System

Abstract

To provide appropriate support when a visually impaired person or a hearing impaired person acquires information and operates a device.SOLUTION: A system includes a voice conversion section, a text conversion section, a Braille conversion section, a navigation support section, a voice recognition control section, and a visual information interpretation section. The voice conversion section converts a text into a voice. The text conversion section converts a voice into a text. The Braille conversion section converts a text to Braille. The navigation support section provides real-time voice guidance and direction instructions. The voice recognition control section operates a device or an application through a voice command. The visual information interpretation section interprets visual information and aids explanation of environment and recognition of an object.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies do not provide sufficient assistance to visually and hearing impaired people when obtaining information and operating devices, and there is room for improvement.

[0005] The system according to the embodiment aims to provide appropriate assistance to visually and hearing impaired people when they obtain information and operate devices. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech conversion unit, a text conversion unit, a Braille conversion unit, a navigation aid, a speech recognition control unit, and a visual information interpretation unit. The speech conversion unit converts text to speech. The text conversion unit converts speech to text. The Braille conversion unit converts text to Braille. The navigation aid provides real-time voice guidance and directions. The speech recognition control unit operates a device or application through voice commands. The visual information interpretation unit interprets visual information to help describe the environment and recognize objects. Effect of the Invention

[0007] The system according to the embodiment can provide appropriate assistance to visually impaired and hearing impaired people when they obtain information and operate devices. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The AI ​​assistant system according to the embodiment of the present invention is a system that provides support functions for the hearing impaired and the visually impaired. The system has a text-to-speech conversion function, a voice-to-text conversion function, a text-to-Braille conversion function, a navigation support function that provides real-time voice guidance and directional instructions, a voice recognition control function, and a function that interprets visual information to assist in the description of the environment and the recognition of objects. For example, the text-to-speech conversion function allows the hearing impaired to receive text information by voice. The voice-to-text conversion function allows the visually impaired to receive voice information in text. Furthermore, the text information to Braille conversion function allows the visually impaired to receive information in Braille. The navigation support function that provides real-time voice guidance and directional instructions supports the visually impaired to move safely. The voice recognition control function allows the user to operate devices and applications through voice commands. The function that interprets visual information to assist in the description of the environment and the recognition of objects makes it easier for the visually impaired to understand the surrounding environment. As a result, the AI ​​assistant system can provide various support to the hearing impaired and the visually impaired, improving the quality of daily life.

[0029] The AI ​​assistant system according to the embodiment includes a speech conversion unit, a text conversion unit, a Braille conversion unit, a navigation support unit, a speech recognition control unit, and a visual information interpretation unit. The speech conversion unit converts text into speech. For example, the speech conversion unit receives text as an input and generates speech using speech synthesis technology. The speech conversion unit can use, for example, a deep learning model such as WaveNet or Tacotron as a speech synthesis technology. The speech conversion unit can also evaluate the quality of the generated speech and make adjustments as necessary. For example, the speech conversion unit evaluates the naturalness and clarity of the speech and makes adjustments. The text conversion unit converts speech into text. For example, the text conversion unit receives speech as an input and generates text using speech recognition technology. The text conversion unit can use, for example, a deep learning model such as DeepSpeech or Kaldi as a speech recognition technology. The text conversion unit can also evaluate the accuracy of the generated text and make corrections as necessary. For example, the text conversion unit presents the results of speech recognition to a human proofreader and makes corrections. The braille conversion unit converts text into braille. For example, the braille conversion unit receives text as an input and generates braille using a braille conversion algorithm. The braille conversion unit can use, for example, standards such as Braille ASCII and Unified English Braille as the braille conversion algorithm. The braille conversion unit can also evaluate the accuracy of the generated braille and make corrections as necessary. For example, the braille conversion unit evaluates the legibility and accuracy of the braille and makes adjustments. The navigation support unit provides real-time voice guidance and direction instructions. For example, the navigation support unit receives GPS data as an input and identifies the user's current location. The navigation support unit calculates the optimal route to the user's destination using, for example, map data. The navigation support unit also provides real-time voice guidance to the user using voice synthesis technology. For example, the navigation support unit provides voice instructions to the user such as "Turn right at the next intersection."The voice recognition control unit operates a device or application through a voice command. For example, the voice recognition control unit receives a user's voice command as an input and interprets the command using a voice recognition technology. The voice recognition control unit can use services such as Google (registered trademark) Speech-to-Text and Amazon (registered trademark) Transcribe as voice recognition technology. The voice recognition control unit also operates a device or application based on the interpreted command. For example, the voice recognition control unit starts a music player app and plays music based on the user's command "play music". The visual information interpretation unit interprets visual information and assists in describing the environment and recognizing objects. For example, the visual information interpretation unit receives video data from a camera as an input and recognizes objects using image recognition technology. The visual information interpretation unit can use deep learning models such as YOLO and Faster R-CNN as image recognition technology. The visual information interpretation unit also provides a description of the environment to the user based on the recognized object. For example, the visual information interpretation unit provides a warning to the user by voice, such as "there is an obstacle ahead." As a result, the AI ​​assistant system according to the embodiment can provide a variety of assistance to people with hearing or visual impairments, improving the quality of their daily lives.

[0030] The speech conversion unit converts text into speech. For example, the speech conversion unit receives text as input and generates speech using speech synthesis technology. For example, the speech conversion unit can use deep learning models such as WaveNet and Tacotron as speech synthesis technology. These models have the ability to generate natural and fluent speech by considering the context and emotions of the text. Specifically, WaveNet provides high-quality speech by directly generating speech waveforms, while Tacotron goes through a process of converting text into a spectrogram and converting it into speech. The speech conversion unit can also evaluate the quality of the generated speech and make adjustments as necessary. For example, the speech conversion unit evaluates the naturalness and clarity of the speech and makes adjustments. The evaluation includes parameters such as the pitch, speed, and intonation of the speech, and optimizing these provides a speech that is easier to hear. The speech conversion unit can also customize the gender and voice quality of the speech according to the user's preferences. This allows the speech conversion unit to provide individualized speech output for the user, achieving a more personalized experience. Furthermore, the speech conversion unit can also support multiple languages, converting texts in different languages ​​into appropriate speech to accommodate international users. This allows the speech conversion unit to provide high-quality speech output to a wide range of users, reducing communication barriers.

[0031] The text conversion unit converts speech to text. For example, the text conversion unit receives speech as input and generates text using speech recognition technology. For example, the text conversion unit can use deep learning models such as DeepSpeech and Kaldi as speech recognition technology. These models achieve high-precision speech recognition by learning large amounts of speech data. Specifically, DeepSpeech is an end-to-end speech recognition model that generates text directly from speech waveforms. On the other hand, Kaldi is a modularized speech recognition system that operates by combining multiple components such as acoustic models, language models, and decoders. The text conversion unit can also evaluate the accuracy of the generated text and make corrections if necessary. For example, the text conversion unit presents the results of speech recognition to a human proofreader and makes corrections. This allows the text conversion unit to improve the accuracy of speech recognition and reduce misrecognition. The text conversion unit can also provide personalized speech recognition by adapting to the speech patterns and accents of specific users. Furthermore, since the text conversion unit can convert speech to text in real time, it is expected to be used in situations such as meetings and lectures. This allows the text conversion unit to provide the user with fast and accurate text conversion, thereby improving communication efficiency.

