System

Abstract

An object of the system according to the embodiment is to convert sign language and finger characters into characters and voices in real time.SOLUTION: A system includes a recognition unit, an analysis unit, and a conversion unit. The recognition unit recognizes sign language or finger characters. The analysis unit analyzes the sign language or the finger character recognized by the recognition unit. The conversion unit converts the meaning of the sign language or the finger character analyzed by the analysis unit into a character or a voice.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to convert sign language or finger spelling into text or speech in real time.

[0005] The system according to the embodiment aims to convert sign language and finger spelling into text and speech in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes a recognition unit, an analysis unit, and a conversion unit. The recognition unit recognizes sign language or fingerspelling. The analysis unit analyzes the sign language or fingerspelling recognized by the recognition unit. The conversion unit converts the meaning of the sign language or fingerspelling analyzed by the analysis unit into characters or speech. [Effects of the Invention]

[0007] The system according to the embodiment can convert sign language and finger spelling into text and speech in real time. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A sign language conversion system according to an embodiment of the present invention is a system for converting sign language or fingerspelling into text or speech. This system uses a generative AI to analyze sign language or fingerspelling in real time and convert it into text or speech. This enables the sign language conversion system to facilitate communication between people who use sign language and people who communicate using text or speech.

[0029] A sign language conversion system according to an embodiment includes a recognition unit, an analysis unit, and a conversion unit. The recognition unit recognizes sign language or fingerspelling. For example, the recognition unit uses a camera to capture sign language movements and recognize the video data. The recognition unit can also use a sensor to recognize fingerspelling movements. The recognition unit can also recognize sign language or fingerspelling movements in real time. For example, the recognition unit uses a camera to capture sign language movements and recognize the video data in real time. The recognition unit can also recognize fingerspelling movements in real time. The analysis unit analyzes the sign language or fingerspelling recognized by the recognition unit. For example, a generation AI analyzes the sign language movements and understands their meaning. The generation AI can also analyze fingerspelling movements and understand their meaning. The analysis unit can also analyze sign language or fingerspelling movements in real time. For example, the generation AI analyzes sign language movements in real time and understands their meaning. The generation AI can also analyze fingerspelling movements in real time and understand their meaning. The conversion unit converts the meaning of the sign language or fingerspelling analyzed by the analysis unit into characters or audio. For example, the generation AI converts the meaning of sign language into characters and displays it on a display. The generation AI can also convert the meaning of finger spelling into audio and play it back through a speaker. Furthermore, the conversion unit can convert the meaning of sign language or finger spelling into characters or audio in real time. For example, the generation AI can convert the meaning of sign language into characters in real time and display it on a display. The generation AI can also convert the meaning of finger spelling into audio in real time and play it back through a speaker. In this way, the sign language conversion system according to the embodiment can convert sign language or finger spelling into characters or audio in real time.

[0030] The recognition unit can learn the user's individual hand shape or movement habits and improve individually optimized recognition accuracy. For example, the recognition unit collects training data customized for each user and creates an individual model so that the generation AI can learn the user's hand shape and movement habits. For example, by having the user repeatedly use a specific sign language, the recognition unit learns the movement and improves recognition accuracy. The recognition unit also analyzes the user's hand shape and movement habits in real time, and the generation AI dynamically adjusts recognition accuracy based on that data. For example, the recognition unit detects subtle movements and changes in speed when the user signs and reflects them in the recognition model. The recognition unit also allows the generation AI to learn the user's hand shape and movement habits over a long period of time and continuously improve recognition accuracy. For example, the recognition unit collects data on the user's daily use of sign language and regularly updates the model. This allows the generation AI to provide recognition accuracy optimized for each user.

[0031] The recognition unit simultaneously analyzes not only hand movements but also facial expressions and body movements, enabling a more accurate understanding of meaning. For example, the recognition unit uses multiple cameras and sensors to collect data so that the generation AI can simultaneously analyze hand movements, facial expressions, and body movements. For example, it analyzes facial expressions and body movements when signing to complement the meaning of the sign language. The recognition unit also develops an algorithm that comprehensively analyzes hand movements, facial expressions, and body movements, allowing the generation AI to more accurately understand the meaning. For example, it analyzes facial expressions and body movements linked to sign language movements to understand the context of the sign language. The recognition unit also builds a system in which the generation AI analyzes hand movements, facial expressions, and body movements in real time to dynamically complement the meaning of the sign language. For example, it detects subtle changes in facial expressions and body movements when signing to accurately understand the meaning of the sign language. This enables a more accurate understanding of the meaning of sign language and finger spelling.

[0032] The recognition unit can simultaneously recognize sign language or finger spellings in different languages, thereby building a multilingual system. For example, the recognition unit collects multilingual training data and trains a model so that the generation AI can simultaneously recognize sign language and finger spellings in different languages. For example, the model is trained using sign language data from English, Japanese, French, etc. The recognition unit also develops an algorithm that simultaneously recognizes sign language and finger spellings in different languages, thereby building a multilingual system. For example, the recognition unit automatically detects the sign language and provides an appropriate translation. The recognition unit also builds a multilingual system so that the generation AI can recognize sign language and finger spellings in different languages ​​in real time. For example, when a user uses sign language in a different language, the generation AI automatically switches the language for recognition. This allows sign language and finger spellings in different languages ​​to be recognized simultaneously.

[0033] The recognition unit uses a glove-type sensor to directly measure hand movements, enabling recognition without using a camera. For example, the recognition unit uses a glove-type sensor to directly measure hand movements, and a generation AI uses that data to build a system that recognizes sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy and inputs the data into the generation AI. The recognition unit also develops technology to measure hand movements using a glove-type sensor, allowing the generation AI to recognize sign language or fingerspelling without using a camera. For example, a sensor attached to the glove measures hand movements in real time, and the generation AI analyzes the data. The recognition unit also develops a system that uses a glove-type sensor to measure hand movements, and a generation AI uses that data to recognize sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy, and the generation AI analyzes the data. This allows hand movements to be recognized with high accuracy using a glove-type sensor.

[0034] The conversion unit can select an appropriate expression by taking context into consideration when converting the meaning of sign language or finger spelling into text. For example, the conversion unit develops an algorithm that analyzes context and selects an appropriate expression when the generation AI converts the meaning of sign language or finger spelling into text. For example, it selects an appropriate word or phrase by taking the context before and after the sign language into consideration. Furthermore, the conversion unit has the generation AI analyze the context using natural language processing technology in order to convert the meaning of sign language or finger spelling into text by taking context into consideration. For example, it analyzes the context before and after the sign language and selects an appropriate expression. Furthermore, the conversion unit builds a system that selects an appropriate expression by taking context into consideration when the generation AI converts the meaning of sign language or finger spelling into text. For example, it analyzes the context before and after the sign language and selects an appropriate word or phrase. This makes it possible to select an appropriate expression by taking context into consideration.

