores while understanding emotions.

[1644] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1645] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1646] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1647] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1648] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1649] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1650] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1651] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1652] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1653] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1654] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1655] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1656] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1657] 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.

[1658] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1659] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1660] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1661] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1662] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1663] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1664] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1665] The following is further disclosed regarding the above embodiment.

[1666] (Claim 1)

[1667] means for capturing the user's voice;

[1668] means for converting the captured audio into text data;

[1669] A means for converting text data into sign language video data;

[1670] a means for displaying sign language video data;

[1671] means for capturing a user's sign language actions;

[1672] means for converting the captured sign language actions into text data;

[1673] a means for displaying text data;

[1674] A communication support system including:

[1675] (Claim 2)

[1676] 2. The communication support system according to claim 1, wherein the means for converting text data into sign language video data includes means for collating the text data with a sign language database to obtain the corresponding sign language video.

[1677] (Claim 3)

[1678] 2. The communication support system according to claim 1, wherein the means for capturing the user's sign language actions includes means for capturing the sign language actions in real time using a camera.

[1679] "Example 1"

[1680] (Claim 1)

[1681] means for capturing the user's voice;

[1682] means for compressing the captured audio;

[1683] means for transmitting the compressed audio data to a server;

[1684] means for converting received voice data into text data;

[1685] means for converting text data into sign language video data based on a sign language database;

[1686] a means for displaying sign language video data;

[1687] means for capturing a user's sign language actions in real time;

[1688] means for transmitting the captured sign language action data to a server;

[1689] means for converting the received sign language action data into text data;

[1690] a means for displaying text data;

[1691] A system including:

[1692] (Claim 2)

[1693] 2. The system according to claim 1, wherein the means for converting text data into sign language video data includes means for comparing the text data with a sign language database to obtain corresponding sign language video.

[1694] (Claim 3)

[1695] 10. The system of claim 1, wherein the means for capturing the user's sign language actions includes means for capturing the sign language actions in real time using a camera.

[1696] "Application Example 1"

[1697] New Claims

[1698] (Claim 1)

[1699] means for capturing the user's voice;

[1700] means for converting the captured audio into text data;

[1701] A means for converting text data into sign language video data;

[1702] a means for displaying sign language video data;

[1703] means for capturing a user's sign language actions;

[1704] means for converting the captured sign language actions into text data;

[1705] a means for displaying text data;

[1706] A means for referencing a database specialized in generating sign language video data;

[1707] Equipped with an interface to support customer service in real-world stores

[1708] system.

[1709] (Claim 2)

[1710] 2. The system according to claim 1, wherein the means for converting text data into sign language video data includes means for comparing the text data with a sign language database to obtain corresponding sign language video.

[1711] (Claim 3)

[1712] 10. The system of claim 1, wherein the means for capturing the user's sign language actions includes means for capturing the sign language actions in real time using a camera.

[1713] "Example 2: Combining Emotion Engines"

[1714] (Claim 1)

[1715] means for capturing the user's voice;

[1716] means for converting the captured audio into text data;

[1717] A means for converting text data into sign language video data;

[1718] a means for displaying sign language video data;

[1719] means for capturing a user's sign language actions;

[1720] means for converting the captured sign language actions into text data;

[1721] a means for displaying text data;

[1722] means for recognizing the user's emotional state from the captured speech and sign language actions;

[1723] means for modifying the sign language video data based on the emotional state;

[1724] A system including:

[1725] (Claim 2)

[1726] 2. The system according to claim 1, wherein the means for converting text data into sign language video data includes means for comparing the text data with a sign language database to obtain corresponding sign language video.

[1727] (Claim 3)

[1728] 10. The system of claim 1, wherein the means for capturing the user's sign language actions includes means for capturing the sign language actions in real time using a camera.

[1729] (Claim 4)

[1730] 10. The system of claim 1, wherein the means for recognizing the user's emotional state from the captured speech and sign language actions uses an emotion engine.

[1731] (Claim 5)

[1732] 10. The system of claim 1, wherein the means for modifying the sign language video data based on an emotional state uses a natural language processing algorithm.

[1733] "Application example 2 when combining emotion engines"

[1734] (Claim 1)

[1735] means for capturing the user's voice;

[1736] means for converting the captured audio into text data;

[1737] A means for converting text data into sign language video data;

[1738] a means for displaying sign language video data;

[1739] means for capturing a user's sign language actions;

[1740] means for converting the captured sign language actions into text data;

[1741] a means for displaying text data;

[1742] A means for recognizing a user's emotional state and improving the quality of communication based on that information;

[1743] Integrating the above methods to support smooth communication in physical stores using smart glasses,

[1744] A system including:

[1745] (Claim 2)

[1746] The system of claim 1, wherein the means for converting text data into sign language video data includes means for comparing the text data with a sign language database to obtain corresponding sign language video, and further including means for fine-tuning the sign language video based on the user's emotional state.

[1747] (Claim 3)

[1748] 10. The system of claim 1, wherein the means for capturing the user's sign language actions comprises means for capturing the sign language actions in real time using a camera, and further means for analyzing the emotional state of the sign language actions. [Explanation of symbols]

[1749] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing the user's voice; means for converting the captured audio into text data; A means for converting text data into sign language video data; a means for displaying sign language video data; means for capturing a user's sign language actions; means for converting the captured sign language actions into text data; a means for displaying text data; A communication support system including:

2. 2. The communication support system according to claim 1, wherein the means for converting text data into sign language video data includes means for collating the text data with a sign language database to obtain the corresponding sign language video.

3. 2. The communication support system according to claim 1, wherein the means for capturing the user's sign language actions includes means for capturing the sign language actions in real time using a camera.

Images