[0032] The braille converter converts text into braille. For example, the braille converter receives text as input and generates braille using a braille conversion algorithm. The braille converter can use standards such as Braille ASCII and Unified English Braille as the braille conversion algorithm. These standards provide rules for making braille easier to read for visually impaired people. Specifically, Braille ASCII specifies rules for converting English alphabets and numbers into braille, and Unified English Braille provides rules for converting more complex text, including English grammar and punctuation, into braille. The braille converter can also evaluate the accuracy of the generated braille and make corrections as necessary. For example, the braille converter evaluates the legibility and accuracy of the braille and makes adjustments. The evaluation includes parameters such as the placement and spacing of braille and the height of the dots, and by optimizing these, braille that is easier to read is provided. The braille converter can also customize the format of braille according to the user's preferences. This allows the Braille converter to provide individualized Braille output to the user, realizing a more personalized experience. Furthermore, the Braille converter can also support multiple languages, and can convert text in different languages ​​into appropriate Braille to accommodate international users. This allows the Braille converter to provide high-quality Braille output to a wide range of users, reducing barriers to information access.

[0033] The navigation support unit provides real-time voice guidance and direction instructions. For example, the navigation support unit receives GPS data as input and identifies the user's current location. The navigation support unit uses, for example, map data to calculate the optimal route to the user's destination. This also takes into account information such as road congestion, traffic regulations, and pedestrian-only roads. The navigation support unit also uses voice synthesis technology to provide real-time voice guidance to the user. For example, the navigation support unit provides instructions to the user by voice, such as "Turn right at the next intersection." Furthermore, the navigation support unit can monitor the user's moving speed and direction in real time and update the guidance as necessary. For example, if the user deviates from the planned route, the navigation support unit immediately calculates a new route and provides re-guidance. The navigation support unit can also provide guidance specialized for visually impaired people. For example, by providing voice guidance for pedestrian signals and location information of obstacles, the navigation support unit can support the safe movement of visually impaired people. As a result, the navigation support unit can provide quick and accurate direction instructions to the user, improving the efficiency and safety of movement. Furthermore, the navigation assistant can learn the user's past travel history and provide personalized guidance, making the user's travel experience more comfortable and convenient.

[0034] The voice recognition control unit operates a device or application through voice commands. For example, the voice recognition control unit receives a user's voice command as an input and interprets the command using voice recognition technology. The voice recognition control unit can use services such as Google Speech-to-Text and Amazon Transcribe as voice recognition technology. These services provide highly accurate voice recognition and can accurately interpret the user's voice command. Specifically, the voice recognition control unit receives a user's command "play music," launches a music player application, and plays music. The voice recognition control unit can also receive a user's command "tell me the weather," obtain weather information, and provide it by voice. Furthermore, the voice recognition control unit can interpret multiple commands consecutively and perform complex operations. For example, if a user issues a consecutive command such as "tell me tomorrow's schedule, then send me an email," the voice recognition control unit first launches a calendar application to check the schedule, and then launches an email application to send the specified email. In this way, the voice recognition control unit can provide the user with an intuitive and efficient means of operation, making it more convenient to use devices and applications. The voice recognition control unit can also learn the characteristics of the user's voice and speech patterns to provide personalized voice recognition, allowing the voice recognition control unit to realize flexible operations according to the user's needs and improve the user experience.

[0035] The visual information interpretation unit interprets visual information and assists in describing the environment and recognizing objects. For example, the visual information interpretation unit receives video data from a camera as input and recognizes objects using image recognition technology. The visual information interpretation unit can use deep learning models such as YOLO and Faster R-CNN as image recognition technology. These models realize high-speed and high-precision object recognition and provide environmental information in real time. Specifically, YOLO uses a single neural network to analyze the entire image at once and predicts the object's position and class simultaneously. On the other hand, Faster R-CNN uses a region proposal network to generate candidate regions for objects and predicts the object's class based on the candidate regions. The visual information interpretation unit provides a description of the environment to the user based on the recognized objects. For example, the visual information interpretation unit provides a voice warning to the user such as "There is an obstacle ahead." The visual information interpretation unit can also provide detailed descriptions of the type and location of objects. For example, by providing specific information such as "There is a red car on the right" or "There is a pedestrian on the left," the system supports the user's safe movement. Furthermore, the visual information interpretation unit can learn the user's past actions and environmental information and provide personalized explanations. This allows the visual information interpretation unit to provide more appropriate and useful information to the user, improving the quality of daily life. In addition, the visual information interpretation unit can flexibly respond to different environments and situations, making it a very useful support tool for the visually impaired.

[0036] The barrier-free communication unit can provide sign language recognition and sign language translation. The barrier-free communication unit, for example, uses sign language recognition technology to recognize the hand movements of a user and convert the sign language into text. For example, the barrier-free communication unit captures the hand movements with a camera and recognizes the sign language using a deep learning model. The barrier-free communication unit can also convert text into sign language using sign language translation technology. For example, the barrier-free communication unit receives text as input and generates a sign language animation. This allows smooth communication between the hearing impaired and the hearing-able.

[0037] The accessible content providing unit can improve the accessibility of web pages and documents. For example, the accessible content providing unit evaluates the accessibility of a web page and suggests improvements. For example, the accessible content providing unit analyzes the HTML code of a web page and performs an evaluation based on accessibility standards. The accessible content providing unit can also provide tools for improving the accessibility of documents. For example, the accessible content providing unit analyzes the format of a document and makes corrections based on accessibility standards. This can support the provision of content that is suitable for people with disabilities.

[0038] The customization setting unit can adjust the tone, speed, and display settings of the voice for each user. For example, the customization setting unit can adjust the tone and speed of the voice according to the user's preferences. For example, the customization setting unit can generate voice using the voice of a voice actor preferred by the user. The customization setting unit can also adjust the settings of the Braille display. For example, the customization setting unit can adjust the size and spacing of the Braille depending on the degree of the user's visual impairment. This makes it possible to provide services tailored to the needs of each individual user.

[0039] The predictive input unit can predict the operation desired by the user in response to a command input by voice recognition. The predictive input unit, for example, analyzes the user's voice command and predicts the next operation to be performed. For example, when the user says "play the next song," the predictive input unit predicts and suggests the next song to be played. The predictive input unit can also make predictions based on the user's past operation history. For example, the predictive input unit analyzes the history of songs that the user has played in the past and suggests the next song to be played. This makes it possible to predict the operation intended by the user and perform efficient operations.

[0040] The high-precision sign language recognition unit can recognize facial expressions and body movements in addition to hand movements of the sign language. For example, the high-precision sign language recognition unit captures the user's hand movements, facial expressions, and body movements with a camera and recognizes the sign language using a deep learning model. For example, the high-precision sign language recognition unit recognizes the sign language taking into account not only hand movements but also facial expressions and body movements. In addition, the high-precision sign language recognition unit can convert the recognized sign language into text. This improves the recognition accuracy of the sign language, enabling more natural communication.