[0035] The conversion unit can refer to the user's past utterance history and provide consistent expressions when converting the meaning of sign language or finger spelling into text. For example, the conversion unit builds a system that references the user's past utterance history and provides consistent expressions when the generation AI converts the meaning of sign language or finger spelling into text. For example, it selects an appropriate expression based on the user's past utterance data. The conversion unit also references the user's past utterance history and the generation AI builds a utterance history database to provide consistent expressions. For example, it collects the user's past utterance data and selects an appropriate expression. The conversion unit also develops an algorithm that references the user's past utterance history and provides consistent expressions when the generation AI converts the meaning of sign language or finger spelling into text. For example, it selects an appropriate expression based on the user's past utterance data. This makes it possible to refer to the user's past utterance history and provide consistent expressions.

[0036] The conversion unit can improve visual accessibility by displaying the meaning of sign language or finger spelling in a different font or style when converting the meaning of sign language or finger spelling into text. For example, the conversion unit builds a system that displays the meaning of sign language or finger spelling in a different font or style when the generation AI converts the meaning of sign language or finger spelling into text. For example, the conversion unit selects a visually accessible font or style. The conversion unit also develops a system that improves visual accessibility by displaying the meaning in a different font or style. For example, the conversion unit provides a function that allows users to customize the font or style. The conversion unit also builds a system that improves visual accessibility by displaying the meaning of sign language or finger spelling in a different font or style when the generation AI converts the meaning of sign language or finger spelling into text. For example, the conversion unit selects a visually accessible font or style. This improves visual accessibility.

[0037] The conversion unit can learn the characteristics of the user's voice when converting the meaning of sign language or finger spelling into speech and generate individually optimized speech. For example, the conversion unit builds a system in which a generation AI learns the characteristics of the user's voice and generates individually optimized speech when converting the meaning of sign language or finger spelling into speech. For example, it learns the tone and pitch of the user's voice and generates a natural speech. In addition, to learn the characteristics of the user's voice, the conversion unit develops an algorithm in which the generation AI collects the user's voice data and generates individually optimized speech. For example, it analyzes the characteristics of the user's voice and reflects them in a speech synthesis model. In addition, the conversion unit develops a system in which the generation AI learns the characteristics of the user's voice and generates individually optimized speech when converting the meaning of sign language or finger spelling into speech. For example, it trains a speech synthesis model based on the characteristics of the user's voice and generates a natural speech. In this way, it is possible to learn the characteristics of the user's voice and generate individually optimized speech.

[0038] The conversion unit can consider the context and add appropriate intonation or intonation when converting the meaning of sign language or finger spelling into speech. For example, when the generation AI converts the meaning of sign language or finger spelling into speech, the conversion unit develops an algorithm that analyzes the context and adds appropriate intonation and intonation. For example, it generates natural-looking speech by considering the context before and after the sign language. Furthermore, in order to convert the meaning of sign language or finger spelling into speech by considering the context, the generation AI analyzes the context using natural language processing technology. For example, it analyzes the context before and after the sign language and adds appropriate intonation and intonation. Furthermore, the conversion unit builds a system that considers the context and adds appropriate intonation and intonation when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it analyzes the context before and after the sign language and generates natural-looking speech. This makes it possible to add appropriate intonation and intonation by considering the context.

[0039] The conversion unit can accommodate speech in different languages ​​when converting the meaning of sign language or finger spelling into speech, thereby building a multilingual system. For example, the conversion unit builds a system that can accommodate speech in different languages ​​when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it develops a speech synthesis model that supports languages ​​such as English, Japanese, and French. To build a multilingual system, the generation AI collects speech data in different languages ​​and trains the speech synthesis model. For example, it develops a speech synthesis model that supports multiple languages ​​and converts the meaning of sign language into speech in multiple languages. The conversion unit can also develop a system that can accommodate speech in different languages ​​when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it translates the meaning of sign language in real time and converts it into speech in multiple languages. This makes it possible to accommodate speech in different languages.

[0040] The conversion unit can add a function that allows the user to customize the speed or tone of the voice when converting the meaning of sign language or finger spelling into speech. For example, the conversion unit builds a system that adds a function that allows the user to customize the speed and tone of the voice when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it provides an interface that allows the user to adjust the speed and tone of the voice. Furthermore, the conversion unit develops a system that adds a function that allows the user to customize the speed and tone of the voice when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it provides a function that allows the user to change the voice settings. Furthermore, the conversion unit develops a system that adds a function that allows the user to customize the speed and tone of the voice when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it provides an interface that allows the user to adjust the speed and tone of the voice in real time. This allows the user to customize the speed and tone of the voice.

[0041] The conversion unit can select appropriate sign language or finger spelling by taking context into consideration when converting text or spoken conversation into sign language or finger spelling. For example, the conversion unit develops an algorithm that analyzes context and selects appropriate sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, the appropriate sign language or finger spelling is selected by taking context before and after the conversation into consideration. Furthermore, in order to convert text or spoken conversation into sign language or finger spelling by taking context into consideration, the generation AI analyzes context using natural language processing technology. For example, the context before and after the conversation is analyzed and appropriate sign language or finger spelling is selected. Furthermore, the conversion unit builds a system that selects appropriate sign language or finger spelling by taking context into consideration when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, the context before and after the conversation is analyzed and appropriate sign language or finger spelling is selected. This makes it possible to select appropriate sign language or finger spelling by taking context into consideration.

[0042] The conversion unit, when converting text or spoken conversation into sign language or finger spelling, can refer to the user's past communication history and provide consistent sign language or finger spelling. For example, when the generation AI converts text or spoken conversation into sign language or finger spelling, the conversion unit references the user's past communication history and builds a system that provides consistent sign language or finger spelling. For example, the conversion unit selects appropriate sign language or finger spelling based on the user's past communication data. The conversion unit also references the user's past communication history and causes the generation AI to build a communication history database to provide consistent sign language or finger spelling. For example, the conversion unit collects the user's past communication data and selects appropriate sign language or finger spelling. The conversion unit also develops an algorithm that references the user's past communication history and provides consistent sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, the conversion unit selects appropriate sign language or finger spelling based on the user's past communication data. This makes it possible to refer to the user's past communication history and provide consistent sign language or finger spelling.

[0043] The conversion unit, when converting text or spoken conversation into sign language or finger spelling, can support sign language or finger spelling in different languages, allowing for the construction of a multilingual system. For example, when the generation AI converts text or spoken conversation into sign language or finger spelling, the conversion unit builds a system that can support sign language or finger spelling in different languages. For example, it develops models that support sign languages ​​such as English, Japanese, and French. In addition, to build a multilingual system, the generation AI collects sign language data in different languages ​​and trains the models. For example, it develops sign language models that support multiple languages ​​and converts text or spoken conversation into sign language in multiple languages. In addition, the conversion unit, when the generation AI converts text or spoken conversation into sign language or finger spelling, it develops a system that can support sign language or finger spelling in different languages. For example, it translates text or spoken conversation in real time and converts it into sign language in multiple languages. This makes it possible to support sign language or finger spelling in different languages.