[0041] The voice conversion unit can generate voice using the voice of a voice actor preferred by the user. For example, the voice conversion unit converts text to voice using voice data of a voice actor selected by the user. The voice conversion unit can also evaluate the quality of the generated voice and make adjustments as necessary. This allows for more friendly voice guidance by generating voice in a voice preferred by the user.

[0042] The speech conversion unit can automatically select an appropriate intonation based on the context of the sentence during speech conversion. The speech conversion unit uses natural language processing technology, for example, to analyze the context of the sentence and select an appropriate intonation. For example, the speech conversion unit analyzes the structure and meaning of the sentence and determines the intonation. A deep learning model can be used as the natural language processing technology. The speech conversion unit applies an appropriate intonation based on the analysis result. For example, in the case of a question, a rising intonation is applied. Also, in the case of an exclamation, an emphasized intonation can be applied. This makes it possible to select an appropriate intonation according to the context of the sentence.

[0043] During voice conversion, the voice conversion unit can select the optimal voice generation method by referring to the user's past voice conversion history. The voice conversion unit, for example, uses a database for storing and referring to the user's past voice conversion history. For example, the voice conversion unit stores and analyzes voice data generated by the user in the past. The voice conversion unit selects the optimal voice generation method based on the past voice conversion history. For example, voice is generated based on a tone that the user previously preferred. In addition, specific phrases that the user previously used can be used preferentially. This enables optimal voice generation based on the user's past voice conversion history.

[0044] The voice conversion unit can apply a region-specific accent during voice conversion, taking into account the geographical location information of the user. The voice conversion unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the voice conversion unit identifies the user's current location and applies an accent for that region. The voice conversion unit uses a voice synthesis technique to apply a region-specific accent. For example, the voice conversion unit can apply a Kansai dialect accent to a user in the Kansai region. Also, the voice conversion unit can apply a Tohoku dialect accent to a user in the Tohoku region. This allows for more natural voice guidance by applying a region-specific accent.

[0045] During the voice conversion, the voice conversion unit can analyze the user's social media activity and generate voice based on related topics. For example, the voice conversion unit collects social media data to analyze the user's social media activity. For example, the voice conversion unit identifies topics that the user has recently been interested in and generates voice based on the topics. The voice conversion unit uses natural language processing techniques to analyze the social media activity. For example, the voice conversion unit analyzes the content posted by the user and extracts related topics. This makes it possible to generate voice based on the user's interests.

[0046] The text conversion unit can automatically insert appropriate punctuation marks based on the context of the speech during text conversion. The text conversion unit uses natural language processing technology, for example, to analyze the context of the speech and insert appropriate punctuation marks. For example, the text conversion unit analyzes the structure and meaning of the speech and determines the punctuation marks. A deep learning model can be used as the natural language processing technology. The text conversion unit inserts appropriate punctuation marks based on the analysis results. For example, in the case of a question sentence, a question mark can be inserted at the end of the sentence. Also, in the case of an exclamation sentence, an exclamation mark can be inserted at the end of the sentence. This makes it possible to insert appropriate punctuation marks according to the context of the speech.

[0047] The text conversion unit can select the optimal text generation method by referring to the user's past text conversion history during text conversion. The text conversion unit, for example, uses a database for storing and referring to the user's past text conversion history. For example, the text conversion unit stores and analyzes text data generated by the user in the past. The text conversion unit selects the optimal text generation method based on the past text conversion history. For example, text is generated based on an expression method that the user has preferred in the past. In addition, specific phrases that the user has used in the past can be used preferentially. This enables optimal text generation based on the user's past text conversion history.

[0048] The text conversion unit can apply a region-specific expression during text conversion, taking into account the geographical location information of the user. The text conversion unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the text conversion unit identifies the user's current location and applies an expression for that region. The text conversion unit uses natural language processing technology to apply the region-specific expression. For example, the text conversion unit can apply an expression in Kansai dialect to a user in the Kansai region, and an expression in Tohoku dialect to a user in the Tohoku region. This allows more natural text generation by applying a region-specific expression.

[0049] During text conversion, the text conversion unit can analyze the user's social media activity and generate text based on related topics. For example, the text conversion unit collects social media data to analyze the user's social media activity. For example, the text conversion unit identifies topics that the user has recently been interested in and generates text based on the topics. The text conversion unit uses natural language processing techniques to analyze the social media activity. For example, the text conversion unit analyzes the content posted by the user and extracts related topics. This makes it possible to generate text based on the user's interests.

[0050] The braille conversion unit can automatically select an appropriate braille expression based on the context of the text during braille conversion. The braille conversion unit uses natural language processing technology, for example, to analyze the context of the text and select an appropriate braille expression. For example, the braille conversion unit analyzes the structure and meaning of the text and determines the braille expression. A deep learning model can be used as the natural language processing technology. The braille conversion unit applies an appropriate braille expression based on the analysis result. For example, in the case of a question sentence, braille including a question mark is generated. Also, in the case of an exclamation sentence, braille including an exclamation mark can be generated. This makes it possible to select an appropriate braille expression according to the context of the text.

[0051] The braille conversion unit can select the optimal braille generation method by referring to the user's past braille conversion history at the time of braille conversion. The braille conversion unit uses, for example, a database for storing and referring to the user's past braille conversion history. For example, the braille conversion unit stores and analyzes braille data generated by the user in the past. The braille conversion unit selects the optimal braille generation method based on the past braille conversion history. For example, braille is generated based on an expression method that the user previously preferred. In addition, a specific phrase that the user previously used can be preferentially used. This enables optimal braille generation based on the user's past braille conversion history.

[0052] The braille conversion unit can apply a region-specific braille expression in consideration of the geographical location information of the user during braille conversion. The braille conversion unit uses, for example, GPS data to acquire the geographical location information of the user. For example, the braille conversion unit identifies the user's current location and applies the braille expression for that region. The braille conversion unit uses natural language processing technology to apply the region-specific braille expression. For example, the braille conversion unit can apply a braille expression in Kansai dialect to a user in the Kansai region. Also, the braille conversion unit can apply a braille expression in Tohoku dialect to a user in the Tohoku region. This allows more natural braille generation by applying a braille expression specific to the region.

[0053] The Braille conversion unit can analyze the user's social media activity and generate Braille based on related topics during Braille conversion. The Braille conversion unit, for example, collects social media data to analyze the user's social media activity. For example, the Braille conversion unit identifies topics that the user has recently been interested in and generates Braille based on the topics. The Braille conversion unit uses natural language processing technology to analyze the social media activity. For example, the Braille conversion unit analyzes the content posted by the user and extracts related topics. This makes it possible to generate Braille based on the user's interests.

[0054] When providing navigation support, the navigation support unit can select an optimal guidance method by referring to the user's past movement history. The navigation support unit, for example, uses a database for storing and referring to the user's past movement history. For example, the navigation support unit stores and analyzes routes the user has traveled in the past. The navigation support unit selects an optimal guidance method based on the past movement history. For example, the navigation support unit proposes an optimal guidance method based on routes the user has used in the past. In addition, a route that avoids congestion can be proposed based on the user's past movement history. This makes it possible to provide optimal guidance based on the user's past movement history.