[0044] The conversion unit can add a function that allows a user to customize the animation of sign language or finger spelling when converting text or spoken conversation into sign language or finger spelling. For example, the conversion unit builds a system that adds a function that allows a user to customize the animation of sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, it provides an interface that allows a user to adjust the speed and style of the sign language. Furthermore, the conversion unit develops a system that adds a function that allows a user to change the animation settings by adding a function that allows a user to customize the animation of sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, it provides an interface that allows a user to adjust the speed and style of the animation in real time. This allows the animation of sign language or finger spelling to be customized.

[0045] The system develops a system in which a generation AI learns a user's communication style and provides individually optimized responses in two-way real-time communication. For example, the system builds a system in which a generation AI learns a user's communication style and provides individually optimized responses in two-way real-time communication. For example, the system generates appropriate responses based on the user's past communication data. The system also develops an algorithm in which the generation AI collects the user's communication data to learn the user's communication style and provides individually optimized responses. For example, the system analyzes the user's communication patterns and generates appropriate responses. The system also develops a system in which the generation AI learns a user's communication style and provides individually optimized responses in two-way real-time communication. For example, the system dynamically adjusts responses based on the user's communication style. This makes it possible to provide individually optimized responses based on the user's communication style.

[0046] A system is developed in which a generative AI understands context and generates responses at the appropriate time in two-way real-time communication. For example, the system is constructed so that a generative AI understands context and generates responses at the appropriate time in two-way real-time communication. For example, the system analyzes the context before and after a conversation and generates a response at the appropriate time. In order to understand the context and generate a response at the appropriate time, the generative AI analyzes the context using natural language processing technology. For example, the system analyzes the context before and after a conversation and generates a response at the appropriate time. In addition, a system is developed in which a generative AI understands context and generates responses at the appropriate time in two-way real-time communication. For example, the system analyzes the context before and after a conversation and generates a response at the appropriate time. This makes it possible to understand the context and generate a response at the appropriate time.

[0047] The system builds a multilingual system in which the generation AI can handle sign language or finger spelling in different languages ​​during two-way real-time communication. For example, the system builds a system in which the generation AI can handle sign language and finger spelling in different languages ​​during two-way real-time communication. For example, a model that supports sign languages ​​such as English, Japanese, and French is developed. To build a multilingual system, the generation AI collects sign language data in different languages ​​and trains the model. For example, a sign language model that supports multiple languages ​​is developed, realizing two-way real-time communication in multiple languages. The system also develops a system in which the generation AI can handle sign language and finger spelling in different languages ​​during two-way real-time communication. For example, the system translates the meaning of sign language in real time, realizing two-way communication in multiple languages. This makes it possible to handle sign language and finger spelling in different languages.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The recognition unit not only recognizes sign language and finger spelling movements, but can also measure the temperature and humidity of the user's hands and analyze their condition. For example, if the temperature of the hands is high, it determines that the user may be nervous and adjusts the recognition accuracy. If the humidity of the hands is high, it determines that the user may be sweating and improves recognition accuracy by taking into account the slippage of hand movements. Furthermore, by collecting hand temperature and humidity data over a long period of time and analyzing changes in the user's hand condition, it is possible to achieve even more accurate recognition. This is expected to improve recognition accuracy by taking hand temperature and humidity into account.

[0050] The recognition unit can analyze not only the user's hand movements but also the hand muscle movements. For example, a sensor that measures hand muscle movements can be used to analyze sign language and finger spelling movements in more detail. Furthermore, based on the hand muscle movement data, the recognition unit can learn the user's hand movement patterns and improve recognition accuracy. Furthermore, the hand muscle movement data can be analyzed in real time to dynamically complement the sign language and finger spelling movements. This is expected to improve recognition accuracy by taking hand muscle movements into account.

[0051] The recognition unit can analyze not only hand movements but also the user's gaze. For example, it uses gaze tracking technology to analyze the direction the user is looking and complement the meaning of sign language or finger spelling. It can also estimate the user's intention based on gaze movement data, improving recognition accuracy. Furthermore, it can analyze gaze movement data in real time and dynamically complement sign language or finger spelling movements. This is expected to improve recognition accuracy by taking gaze movement into account.

[0052] The recognition unit can simultaneously recognize sign language and finger spellings in different languages, building a multilingual system. For example, in order for the generation AI to simultaneously recognize sign language and finger spellings in different languages, multilingual training data is collected and a model is trained. For example, sign language data from English, Japanese, French, etc. is used to train the model. In addition, an algorithm is developed to simultaneously recognize sign language and finger spellings in different languages, and the generation AI builds a multilingual system. For example, it automatically detects the sign language and provides an appropriate translation. In addition, the generation AI recognizes sign language and finger spellings in different languages ​​in real time, building a multilingual system. For example, when a user uses sign language in a different language, the generation AI automatically switches the language for recognition. This allows sign language and finger spellings in different languages ​​to be recognized simultaneously.

[0053] The recognition unit uses a glove-type sensor to directly measure hand movements, enabling recognition without using a camera. For example, a system can be built in which hand movements are measured directly using a glove-type sensor, and a generation AI uses that data to recognize sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy and inputs the data into the generation AI. We will also develop technology to measure hand movements using a glove-type sensor, allowing the generation AI to recognize sign language or fingerspelling without using a camera. For example, a sensor attached to the glove measures hand movements in real time, and the generation AI analyzes the data. We will also develop a system in which hand movements are measured using a glove-type sensor, and a generation AI uses that data to recognize sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy, and the generation AI analyzes the data. This makes it possible to recognize hand movements with high accuracy using a glove-type sensor.

[0054] The conversion unit is able to select appropriate expressions by taking context into consideration when converting the meaning of sign language or finger spelling into text. For example, when the generation AI converts the meaning of sign language or finger spelling into text, an algorithm is developed that analyzes the context and selects appropriate expressions. For example, appropriate words and phrases are selected by taking the context before and after the sign language into consideration. Furthermore, in order to convert the meaning of sign language or finger spelling into text by taking context into consideration, the generation AI analyzes the context using natural language processing technology. For example, the context before and after the sign language is analyzed and appropriate expressions are selected. Furthermore, a system is built that selects appropriate expressions by taking context into consideration when the generation AI converts the meaning of sign language or finger spelling into text. For example, the context before and after the sign language is analyzed and appropriate words and phrases are selected. This makes it possible to select appropriate expressions by taking context into consideration.