[0055] The navigation support unit can provide an optimal route by referring to real-time traffic information during navigation support. The navigation support unit uses traffic information data to obtain real-time traffic information, for example. For example, the navigation support unit obtains and analyzes traffic congestion information and the operation status of public transportation. The navigation support unit calculates an optimal route based on the real-time traffic information. For example, the navigation support unit proposes a route that avoids traffic congestion. In addition, the navigation support unit can propose an optimal route taking into account the operation status of public transportation. This makes it possible to provide an optimal route based on real-time traffic information.

[0056] The navigation support unit can provide region-specific guidance by taking into account the geographical location information of the user when providing navigation support. The navigation support unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the navigation support unit identifies the user's current location and provides region-specific guidance. The navigation support unit uses voice synthesis technology to provide region-specific guidance. For example, the navigation support unit can provide Kansai dialect guidance to a user in the Kansai region, and Tohoku dialect guidance to a user in the Tohoku region. This allows for more natural navigation by providing region-specific guidance.

[0057] During navigation assistance, the navigation assistance unit can analyze the user's social media activity and provide guidance based on related topics. For example, the navigation assistance unit collects social media data to analyze the user's social media activity. For example, the navigation assistance unit identifies topics that the user has recently been interested in and provides guidance based on the topics. The navigation assistance unit uses natural language processing techniques to analyze the social media activity. For example, the navigation assistance unit analyzes the content posted by the user and extracts related topics. This enables guidance based on the user's interests.

[0058] The voice recognition control unit can select the optimal interpretation method by referring to the user's past voice command history during voice recognition. The voice recognition control unit, for example, uses a database for storing and referring to the user's past voice command history. For example, the voice recognition control unit stores and analyzes voice commands used by the user in the past. The voice recognition control unit selects the optimal interpretation method based on the past voice command history. For example, it preferentially interprets specific phrases used by the user in the past. In addition, the voice recognition control unit can analyze the user's past voice command history and select the most efficient interpretation method. This enables optimal interpretation based on the user's past voice command history.

[0059] The voice recognition control unit can automatically select an appropriate command based on the context of the voice during voice recognition. The voice recognition control unit uses natural language processing technology, for example, to analyze the context of the voice and select an appropriate command. For example, the voice recognition control unit analyzes the structure and meaning of the voice and determines the command. A deep learning model can be used as the natural language processing technology. The voice recognition control unit selects an appropriate command based on the analysis result. For example, in the case of a question sentence, an appropriate response command is selected. Also, in the case of an exclamation sentence, a command reflecting the emotion can be selected. This makes it possible to select an appropriate command according to the context of the voice.

[0060] The voice recognition control unit can apply region-specific commands during voice recognition, taking into account the geographical location information of the user. The voice recognition control unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the voice recognition control unit identifies the current location of the user and applies region-specific commands. The voice recognition control unit uses natural language processing technology to apply region-specific commands. For example, the voice recognition control unit can apply Kansai dialect voice commands to a user in the Kansai region. Also, the voice recognition control unit can apply Tohoku dialect voice commands to a user in the Tohoku region. This allows for more natural voice recognition by applying region-specific commands.

[0061] During voice recognition, the voice recognition control unit can analyze the user's social media activities and interpret the command based on related topics. For example, the voice recognition control unit collects social media data to analyze the user's social media activities. For example, the voice recognition control unit identifies topics that the user has recently been interested in and interprets the command based on the topics. The voice recognition control unit uses natural language processing techniques to analyze the social media activities. For example, the voice recognition control unit analyzes the content of the user's posts and extracts related topics. This enables the interpretation of the voice command based on the user's interests.

[0062] When interpreting visual information, the visual information interpretation unit can select the optimal interpretation method by referring to the user's past visual information interpretation history. The visual information interpretation unit, for example, uses a database for storing and referring to the user's past visual information interpretation history. For example, the visual information interpretation unit stores and analyzes visual information previously interpreted by the user. The visual information interpretation unit selects the optimal interpretation method based on the past visual information interpretation history. For example, it preferentially interprets a specific pattern previously interpreted by the user. In addition, the user's past visual information interpretation history can be analyzed to select the most efficient interpretation method. This enables optimal interpretation based on the user's past visual information interpretation history.

[0063] The visual information interpretation unit can automatically select an appropriate interpretation based on the context of the environment when interpreting visual information. The visual information interpretation unit uses, for example, environmental recognition technology to analyze the context of the environment and select an appropriate interpretation. For example, the visual information interpretation unit analyzes the structure and meaning of the environment and determines the interpretation. As the environmental recognition technology, deep learning models such as YOLO and Faster R-CNN can be used. The visual information interpretation unit selects an appropriate interpretation based on the analysis result. For example, when indoors, indoor objects can be interpreted preferentially. Also, when outdoors, outdoor objects can be interpreted preferentially. This enables appropriate interpretation according to the context of the environment.

[0064] The visual information interpretation unit can provide a region-specific interpretation by taking into account the geographical location information of the user when interpreting visual information. The visual information interpretation unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the visual information interpretation unit identifies the user's current location and provides an interpretation specific to the region. The visual information interpretation unit uses an environmental recognition technology to provide an interpretation specific to the region. For example, the visual information interpretation unit can preferentially interpret objects in the Kansai region for a user in the Kansai region. Also, the visual information interpretation unit can preferentially interpret objects in the Tohoku region for a user in the Tohoku region. This allows for more natural interpretation of visual information by providing an interpretation specific to the region.

[0065] When interpreting visual information, the visual information interpretation unit can analyze the user's social media activity and provide an interpretation based on related topics. The visual information interpretation unit, for example, collects social media data to analyze the user's social media activity. For example, the visual information interpretation unit identifies topics that the user has recently been interested in and provides an interpretation based on the topics. The visual information interpretation unit uses natural language processing techniques to analyze the social media activity. For example, the visual information interpretation unit analyzes the content posted by the user and extracts related topics. This enables visual information interpretation based on the user's interests.

[0066] When recognizing a sign language, the barrier-free communication unit can select an optimal interpretation method by referring to the user's past sign language history. The barrier-free communication unit, for example, uses a database for storing and referring to the user's past sign language history. For example, the barrier-free communication unit stores and analyzes sign languages ​​used by the user in the past. The barrier-free communication unit selects an optimal interpretation method based on the past sign language history. For example, it gives priority to interpreting specific phrases used by the user in the past. In addition, the barrier-free communication unit can analyze the user's past sign language history and select the most efficient interpretation method. This enables optimal interpretation based on the user's past sign language history.

[0067] The barrier-free communication unit can apply a region-specific sign language in consideration of the geographical location information of the user when recognizing the sign language. The barrier-free communication unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the barrier-free communication unit identifies the user's current location and applies the region-specific sign language. The barrier-free communication unit uses natural language processing technology to apply the region-specific sign language. For example, the barrier-free communication unit can apply Kansai dialect sign language to a user in the Kansai region. Also, the barrier-free communication unit can apply Tohoku dialect sign language to a user in the Tohoku region. In this way, applying the region-specific sign language enables more natural sign language recognition.