[0055] When converting the meaning of sign language or finger spelling into text, the conversion unit can refer to the user's past utterance history and provide consistent expressions. For example, when the generation AI converts the meaning of sign language or finger spelling into text, it references the user's past utterance history and builds a system that provides consistent expressions. For example, it selects an appropriate expression based on the user's past utterance data. In addition, in order to refer to the user's past utterance history and provide consistent expressions, the generation AI builds a utterance history database. For example, it collects the user's past utterance data and selects an appropriate expression. In addition, when the generation AI converts the meaning of sign language or finger spelling into text, it references the user's past utterance history and develops an algorithm that provides consistent expressions. For example, it selects an appropriate expression based on the user's past utterance data. This makes it possible to refer to the user's past utterance history and provide consistent expressions.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The recognition unit recognizes sign language or finger spelling. For example, a camera is used to capture sign language movements and recognize the video data. Finger spelling movements can also be recognized using a sensor. Furthermore, the recognition unit can recognize sign language or finger spelling movements in real time. Step 2: The analysis unit analyzes the sign language or fingerspelling recognized by the recognition unit. For example, the generation AI analyzes the sign language movements and understands their meaning. The generation AI can also analyze the fingerspelling movements and understand their meaning. Furthermore, the analysis unit can analyze the sign language or fingerspelling movements in real time. Step 3: The conversion unit converts the meaning of the sign language or finger spelling analyzed by the analysis unit into text or audio. For example, the generation AI converts the meaning of the sign language into text and displays it on a display. The generation AI can also convert the meaning of the finger spelling into audio and play it through a speaker. Furthermore, the conversion unit can convert the meaning of the sign language or finger spelling into text or audio in real time.

[0058] (Example 2) A sign language conversion system according to an embodiment of the present invention is a system for converting sign language or fingerspelling into text or speech. This system uses a generative AI to analyze sign language or fingerspelling in real time and convert it into text or speech. This enables the sign language conversion system to facilitate communication between people who use sign language and people who communicate using text or speech.

[0059] A sign language conversion system according to an embodiment includes a recognition unit, an analysis unit, and a conversion unit. The recognition unit recognizes sign language or fingerspelling. For example, the recognition unit uses a camera to capture sign language movements and recognize the video data. The recognition unit can also use a sensor to recognize fingerspelling movements. The recognition unit can also recognize sign language or fingerspelling movements in real time. For example, the recognition unit uses a camera to capture sign language movements and recognize the video data in real time. The recognition unit can also recognize fingerspelling movements in real time. The analysis unit analyzes the sign language or fingerspelling recognized by the recognition unit. For example, a generation AI analyzes the sign language movements and understands their meaning. The generation AI can also analyze fingerspelling movements and understand their meaning. The analysis unit can also analyze sign language or fingerspelling movements in real time. For example, the generation AI analyzes sign language movements in real time and understands their meaning. The generation AI can also analyze fingerspelling movements in real time and understand their meaning. The conversion unit converts the meaning of the sign language or fingerspelling analyzed by the analysis unit into characters or audio. For example, the generation AI converts the meaning of sign language into characters and displays it on a display. The generation AI can also convert the meaning of finger spelling into audio and play it back through a speaker. Furthermore, the conversion unit can convert the meaning of sign language or finger spelling into characters or audio in real time. For example, the generation AI can convert the meaning of sign language into characters in real time and display it on a display. The generation AI can also convert the meaning of finger spelling into audio in real time and play it back through a speaker. In this way, the sign language conversion system according to the embodiment can convert sign language or finger spelling into characters or audio in real time.

[0060] The recognition unit can learn the user's individual hand shape or movement habits and improve individually optimized recognition accuracy. For example, the recognition unit collects training data customized for each user and creates an individual model so that the generation AI can learn the user's hand shape and movement habits. For example, by having the user repeatedly use a specific sign language, the recognition unit learns the movement and improves recognition accuracy. The recognition unit also analyzes the user's hand shape and movement habits in real time, and the generation AI dynamically adjusts recognition accuracy based on that data. For example, the recognition unit detects subtle movements and changes in speed when the user signs and reflects them in the recognition model. The recognition unit also allows the generation AI to learn the user's hand shape and movement habits over a long period of time and continuously improve recognition accuracy. For example, the recognition unit collects data on the user's daily use of sign language and regularly updates the model. This allows the generation AI to provide recognition accuracy optimized for each user.

[0061] The recognition unit simultaneously analyzes not only hand movements but also facial expressions and body movements, enabling a more accurate understanding of meaning. For example, the recognition unit uses multiple cameras and sensors to collect data so that the generation AI can simultaneously analyze hand movements, facial expressions, and body movements. For example, it analyzes facial expressions and body movements when signing to complement the meaning of the sign language. The recognition unit also develops an algorithm that comprehensively analyzes hand movements, facial expressions, and body movements, allowing the generation AI to more accurately understand the meaning. For example, it analyzes facial expressions and body movements linked to sign language movements to understand the context of the sign language. The recognition unit also builds a system in which the generation AI analyzes hand movements, facial expressions, and body movements in real time to dynamically complement the meaning of the sign language. For example, it detects subtle changes in facial expressions and body movements when signing to accurately understand the meaning of the sign language. This enables a more accurate understanding of the meaning of sign language and finger spelling.

[0062] The recognition unit can use the emotion estimation function to analyze the user's emotion when using sign language or fingerspelling, and complement the meaning of the sign language or fingerspelling based on that emotion. For example, the recognition unit estimates emotion using facial expression recognition technology so that the generation AI can analyze the user's emotion when using sign language or fingerspelling. For example, the recognition unit analyzes the user's facial expression when using sign language and calculates an emotion score. The recognition unit also uses the emotion estimation function to develop an algorithm that complements the meaning of sign language or fingerspelling. For example, the recognition unit complements the meaning of sign language based on the user's emotion when using sign language, providing a more accurate translation. The recognition unit also builds a system that analyzes the user's emotion when using sign language or fingerspelling in real time, and dynamically complements the meaning of sign language or fingerspelling based on that emotion. For example, the recognition unit adjusts the meaning of sign language according to changes in the user's emotion. This makes it possible to complement the meaning of sign language or fingerspelling based on the user's emotion.

[0063] The recognition unit can simultaneously recognize sign language or finger spellings in different languages, thereby building a multilingual system. For example, the recognition unit collects multilingual training data and trains a model so that the generation AI can simultaneously recognize sign language and finger spellings in different languages. For example, the model is trained using sign language data from English, Japanese, French, etc. The recognition unit also develops an algorithm that simultaneously recognizes sign language and finger spellings in different languages, thereby building a multilingual system. For example, the recognition unit automatically detects the sign language and provides an appropriate translation. The recognition unit also builds a multilingual system so that the generation AI can recognize sign language and finger spellings in different languages ​​in real time. For example, when a user uses sign language in a different language, the generation AI automatically switches the language for recognition. This allows sign language and finger spellings in different languages ​​to be recognized simultaneously.

[0064] The recognition unit uses a glove-type sensor to directly measure hand movements, enabling recognition without using a camera. For example, the recognition unit uses a glove-type sensor to directly measure hand movements, and a generation AI uses that data to build a system that recognizes sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy and inputs the data into the generation AI. The recognition unit also develops technology to measure hand movements using a glove-type sensor, allowing the generation AI to recognize sign language or fingerspelling without using a camera. For example, a sensor attached to the glove measures hand movements in real time, and the generation AI analyzes the data. The recognition unit also develops a system that uses a glove-type sensor to measure hand movements, and a generation AI uses that data to recognize sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy, and the generation AI analyzes the data. This allows hand movements to be recognized with high accuracy using a glove-type sensor.