[0068] When providing content, the accessible content providing unit can select the optimal display method by referring to the user's past content browsing history. The accessible content providing unit, for example, uses a database for storing and referring to the user's past content browsing history. For example, the accessible content providing unit stores and analyzes content previously viewed by the user. The accessible content providing unit selects the optimal display method based on the past content browsing history. For example, the accessible content providing unit provides content based on a display method previously preferred by the user. In addition, a specific format previously used by the user can be preferentially used. This enables optimal display based on the user's past content browsing history.

[0069] The accessible content providing unit can provide region-specific content by taking into consideration the geographical location information of the user when providing content. The accessible content providing unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the accessible content providing unit identifies the user's current location and provides content specific to the region. The accessible content providing unit uses natural language processing technology to provide region-specific content. For example, the accessible content providing unit can provide content for the Kansai region to a user in the Kansai region. Also, the accessible content providing unit can provide content for the Tohoku region to a user in the Tohoku region. This allows content to be provided more naturally by providing content specific to the region.

[0070] The customization setting unit can select the optimal setting method by referring to the user's past setting history during customization setting. The customization setting unit, for example, uses a database for storing and referring to the user's past setting history. For example, the customization setting unit stores and analyzes settings used by the user in the past. The customization setting unit selects the optimal setting method based on the past setting history. For example, customization is provided based on settings that the user preferred in the past. Also, specific settings used by the user in the past can be used preferentially. This enables optimal settings based on the user's past setting history.

[0071] The customization setting unit can provide region-specific settings in consideration of the geographical location information of the user during customization setting. The customization setting unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the customization setting unit identifies the user's current location and provides settings specific to the region. The customization setting unit uses natural language processing technology to provide region-specific settings. For example, the customization setting unit can provide Kansai region settings to a user in the Kansai region. Also, the customization setting unit can provide Tohoku region settings to a user in the Tohoku region. This allows for more natural customization by providing region-specific settings.

[0072] The predictive input unit can select the optimal prediction method by referring to the user's past input history at the time of predictive input. The predictive input unit uses, for example, a database for storing and referring to the user's past input history. For example, the predictive input unit stores and analyzes contents input by the user in the past. The predictive input unit selects the optimal prediction method based on the past input history. For example, it predicts a specific phrase input by the user in the past with priority. In addition, the predictive input unit can analyze the user's past input history and select the most efficient prediction method. This enables optimal prediction based on the user's past input history.

[0073] The predictive input unit can provide a region-specific prediction in consideration of the geographical location information of the user at the time of predictive input. The predictive input unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the predictive input unit identifies the user's current location and provides a region-specific prediction. The predictive input unit uses natural language processing technology to provide a region-specific prediction. For example, the predictive input unit can provide a predictive input for the Kansai region to a user in the Kansai region. Also, the predictive input unit can provide a predictive input for the Tohoku region to a user in the Tohoku region. This allows for more natural predictive input by providing a region-specific prediction.

[0074] The high-precision sign language recognition unit can select the optimal interpretation method by referring to the user's past sign language history when recognizing a sign language. The high-precision sign language recognition unit, for example, uses a database for storing and referring to the user's past sign language history. For example, the high-precision sign language recognition unit stores and analyzes sign languages ​​used by the user in the past. The high-precision sign language recognition unit selects the optimal interpretation method based on the past sign language history. For example, it gives priority to interpreting specific phrases used by the user in the past. In addition, the high-precision sign language recognition unit can analyze the user's past sign language history and select the most efficient interpretation method. This enables optimal interpretation based on the user's past sign language history.

[0075] The high-precision sign language recognition unit can apply a region-specific sign language in consideration of the geographical location information of the user during sign language recognition. The high-precision sign language recognition unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the high-precision sign language recognition unit identifies the user's current location and applies the region-specific sign language. The high-precision sign language recognition unit uses natural language processing technology to apply the region-specific sign language. For example, the high-precision sign language recognition unit can apply Kansai dialect sign language to a user in the Kansai region. Also, the high-precision sign language recognition unit can apply Tohoku dialect sign language to a user in the Tohoku region. This allows for more natural sign language recognition by applying the region-specific sign language.

[0076] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0077] The AI ​​assistant system may further include a health management unit that monitors the user's health condition. The health management unit may, for example, measure the user's heart rate and blood pressure and issue an alert if an abnormality is detected. The health management unit may also record the user's amount of exercise and suggest an appropriate exercise plan. Furthermore, the health management unit may record the user's diet and provide advice on nutritional balance. This may support the user's health management and improve the quality of life.

[0078] The accessible content providing unit can further refer to the user's learning history to provide optimal learning content. For example, it can suggest what the user should study next based on what the user has studied in the past. The accessible content providing unit can also adjust the difficulty of the content according to the user's learning pace. Furthermore, the accessible content providing unit can customize the way content is displayed to suit the user's learning style. This can improve the user's learning efficiency.

[0079] The voice conversion unit can further apply a region-specific accent by taking into account the geographical location information of the user. For example, the voice conversion unit identifies the user's current location and applies an accent for that region. The voice conversion unit uses a voice synthesis technique to apply a region-specific accent. For example, the voice conversion unit can apply a Kansai dialect accent to a user in the Kansai region, and a Tohoku dialect accent to a user in the Tohoku region. This allows for more natural voice guidance by applying a region-specific accent.

[0080] The text conversion unit can further analyze the user's social media activities and generate text based on related topics. For example, the text conversion unit identifies topics that the user has recently been interested in and generates text based on the topics. The text conversion unit uses natural language processing techniques to analyze the social media activities. For example, the text conversion unit analyzes the content of the user's posts and extracts related topics. This enables text generation based on the user's interests. The text conversion unit can also select an optimal text generation method by referring to the user's past text conversion history. This enables optimal text generation based on the user's past text conversion history.

[0081] The navigation support unit can further select the optimal guidance method by referring to the user's past movement history. For example, the navigation support unit saves and analyzes routes that the user has traveled in the past. The navigation support unit selects the optimal guidance method based on the past movement history. For example, the navigation support unit can suggest the optimal guidance method based on routes that the user has used in the past. In addition, the navigation support unit can suggest routes that avoid congestion based on the user's past movement history. This makes it possible to provide optimal guidance based on the user's past movement history.

[0082] The process flow of the first embodiment will be briefly described below.

[0083] Step 1: The speech conversion unit converts text into speech. For example, the speech conversion unit receives text as input and generates speech using speech synthesis technology. For example, the speech conversion unit can use deep learning models such as WaveNet and Tacotron as the speech synthesis technology. The speech conversion unit can also evaluate the quality of the generated speech and make adjustments as necessary. For example, the speech conversion unit evaluates the naturalness and clarity of the speech and makes adjustments. Step 2: The text conversion unit converts the speech into text. For example, the text conversion unit receives speech as an input and generates text using speech recognition technology. For example, the text conversion unit can use a deep learning model such as DeepSpeech or Kaldi as the speech recognition technology. The text conversion unit can also evaluate the accuracy of the generated text and make corrections if necessary. For example, the text conversion unit presents the results of the speech recognition to a human proofreader for correction. Step 3: The Braille converter converts the text into Braille. For example, the Braille converter receives the text as input and generates Braille using a Braille conversion algorithm. For example, the Braille converter can use a standard such as Braille ASCII or Unified English Braille as the Braille conversion algorithm. The Braille converter can also evaluate the accuracy of the generated Braille and make corrections if necessary. For example, the Braille converter can evaluate the legibility and accuracy of the Braille and make adjustments. Step 4: The navigation assistance unit provides real-time voice guidance and direction instructions. For example, the navigation assistance unit receives GPS data as input and identifies the user's current location. The navigation assistance unit calculates an optimal route to the user's destination, for example, using map data. The navigation assistance unit also provides real-time voice guidance to the user using voice synthesis technology. For example, the navigation assistance unit provides voice instructions to the user such as "Turn right at the next intersection." Step 5: The voice recognition control unit operates a device or application through a voice command. For example, the voice recognition control unit receives a user's voice command as an input and interprets the command using a voice recognition technology. The voice recognition control unit can use services such as Google Speech-to-Text and Amazon Transcribe as the voice recognition technology. The voice recognition control unit also operates a device or application based on the interpreted command. For example, the voice recognition control unit launches a music player app and plays music based on the user's command "play music." Step 6: The visual information interpretation unit interprets the visual information and assists in describing the environment and recognizing objects. For example, the visual information interpretation unit receives video data from a camera as input and recognizes objects using image recognition technology. The visual information interpretation unit can use deep learning models such as YOLO and Faster R-CNN as image recognition technology. The visual information interpretation unit also provides a description of the environment to the user based on the recognized objects. For example, the visual information interpretation unit provides a voice warning to the user such as "There is an obstacle ahead."

[0084] (Example 2) The AI ​​assistant system according to the embodiment of the present invention is a system that provides support functions for the hearing impaired and the visually impaired. The system has a text-to-speech conversion function, a voice-to-text conversion function, a text-to-Braille conversion function, a navigation support function that provides real-time voice guidance and directional instructions, a voice recognition control function, and a function that interprets visual information to assist in the description of the environment and the recognition of objects. For example, the text-to-speech conversion function allows the hearing impaired to receive text information by voice. The voice-to-text conversion function allows the visually impaired to receive voice information in text. Furthermore, the text information to Braille conversion function allows the visually impaired to receive information in Braille. The navigation support function that provides real-time voice guidance and directional instructions supports the visually impaired to move safely. The voice recognition control function allows the user to operate devices and applications through voice commands. The function that interprets visual information to assist in the description of the environment and the recognition of objects makes it easier for the visually impaired to understand the surrounding environment. As a result, the AI ​​assistant system can provide various support to the hearing impaired and the visually impaired, improving the quality of daily life.

[0085] The AI ​​assistant system according to the embodiment includes a speech conversion unit, a text conversion unit, a Braille conversion unit, a navigation support unit, a speech recognition control unit, and a visual information interpretation unit. The speech conversion unit converts text into speech. For example, the speech conversion unit receives text as an input and generates speech using speech synthesis technology. The speech conversion unit can use, for example, a deep learning model such as WaveNet or Tacotron as a speech synthesis technology. The speech conversion unit can also evaluate the quality of the generated speech and make adjustments as necessary. For example, the speech conversion unit evaluates the naturalness and clarity of the speech and makes adjustments. The text conversion unit converts speech into text. For example, the text conversion unit receives speech as an input and generates text using speech recognition technology. The text conversion unit can use, for example, a deep learning model such as DeepSpeech or Kaldi as a speech recognition technology. The text conversion unit can also evaluate the accuracy of the generated text and make corrections as necessary. For example, the text conversion unit presents the results of speech recognition to a human proofreader and makes corrections. The braille conversion unit converts text into braille. For example, the braille conversion unit receives text as an input and generates braille using a braille conversion algorithm. The braille conversion unit can use, for example, standards such as Braille ASCII and Unified English Braille as the braille conversion algorithm. The braille conversion unit can also evaluate the accuracy of the generated braille and make corrections as necessary. For example, the braille conversion unit evaluates the legibility and accuracy of the braille and makes adjustments. The navigation support unit provides real-time voice guidance and direction instructions. For example, the navigation support unit receives GPS data as an input and identifies the user's current location. The navigation support unit calculates the optimal route to the user's destination using, for example, map data. The navigation support unit also provides real-time voice guidance to the user using voice synthesis technology. For example, the navigation support unit provides voice instructions to the user such as "Turn right at the next intersection."The voice recognition control unit operates a device or application through a voice command. For example, the voice recognition control unit receives a user's voice command as an input and interprets the command using voice recognition technology. The voice recognition control unit can use services such as Google Speech-to-Text and Amazon Transcribe as voice recognition technology. The voice recognition control unit also operates a device or application based on the interpreted command. For example, the voice recognition control unit starts a music player app and plays music based on the user's command "play music". The visual information interpretation unit interprets visual information and assists in describing the environment and recognizing objects. For example, the visual information interpretation unit receives video data from a camera as input and recognizes objects using image recognition technology. The visual information interpretation unit can use deep learning models such as YOLO and Faster R-CNN as image recognition technology. The visual information interpretation unit also provides a description of the environment to the user based on the recognized object. For example, the visual information interpretation unit provides a warning to the user by voice, such as "There is an obstacle ahead." As a result, the AI ​​assistant system according to the embodiment can provide a variety of assistance to people with hearing or visual impairments, improving the quality of their daily lives.

[0086] The speech conversion unit converts text into speech. For example, the speech conversion unit receives text as input and generates speech using speech synthesis technology. For example, the speech conversion unit can use deep learning models such as WaveNet and Tacotron as speech synthesis technology. These models have the ability to generate natural and fluent speech by considering the context and emotions of the text. Specifically, WaveNet provides high-quality speech by directly generating speech waveforms, while Tacotron goes through a process of converting text into a spectrogram and converting it into speech. The speech conversion unit can also evaluate the quality of the generated speech and make adjustments as necessary. For example, the speech conversion unit evaluates the naturalness and clarity of the speech and makes adjustments. The evaluation includes parameters such as the pitch, speed, and intonation of the speech, and optimizing these provides a speech that is easier to hear. The speech conversion unit can also customize the gender and voice quality of the speech according to the user's preferences. This allows the speech conversion unit to provide individualized speech output for the user, achieving a more personalized experience. Furthermore, the speech conversion unit can also support multiple languages, converting texts in different languages ​​into appropriate speech to accommodate international users. This allows the speech conversion unit to provide high-quality speech output to a wide range of users, reducing communication barriers.

[0087] The text conversion unit converts speech to text. For example, the text conversion unit receives speech as input and generates text using speech recognition technology. For example, the text conversion unit can use deep learning models such as DeepSpeech and Kaldi as speech recognition technology. These models achieve high-precision speech recognition by learning large amounts of speech data. Specifically, DeepSpeech is an end-to-end speech recognition model that generates text directly from speech waveforms. On the other hand, Kaldi is a modularized speech recognition system that operates by combining multiple components such as acoustic models, language models, and decoders. The text conversion unit can also evaluate the accuracy of the generated text and make corrections if necessary. For example, the text conversion unit presents the results of speech recognition to a human proofreader and makes corrections. This allows the text conversion unit to improve the accuracy of speech recognition and reduce misrecognition. The text conversion unit can also provide personalized speech recognition by adapting to the speech patterns and accents of specific users. Furthermore, since the text conversion unit can convert speech to text in real time, it is expected to be used in situations such as meetings and lectures. This allows the text conversion unit to provide the user with fast and accurate text conversion, thereby improving communication efficiency.