[0065] The recognition unit uses the emotion estimation function to display the user's emotion when using sign language or fingerspelling in real time, thereby improving the quality of communication. The recognition unit, for example, uses the emotion estimation function to build a system that displays the user's emotion when using sign language or fingerspelling in real time. For example, the recognition unit analyzes the user's facial expression and displays an emotion score on a display. The recognition unit also develops a system that improves the quality of communication by displaying the user's emotion in real time. For example, the recognition unit displays the emotion when using sign language to make it easier for the other party to understand that emotion. The recognition unit also uses the emotion estimation function to build a system that improves the quality of communication by displaying the user's emotion when using sign language or fingerspelling in real time. For example, the recognition unit displays the user's emotion score on a display to make it easier for the other party to understand that emotion. This allows the user's emotion to be displayed in real time, thereby improving the quality of communication.

[0066] The conversion unit can select an appropriate expression by taking context into consideration when converting the meaning of sign language or finger spelling into text. For example, the conversion unit develops an algorithm that analyzes context and selects an appropriate expression when the generation AI converts the meaning of sign language or finger spelling into text. For example, it selects an appropriate word or phrase by taking the context before and after the sign language into consideration. Furthermore, the conversion unit has the generation AI analyze the context using natural language processing technology in order to convert the meaning of sign language or finger spelling into text by taking context into consideration. For example, it analyzes the context before and after the sign language and selects an appropriate expression. Furthermore, the conversion unit builds a system that selects an appropriate expression by taking context into consideration when the generation AI converts the meaning of sign language or finger spelling into text. For example, it analyzes the context before and after the sign language and selects an appropriate word or phrase. This makes it possible to select an appropriate expression by taking context into consideration.

[0067] The conversion unit can refer to the user's past utterance history and provide consistent expressions when converting the meaning of sign language or finger spelling into text. For example, the conversion unit builds a system that references the user's past utterance history and provides consistent expressions when the generation AI converts the meaning of sign language or finger spelling into text. For example, it selects an appropriate expression based on the user's past utterance data. The conversion unit also references the user's past utterance history and the generation AI builds a utterance history database to provide consistent expressions. For example, it collects the user's past utterance data and selects an appropriate expression. The conversion unit also develops an algorithm that references the user's past utterance history and provides consistent expressions when the generation AI converts the meaning of sign language or finger spelling into text. For example, it selects an appropriate expression based on the user's past utterance data. This makes it possible to refer to the user's past utterance history and provide consistent expressions.

[0068] The conversion unit can use the emotion estimation function to select an expression that reflects the user's emotion when converting the meaning of sign language or finger spelling into text. For example, the conversion unit uses the emotion estimation function to build a system that selects an expression that reflects the user's emotion when converting the meaning of sign language or finger spelling into text. For example, it selects an appropriate expression based on the user's emotion score. The conversion unit also develops an algorithm that uses the emotion estimation function to select an expression that reflects the user's emotion when the generation AI converts the meaning of sign language or finger spelling into text. For example, it selects an appropriate expression based on the user's emotion score. The conversion unit also develops a system that uses the emotion estimation function to select an expression that reflects the user's emotion when converting the meaning of sign language or finger spelling into text. For example, it selects an appropriate expression based on the user's emotion score. This makes it possible to select an expression that reflects the user's emotion.

[0069] The conversion unit can improve visual accessibility by displaying the meaning of sign language or finger spelling in a different font or style when converting the meaning of sign language or finger spelling into text. For example, the conversion unit builds a system that displays the meaning of sign language or finger spelling in a different font or style when the generation AI converts the meaning of sign language or finger spelling into text. For example, the conversion unit selects a visually accessible font or style. The conversion unit also develops a system that improves visual accessibility by displaying the meaning in a different font or style. For example, the conversion unit provides a function that allows users to customize the font or style. The conversion unit also builds a system that improves visual accessibility by displaying the meaning of sign language or finger spelling in a different font or style when the generation AI converts the meaning of sign language or finger spelling into text. For example, the conversion unit selects a visually accessible font or style. This improves visual accessibility.

[0070] The conversion unit can use the emotion estimation function to add colors or effects to the text according to the user's emotions when converting the meaning of sign language or finger spelling into text. For example, the conversion unit uses the emotion estimation function to build a system that adds colors or effects to the text according to the user's emotions when converting the meaning of sign language or finger spelling into text. For example, bright colors are used for positive emotions and dark colors for negative emotions. The conversion unit also develops an algorithm that uses the emotion estimation function to add effects to the text according to the user's emotions when the generation AI converts the meaning of sign language or finger spelling into text. For example, it adds animation effects to the text based on the emotion score. The conversion unit also develops a system that uses the emotion estimation function to add colors or effects to the text according to the user's emotions when converting the meaning of sign language or finger spelling into text. For example, it dynamically changes the color or effect of the text based on the user's emotion score. This makes it possible to add colors or effects to the text according to the user's emotions.

[0071] The conversion unit can learn the characteristics of the user's voice when converting the meaning of sign language or finger spelling into speech and generate individually optimized speech. For example, the conversion unit builds a system in which a generation AI learns the characteristics of the user's voice and generates individually optimized speech when converting the meaning of sign language or finger spelling into speech. For example, it learns the tone and pitch of the user's voice and generates a natural speech. In addition, to learn the characteristics of the user's voice, the conversion unit develops an algorithm in which the generation AI collects the user's voice data and generates individually optimized speech. For example, it analyzes the characteristics of the user's voice and reflects them in a speech synthesis model. In addition, the conversion unit develops a system in which the generation AI learns the characteristics of the user's voice and generates individually optimized speech when converting the meaning of sign language or finger spelling into speech. For example, it trains a speech synthesis model based on the characteristics of the user's voice and generates a natural speech. In this way, it is possible to learn the characteristics of the user's voice and generate individually optimized speech.

[0072] The conversion unit can consider the context and add appropriate intonation or intonation when converting the meaning of sign language or finger spelling into speech. For example, when the generation AI converts the meaning of sign language or finger spelling into speech, the conversion unit develops an algorithm that analyzes the context and adds appropriate intonation and intonation. For example, it generates natural-looking speech by considering the context before and after the sign language. Furthermore, in order to convert the meaning of sign language or finger spelling into speech by considering the context, the generation AI analyzes the context using natural language processing technology. For example, it analyzes the context before and after the sign language and adds appropriate intonation and intonation. Furthermore, the conversion unit builds a system that considers the context and adds appropriate intonation and intonation when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it analyzes the context before and after the sign language and generates natural-looking speech. This makes it possible to add appropriate intonation and intonation by considering the context.

[0073] The conversion unit can use the emotion estimation function to generate speech that reflects the user's emotion when converting the meaning of sign language or finger spelling into speech. For example, the conversion unit uses the emotion estimation function to build a system that generates speech that reflects the user's emotion when converting the meaning of sign language or finger spelling into speech. For example, the conversion unit adjusts the tone and pitch of the speech based on the user's emotion score. The conversion unit also develops an algorithm that uses the emotion estimation function to generate speech that reflects the user's emotion when the generation AI converts the meaning of sign language or finger spelling into speech. For example, the conversion unit adjusts the intonation and inflection of the speech based on the user's emotion score. The conversion unit also uses the emotion estimation function to develop a system that generates speech that reflects the user's emotion when converting the meaning of sign language or finger spelling into speech. For example, the conversion unit dynamically changes the tone and pitch of the speech based on the user's emotion score. This makes it possible to generate speech that reflects the user's emotion.