[0088] The braille converter converts text into braille. For example, the braille converter receives text as input and generates braille using a braille conversion algorithm. The braille converter can use standards such as Braille ASCII and Unified English Braille as the braille conversion algorithm. These standards provide rules for making braille easier to read for visually impaired people. Specifically, Braille ASCII specifies rules for converting English alphabets and numbers into braille, and Unified English Braille provides rules for converting more complex text, including English grammar and punctuation, into braille. The braille converter can also evaluate the accuracy of the generated braille and make corrections as necessary. For example, the braille converter evaluates the legibility and accuracy of the braille and makes adjustments. The evaluation includes parameters such as the placement and spacing of braille and the height of the dots, and by optimizing these, braille that is easier to read is provided. The braille converter can also customize the format of braille according to the user's preferences. This allows the Braille converter to provide individualized Braille output to the user, realizing a more personalized experience. Furthermore, the Braille converter can also support multiple languages, and can convert text in different languages ​​into appropriate Braille to accommodate international users. This allows the Braille converter to provide high-quality Braille output to a wide range of users, reducing barriers to information access.

[0089] The navigation support unit provides real-time voice guidance and direction instructions. For example, the navigation support unit receives GPS data as input and identifies the user's current location. The navigation support unit uses, for example, map data to calculate the optimal route to the user's destination. This also takes into account information such as road congestion, traffic regulations, and pedestrian-only roads. The navigation support unit also uses voice synthesis technology to provide real-time voice guidance to the user. For example, the navigation support unit provides instructions to the user by voice, such as "Turn right at the next intersection." Furthermore, the navigation support unit can monitor the user's moving speed and direction in real time and update the guidance as necessary. For example, if the user deviates from the planned route, the navigation support unit immediately calculates a new route and provides re-guidance. The navigation support unit can also provide guidance specialized for visually impaired people. For example, by providing voice guidance for pedestrian signals and location information of obstacles, the navigation support unit can support the safe movement of visually impaired people. As a result, the navigation support unit can provide quick and accurate direction instructions to the user, improving the efficiency and safety of movement. Furthermore, the navigation assistant can learn the user's past travel history and provide personalized guidance, making the user's travel experience more comfortable and convenient.

[0090] The voice recognition control unit operates a device or application through voice commands. For example, the voice recognition control unit receives a user's voice command as an input and interprets the command using voice recognition technology. The voice recognition control unit can use services such as Google Speech-to-Text and Amazon Transcribe as voice recognition technology. These services provide highly accurate voice recognition and can accurately interpret the user's voice command. Specifically, the voice recognition control unit receives a user's command "play music," launches a music player application, and plays music. The voice recognition control unit can also receive a user's command "tell me the weather," obtain weather information, and provide it by voice. Furthermore, the voice recognition control unit can interpret multiple commands consecutively and perform complex operations. For example, if a user issues a consecutive command such as "tell me tomorrow's schedule, then send me an email," the voice recognition control unit first launches a calendar application to check the schedule, and then launches an email application to send the specified email. In this way, the voice recognition control unit can provide the user with an intuitive and efficient means of operation, making it more convenient to use devices and applications. The voice recognition control unit can also learn the characteristics of the user's voice and speech patterns to provide personalized voice recognition, allowing the voice recognition control unit to realize flexible operations according to the user's needs and improve the user experience.

[0091] The visual information interpretation unit interprets visual information and assists in describing the environment and recognizing objects. For example, the visual information interpretation unit receives video data from a camera as input and recognizes objects using image recognition technology. The visual information interpretation unit can use deep learning models such as YOLO and Faster R-CNN as image recognition technology. These models realize high-speed and high-precision object recognition and provide environmental information in real time. Specifically, YOLO uses a single neural network to analyze the entire image at once and predicts the object's position and class simultaneously. On the other hand, Faster R-CNN uses a region proposal network to generate candidate regions for objects and predicts the object's class based on the candidate regions. The visual information interpretation unit provides a description of the environment to the user based on the recognized objects. For example, the visual information interpretation unit provides a voice warning to the user such as "There is an obstacle ahead." The visual information interpretation unit can also provide detailed descriptions of the type and location of objects. For example, by providing specific information such as "There is a red car on the right" or "There is a pedestrian on the left," the system supports the user's safe movement. Furthermore, the visual information interpretation unit can learn the user's past actions and environmental information and provide personalized explanations. This allows the visual information interpretation unit to provide more appropriate and useful information to the user, improving the quality of daily life. In addition, the visual information interpretation unit can flexibly respond to different environments and situations, making it a very useful support tool for the visually impaired.

[0092] The barrier-free communication unit can provide sign language recognition and sign language translation. The barrier-free communication unit, for example, uses sign language recognition technology to recognize the hand movements of a user and convert the sign language into text. For example, the barrier-free communication unit captures the hand movements with a camera and recognizes the sign language using a deep learning model. The barrier-free communication unit can also convert text into sign language using sign language translation technology. For example, the barrier-free communication unit receives text as input and generates a sign language animation. This allows smooth communication between the hearing impaired and the hearing-able.

[0093] The accessible content providing unit can improve the accessibility of web pages and documents. For example, the accessible content providing unit evaluates the accessibility of a web page and suggests improvements. For example, the accessible content providing unit analyzes the HTML code of a web page and performs an evaluation based on accessibility standards. The accessible content providing unit can also provide tools for improving the accessibility of documents. For example, the accessible content providing unit analyzes the format of a document and makes corrections based on accessibility standards. This can support the provision of content that is suitable for people with disabilities.

[0094] The customization setting unit can adjust the tone, speed, and display settings of the voice for each user. For example, the customization setting unit can adjust the tone and speed of the voice according to the user's preferences. For example, the customization setting unit can generate voice using the voice of a voice actor preferred by the user. The customization setting unit can also adjust the settings of the Braille display. For example, the customization setting unit can adjust the size and spacing of the Braille depending on the degree of the user's visual impairment. This makes it possible to provide services tailored to the needs of each individual user.

[0095] The predictive input unit can predict the operation desired by the user in response to a command input by voice recognition. The predictive input unit, for example, analyzes the user's voice command and predicts the next operation to be performed. For example, when the user says "play the next song," the predictive input unit predicts and suggests the next song to be played. The predictive input unit can also make predictions based on the user's past operation history. For example, the predictive input unit analyzes the history of songs that the user has played in the past and suggests the next song to be played. This makes it possible to predict the operation intended by the user and perform efficient operations.

[0096] The high-precision sign language recognition unit can recognize facial expressions and body movements in addition to hand movements of the sign language. For example, the high-precision sign language recognition unit captures the user's hand movements, facial expressions, and body movements with a camera and recognizes the sign language using a deep learning model. For example, the high-precision sign language recognition unit recognizes the sign language taking into account not only hand movements but also facial expressions and body movements. In addition, the high-precision sign language recognition unit can convert the recognized sign language into text. This improves the recognition accuracy of the sign language, enabling more natural communication.