[0074] The conversion unit can accommodate speech in different languages ​​when converting the meaning of sign language or finger spelling into speech, thereby building a multilingual system. For example, the conversion unit builds a system that can accommodate speech in different languages ​​when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it develops a speech synthesis model that supports languages ​​such as English, Japanese, and French. To build a multilingual system, the generation AI collects speech data in different languages ​​and trains the speech synthesis model. For example, it develops a speech synthesis model that supports multiple languages ​​and converts the meaning of sign language into speech in multiple languages. The conversion unit can also develop a system that can accommodate speech in different languages ​​when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it translates the meaning of sign language in real time and converts it into speech in multiple languages. This makes it possible to accommodate speech in different languages.

[0075] The conversion unit can add a function that allows the user to customize the speed or tone of the voice when converting the meaning of sign language or finger spelling into speech. For example, the conversion unit builds a system that adds a function that allows the user to customize the speed and tone of the voice when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it provides an interface that allows the user to adjust the speed and tone of the voice. Furthermore, the conversion unit develops a system that adds a function that allows the user to customize the speed and tone of the voice when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it provides a function that allows the user to change the voice settings. Furthermore, the conversion unit develops a system that adds a function that allows the user to customize the speed and tone of the voice when the generation AI converts the meaning of sign language or finger spelling into speech. For example, it provides an interface that allows the user to adjust the speed and tone of the voice in real time. This allows the user to customize the speed and tone of the voice.

[0076] The conversion unit can use the emotion estimation function to add audio effects according to the user's emotion when converting the meaning of sign language or finger spelling into speech. For example, the conversion unit uses the emotion estimation function to build a system that adds audio effects according to the user's emotion when converting the meaning of sign language or finger spelling into speech. For example, a bright tone effect is used for positive emotions and a dark tone effect is used for negative emotions. The conversion unit also develops an algorithm that uses the emotion estimation function to add audio effects according to the user's emotion when the generation AI converts the meaning of sign language or finger spelling into speech. For example, effects such as reverb and echo are added to the speech based on the emotion score. The conversion unit also develops a system that uses the emotion estimation function to add audio effects according to the user's emotion when converting the meaning of sign language or finger spelling into speech. For example, audio effects are dynamically changed based on the user's emotion score. This makes it possible to add audio effects according to the user's emotion.

[0077] The conversion unit can select appropriate sign language or finger spelling by taking context into consideration when converting text or spoken conversation into sign language or finger spelling. For example, the conversion unit develops an algorithm that analyzes context and selects appropriate sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, the appropriate sign language or finger spelling is selected by taking context before and after the conversation into consideration. Furthermore, in order to convert text or spoken conversation into sign language or finger spelling by taking context into consideration, the generation AI analyzes context using natural language processing technology. For example, the context before and after the conversation is analyzed and appropriate sign language or finger spelling is selected. Furthermore, the conversion unit builds a system that selects appropriate sign language or finger spelling by taking context into consideration when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, the context before and after the conversation is analyzed and appropriate sign language or finger spelling is selected. This makes it possible to select appropriate sign language or finger spelling by taking context into consideration.

[0078] The conversion unit, when converting text or spoken conversation into sign language or finger spelling, can refer to the user's past communication history and provide consistent sign language or finger spelling. For example, when the generation AI converts text or spoken conversation into sign language or finger spelling, the conversion unit references the user's past communication history and builds a system that provides consistent sign language or finger spelling. For example, the conversion unit selects appropriate sign language or finger spelling based on the user's past communication data. The conversion unit also references the user's past communication history and causes the generation AI to build a communication history database to provide consistent sign language or finger spelling. For example, the conversion unit collects the user's past communication data and selects appropriate sign language or finger spelling. The conversion unit also develops an algorithm that references the user's past communication history and provides consistent sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, the conversion unit selects appropriate sign language or finger spelling based on the user's past communication data. This makes it possible to refer to the user's past communication history and provide consistent sign language or finger spelling.

[0079] The conversion unit can use the emotion estimation function to select sign language or finger spelling that reflects the user's emotion when converting text or voice conversation into sign language or finger spelling. For example, the conversion unit uses the emotion estimation function to build a system that selects sign language or finger spelling that reflects the user's emotion when converting text or voice conversation into sign language or finger spelling. For example, it selects appropriate sign language or finger spelling based on the user's emotion score. The conversion unit also develops an algorithm that uses the emotion estimation function to select sign language or finger spelling that reflects the user's emotion when the generation AI converts text or voice conversation into sign language or finger spelling. For example, it selects appropriate sign language or finger spelling based on the user's emotion score. The conversion unit also develops a system that uses the emotion estimation function to select sign language or finger spelling that reflects the user's emotion when converting text or voice conversation into sign language or finger spelling. For example, it dynamically changes appropriate sign language or finger spelling based on the user's emotion score. This makes it possible to select sign language or finger spelling that reflects the user's emotion.

[0080] The conversion unit, when converting text or spoken conversation into sign language or finger spelling, can support sign language or finger spelling in different languages, allowing for the construction of a multilingual system. For example, when the generation AI converts text or spoken conversation into sign language or finger spelling, the conversion unit builds a system that can support sign language or finger spelling in different languages. For example, it develops models that support sign languages ​​such as English, Japanese, and French. In addition, to build a multilingual system, the generation AI collects sign language data in different languages ​​and trains the models. For example, it develops sign language models that support multiple languages ​​and converts text or spoken conversation into sign language in multiple languages. In addition, the conversion unit, when the generation AI converts text or spoken conversation into sign language or finger spelling, it develops a system that can support sign language or finger spelling in different languages. For example, it translates text or spoken conversation in real time and converts it into sign language in multiple languages. This makes it possible to support sign language or finger spelling in different languages.

[0081] The conversion unit can add a function that allows a user to customize the animation of sign language or finger spelling when converting text or spoken conversation into sign language or finger spelling. For example, the conversion unit builds a system that adds a function that allows a user to customize the animation of sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, it provides an interface that allows a user to adjust the speed and style of the sign language. Furthermore, the conversion unit develops a system that adds a function that allows a user to change the animation settings by adding a function that allows a user to customize the animation of sign language or finger spelling when the generation AI converts text or spoken conversation into sign language or finger spelling. For example, it provides an interface that allows a user to adjust the speed and style of the animation in real time. This allows the animation of sign language or finger spelling to be customized.

[0082] The conversion unit can use the emotion estimation function to add animation or effects according to the user's emotion when converting text or audio conversation into sign language or finger spelling. For example, the conversion unit uses the emotion estimation function to build a system that adds animation effects according to the user's emotion when converting text or audio conversation into sign language or finger spelling. For example, a bright effect is used for positive emotions and a dark effect is used for negative emotions. The conversion unit also develops an algorithm that uses the emotion estimation function to add animation effects according to the user's emotion when the generation AI converts text or audio conversation into sign language or finger spelling. For example, it adds effects such as reverb and echo to the animation based on the emotion score. The conversion unit also develops a system that uses the emotion estimation function to add animation effects according to the user's emotion when converting text or audio conversation into sign language or finger spelling. For example, it dynamically changes animation effects based on the user's emotion score. This makes it possible to add animation effects according to the user's emotion.

[0083] The system develops a system in which a generation AI learns a user's communication style and provides individually optimized responses in two-way real-time communication. For example, the system builds a system in which a generation AI learns a user's communication style and provides individually optimized responses in two-way real-time communication. For example, the system generates appropriate responses based on the user's past communication data. The system also develops an algorithm in which the generation AI collects the user's communication data to learn the user's communication style and provides individually optimized responses. For example, the system analyzes the user's communication patterns and generates appropriate responses. The system also develops a system in which the generation AI learns a user's communication style and provides individually optimized responses in two-way real-time communication. For example, the system dynamically adjusts responses based on the user's communication style. This makes it possible to provide individually optimized responses based on the user's communication style.

[0084] A system is developed in which a generative AI understands context and generates responses at the appropriate time in two-way real-time communication. For example, the system is constructed so that a generative AI understands context and generates responses at the appropriate time in two-way real-time communication. For example, the system analyzes the context before and after a conversation and generates a response at the appropriate time. In order to understand the context and generate a response at the appropriate time, the generative AI analyzes the context using natural language processing technology. For example, the system analyzes the context before and after a conversation and generates a response at the appropriate time. In addition, a system is developed in which a generative AI understands context and generates responses at the appropriate time in two-way real-time communication. For example, the system analyzes the context before and after a conversation and generates a response at the appropriate time. This makes it possible to understand the context and generate a response at the appropriate time.

[0085] The system uses an emotion estimation function to generate responses that reflect a user's emotions in two-way real-time communication. For example, the system uses the emotion estimation function to build a system that generates responses that reflect a user's emotions in two-way real-time communication. For example, the system generates an appropriate response based on a user's emotion score. The system also develops an algorithm in which a generation AI uses the emotion estimation function to generate responses that reflect a user's emotions in two-way real-time communication. For example, the system generates an appropriate response based on a user's emotion score. The system also develops a system that uses the emotion estimation function to generate responses that reflect a user's emotions in two-way real-time communication. For example, the system dynamically changes responses based on the user's emotion score. This makes it possible to generate responses that reflect the user's emotions.

[0086] The system builds a multilingual system in which the generation AI can handle sign language or finger spelling in different languages ​​during two-way real-time communication. For example, the system builds a system in which the generation AI can handle sign language and finger spelling in different languages ​​during two-way real-time communication. For example, a model that supports sign languages ​​such as English, Japanese, and French is developed. To build a multilingual system, the generation AI collects sign language data in different languages ​​and trains the model. For example, a sign language model that supports multiple languages ​​is developed, realizing two-way real-time communication in multiple languages. The system also develops a system in which the generation AI can handle sign language and finger spelling in different languages ​​during two-way real-time communication. For example, the system translates the meaning of sign language in real time, realizing two-way communication in multiple languages. This makes it possible to handle sign language and finger spelling in different languages.

[0087] The system displays a user's emotions in real time during two-way real-time communication, improving the quality of communication. For example, the system is constructed to use a generative AI to display a user's emotions in real time during two-way real-time communication. For example, the system analyzes the user's facial expressions and displays an emotion score on a display. The system also develops a system that improves the quality of communication during two-way real-time communication by displaying the user's emotions in real time. For example, the system displays the emotions used when using sign language, making it easier for the other party to understand those emotions. The system is also constructed to use a generative AI to display a user's emotions in real time during two-way real-time communication, improving the quality of communication. For example, the system displays the user's emotion score on a display, making it easier for the other party to understand those emotions. This displays the user's emotions in real time and improves the quality of communication.

[0088] The system uses an emotion estimation function to add effects to responses according to the user's emotions in two-way real-time communication. For example, the system uses the emotion estimation function to build a system that adds effects to responses according to the user's emotions in two-way real-time communication. For example, a bright effect is used for positive emotions and a dark effect is used for negative emotions. The system also develops an algorithm in which a generation AI uses the emotion estimation function to add effects to responses according to the user's emotions in two-way real-time communication. For example, effects such as reverb and echo are added to responses based on an emotion score. The system also develops a system that uses the emotion estimation function to add effects to responses according to the user's emotions in two-way real-time communication. For example, the effect of a response is dynamically changed based on the user's emotion score. This makes it possible to add effects to responses according to the user's emotions.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The recognition unit not only recognizes sign language and finger spelling movements, but can also measure the temperature and humidity of the user's hands and analyze their condition. For example, if the temperature of the hands is high, it determines that the user may be nervous and adjusts the recognition accuracy. If the humidity of the hands is high, it determines that the user may be sweating and improves recognition accuracy by taking into account the slippage of hand movements. Furthermore, by collecting hand temperature and humidity data over a long period of time and analyzing changes in the user's hand condition, it is possible to achieve even more accurate recognition. This is expected to improve recognition accuracy by taking hand temperature and humidity into account.

[0091] The recognition unit can analyze not only the user's hand movements but also the hand muscle movements. For example, a sensor that measures hand muscle movements can be used to analyze sign language and finger spelling movements in more detail. Furthermore, based on the hand muscle movement data, the recognition unit can learn the user's hand movement patterns and improve recognition accuracy. Furthermore, the hand muscle movement data can be analyzed in real time to dynamically complement the sign language and finger spelling movements. This is expected to improve recognition accuracy by taking hand muscle movements into account.

[0092] The recognition unit can analyze not only hand movements but also the user's gaze. For example, it uses gaze tracking technology to analyze the direction the user is looking and complement the meaning of sign language or finger spelling. It can also estimate the user's intention based on gaze movement data, improving recognition accuracy. Furthermore, it can analyze gaze movement data in real time and dynamically complement sign language or finger spelling movements. This is expected to improve recognition accuracy by taking gaze movement into account.

[0093] The recognition unit can use the emotion estimation function to analyze the emotion of a user when using sign language or fingerspelling, and complement the meaning of the sign language or fingerspelling based on that emotion. For example, the emotion estimation function can be used to analyze the user's facial expression when using sign language and calculate an emotion score. The emotion estimation function can also be used to develop an algorithm that complements the meaning of sign language or fingerspelling. For example, the meaning of sign language can be complemented based on the emotion of the user when using sign language, providing a more accurate translation. The emotion estimation function can also be used to build a system that analyzes the user's emotion when using sign language or fingerspelling in real time, and dynamically complements the meaning of sign language or fingerspelling based on that emotion. For example, the meaning of sign language can be adjusted according to changes in the user's emotion. This makes it possible to complement the meaning of sign language or fingerspelling based on the user's emotion.

[0094] The recognition unit can simultaneously recognize sign language and finger spellings in different languages, building a multilingual system. For example, in order for the generation AI to simultaneously recognize sign language and finger spellings in different languages, multilingual training data is collected and a model is trained. For example, sign language data from English, Japanese, French, etc. is used to train the model. In addition, an algorithm is developed to simultaneously recognize sign language and finger spellings in different languages, and the generation AI builds a multilingual system. For example, it automatically detects the sign language and provides an appropriate translation. In addition, the generation AI recognizes sign language and finger spellings in different languages ​​in real time, building a multilingual system. For example, when a user uses sign language in a different language, the generation AI automatically switches the language for recognition. This allows sign language and finger spellings in different languages ​​to be recognized simultaneously.

[0095] The recognition unit uses a glove-type sensor to directly measure hand movements, enabling recognition without using a camera. For example, a system can be built in which hand movements are measured directly using a glove-type sensor, and a generation AI uses that data to recognize sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy and inputs the data into the generation AI. We will also develop technology to measure hand movements using a glove-type sensor, allowing the generation AI to recognize sign language or fingerspelling without using a camera. For example, a sensor attached to the glove measures hand movements in real time, and the generation AI analyzes the data. We will also develop a system in which hand movements are measured using a glove-type sensor, and a generation AI uses that data to recognize sign language or fingerspelling. For example, a sensor built into the glove measures hand movements with high accuracy, and the generation AI analyzes the data. This makes it possible to recognize hand movements with high accuracy using a glove-type sensor.

[0096] The recognition unit can use the emotion estimation function to display the user's emotion when using sign language or fingerspelling in real time, thereby improving the quality of communication. For example, a system is constructed using the emotion estimation function to display the user's emotion when using sign language or fingerspelling in real time. For example, the user's facial expression is analyzed and an emotion score is displayed on a display. A system is also developed that improves the quality of communication by displaying the user's emotion in real time. For example, the emotion when using sign language is displayed to make it easier for the other party to understand that emotion. A system is also constructed using the emotion estimation function to display the user's emotion when using sign language or fingerspelling in real time, thereby improving the quality of communication. For example, the user's emotion score is displayed on a display to make it easier for the other party to understand that emotion. In this way, the user's emotion is displayed in real time, improving the quality of communication.

[0097] The conversion unit is able to select appropriate expressions by taking context into consideration when converting the meaning of sign language or finger spelling into text. For example, when the generation AI converts the meaning of sign language or finger spelling into text, an algorithm is developed that analyzes the context and selects appropriate expressions. For example, appropriate words and phrases are selected by taking the context before and after the sign language into consideration. Furthermore, in order to convert the meaning of sign language or finger spelling into text by taking context into consideration, the generation AI analyzes the context using natural language processing technology. For example, the context before and after the sign language is analyzed and appropriate expressions are selected. Furthermore, a system is built that selects appropriate expressions by taking context into consideration when the generation AI converts the meaning of sign language or finger spelling into text. For example, the context before and after the sign language is analyzed and appropriate words and phrases are selected. This makes it possible to select appropriate expressions by taking context into consideration.

[0098] When converting the meaning of sign language or finger spelling into text, the conversion unit can refer to the user's past utterance history and provide consistent expressions. For example, when the generation AI converts the meaning of sign language or finger spelling into text, it references the user's past utterance history and builds a system that provides consistent expressions. For example, it selects an appropriate expression based on the user's past utterance data. In addition, in order to refer to the user's past utterance history and provide consistent expressions, the generation AI builds a utterance history database. For example, it collects the user's past utterance data and selects an appropriate expression. In addition, when the generation AI converts the meaning of sign language or finger spelling into text, it references the user's past utterance history and develops an algorithm that provides consistent expressions. For example, it selects an appropriate expression based on the user's past utterance data. This makes it possible to refer to the user's past utterance history and provide consistent expressions.

[0099] The conversion unit can use the emotion estimation function to select expressions that reflect the user's emotions when converting the meaning of sign language or finger spelling into text. For example, a system can be built that uses the emotion estimation function to select expressions that reflect the user's emotions when converting the meaning of sign language or finger spelling into text. For example, an appropriate expression can be selected based on the user's emotion score. In addition, an algorithm can be developed that uses the emotion estimation function to select expressions that reflect the user's emotions when the generation AI converts the meaning of sign language or finger spelling into text. For example, an appropriate expression can be selected based on the user's emotion score. In addition, a system can be developed that uses the emotion estimation function to select expressions that reflect the user's emotions when converting the meaning of sign language or finger spelling into text. For example, an appropriate expression can be selected based on the user's emotion score. This makes it possible to select expressions that reflect the user's emotions.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The recognition unit recognizes sign language or finger spelling. For example, a camera is used to capture sign language movements and recognize the video data. Finger spelling movements can also be recognized using a sensor. Furthermore, the recognition unit can recognize sign language or finger spelling movements in real time. Step 2: The analysis unit analyzes the sign language or fingerspelling recognized by the recognition unit. For example, the generation AI analyzes the sign language movements and understands their meaning. The generation AI can also analyze the fingerspelling movements and understand their meaning. Furthermore, the analysis unit can analyze the sign language or fingerspelling movements in real time. Step 3: The conversion unit converts the meaning of the sign language or finger spelling analyzed by the analysis unit into text or audio. For example, the generation AI converts the meaning of the sign language into text and displays it on a display. The generation AI can also convert the meaning of the finger spelling into audio and play it through a speaker. Furthermore, the conversion unit can convert the meaning of the sign language or finger spelling into text or audio in real time.

[0102] 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.

[0103] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0108] 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.

[0109] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0110] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0117] 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.

[0118] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 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.

[0122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0123] 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.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0125] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0131] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0132] 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.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0134] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0138] 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.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] 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.

[0142] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0143] 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.

[0144] 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.

[0145] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0146] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0147] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0148] 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.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0150] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0151] 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.

[0152] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0153] 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.

[0154] 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).

[0155] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0156] 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."

[0157] 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.

[0158] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0163] The hardware resource that executes the specific process 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 process may be a single processor.

[0164] 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.

[0165] 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.

[0166] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0167] 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.

[0168] 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. [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a recognition unit that recognizes sign language or finger spelling; an analysis unit that analyzes the sign language or the fingerspelling recognized by the recognition unit; a conversion unit that converts the meaning of the sign language or the fingerspelling analyzed by the analysis unit into characters or voice. A system characterized by:

2. The recognition unit Learns the user's individual hand shape or movement habits to improve individually optimized recognition accuracy 2. The system of claim 1.

3. The recognition unit Analyze not only the hand movements but also the facial expressions or body movements to understand the meaning more accurately.

2. The system of claim 1.

4. The recognition unit The user's emotions when using the sign language or the fingerspelling are analyzed, and the meaning of the sign language or the fingerspelling is complemented based on the emotions.

2. The system of claim 1.

5. The recognition unit Construct a multilingual system that simultaneously recognizes the sign language or finger spelling of different languages.

2. The system of claim 1.

6. The recognition unit The hand movements are directly measured using a glove-type sensor, and are recognized without using a camera.

2. The system of claim 1.

Images