[0097] The voice conversion unit can generate voice using the voice of a voice actor preferred by the user. For example, the voice conversion unit converts text to voice using voice data of a voice actor selected by the user. The voice conversion unit can also evaluate the quality of the generated voice and make adjustments as necessary. This allows for more friendly voice guidance by generating voice in a voice preferred by the user.

[0098] The voice conversion unit can estimate the user's emotion and adjust the tone of the voice based on the estimated emotion of the user. The voice conversion unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the voice conversion unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The voice conversion unit adjusts the tone of the voice based on the estimated emotion. For example, when the user is nervous, the voice can be generated with a calm tone. Also, when the user is relaxed, the voice can be generated with a bright tone. This makes it possible to adjust the tone of the voice according to the emotion of the user.

[0099] The speech conversion unit can automatically select an appropriate intonation based on the context of the sentence during speech conversion. The speech conversion unit uses natural language processing technology, for example, to analyze the context of the sentence and select an appropriate intonation. For example, the speech conversion unit analyzes the structure and meaning of the sentence and determines the intonation. A deep learning model can be used as the natural language processing technology. The speech conversion unit applies an appropriate intonation based on the analysis result. For example, in the case of a question, a rising intonation is applied. Also, in the case of an exclamation, an emphasized intonation can be applied. This makes it possible to select an appropriate intonation according to the context of the sentence.

[0100] During voice conversion, the voice conversion unit can select the optimal voice generation method by referring to the user's past voice conversion history. The voice conversion unit, for example, uses a database for storing and referring to the user's past voice conversion history. For example, the voice conversion unit stores and analyzes voice data generated by the user in the past. The voice conversion unit selects the optimal voice generation method based on the past voice conversion history. For example, voice is generated based on a tone that the user previously preferred. In addition, specific phrases that the user previously used can be used preferentially. This enables optimal voice generation based on the user's past voice conversion history.

[0101] The voice conversion unit can estimate the user's emotion and adjust the voice speed based on the estimated user's emotion. The voice conversion unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the voice conversion unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The voice conversion unit adjusts the voice speed based on the estimated emotion. For example, when the user is nervous, the voice can be generated at a slow speed. Also, when the user is relaxed, the voice can be generated at a normal speed. This makes it possible to adjust the voice speed according to the user's emotion.

[0102] The voice conversion unit can apply a region-specific accent during voice conversion, taking into account the geographical location information of the user. The voice conversion unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the voice conversion unit identifies the user's current location and applies an accent for that region. The voice conversion unit uses a voice synthesis technique to apply a region-specific accent. For example, the voice conversion unit can apply a Kansai dialect accent to a user in the Kansai region. Also, the voice conversion unit can apply a Tohoku dialect accent to a user in the Tohoku region. This allows for more natural voice guidance by applying a region-specific accent.

[0103] During the voice conversion, the voice conversion unit can analyze the user's social media activity and generate voice based on related topics. For example, the voice conversion unit collects social media data to analyze the user's social media activity. For example, the voice conversion unit identifies topics that the user has recently been interested in and generates voice based on the topics. The voice conversion unit uses natural language processing techniques to analyze the social media activity. For example, the voice conversion unit analyzes the content posted by the user and extracts related topics. This makes it possible to generate voice based on the user's interests.

[0104] The text conversion unit can estimate the user's emotion and adjust the text expression method based on the estimated user's emotion. The text conversion unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the text conversion unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The text conversion unit adjusts the text expression method based on the estimated emotion. For example, when the user is nervous, concise and clear text can be generated. Also, when the user is relaxed, detailed and richly expressed text can be generated. This makes it possible to adjust the text expression according to the user's emotion.

[0105] The text conversion unit can automatically insert appropriate punctuation marks based on the context of the speech during text conversion. The text conversion unit uses natural language processing technology, for example, to analyze the context of the speech and insert appropriate punctuation marks. For example, the text conversion unit analyzes the structure and meaning of the speech and determines the punctuation marks. A deep learning model can be used as the natural language processing technology. The text conversion unit inserts appropriate punctuation marks based on the analysis results. For example, in the case of a question sentence, a question mark can be inserted at the end of the sentence. Also, in the case of an exclamation sentence, an exclamation mark can be inserted at the end of the sentence. This makes it possible to insert appropriate punctuation marks according to the context of the speech.

[0106] The text conversion unit can select the optimal text generation method by referring to the user's past text conversion history during text conversion. The text conversion unit, for example, uses a database for storing and referring to the user's past text conversion history. For example, the text conversion unit stores and analyzes text data generated by the user in the past. The text conversion unit selects the optimal text generation method based on the past text conversion history. For example, text is generated based on an expression method that the user has preferred in the past. In addition, specific phrases that the user has used in the past can be used preferentially. This enables optimal text generation based on the user's past text conversion history.

[0107] The text conversion unit can estimate the user's emotion and adjust the length of the text based on the estimated user's emotion. The text conversion unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the text conversion unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The text conversion unit adjusts the length of the text based on the estimated emotion. For example, when the user is nervous, a short text that is to the point can be generated. Also, when the user is relaxed, a longer text including a detailed explanation can be generated. This makes it possible to adjust the length of the text according to the user's emotion.

[0108] The text conversion unit can apply a region-specific expression during text conversion, taking into account the geographical location information of the user. The text conversion unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the text conversion unit identifies the user's current location and applies an expression for that region. The text conversion unit uses natural language processing technology to apply the region-specific expression. For example, the text conversion unit can apply an expression in Kansai dialect to a user in the Kansai region, and an expression in Tohoku dialect to a user in the Tohoku region. This allows more natural text generation by applying a region-specific expression.

[0109] During text conversion, the text conversion unit can analyze the user's social media activity and generate text based on related topics. For example, the text conversion unit collects social media data to analyze the user's social media activity. For example, the text conversion unit identifies topics that the user has recently been interested in and generates text based on the topics. The text conversion unit uses natural language processing techniques to analyze the social media activity. For example, the text conversion unit analyzes the content posted by the user and extracts related topics. This makes it possible to generate text based on the user's interests.

[0110] The braille conversion unit can estimate the user's emotion and adjust the braille expression method based on the estimated user's emotion. The braille conversion unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the braille conversion unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The braille conversion unit adjusts the braille expression method based on the estimated emotion. For example, when the user is nervous, concise and clear braille is generated. Also, when the user is relaxed, detailed and richly expressed braille can be generated. This makes it possible to adjust the braille expression according to the user's emotion.

[0111] The braille conversion unit can automatically select an appropriate braille expression based on the context of the text during braille conversion. The braille conversion unit uses natural language processing technology, for example, to analyze the context of the text and select an appropriate braille expression. For example, the braille conversion unit analyzes the structure and meaning of the text and determines the braille expression. A deep learning model can be used as the natural language processing technology. The braille conversion unit applies an appropriate braille expression based on the analysis result. For example, in the case of a question sentence, braille including a question mark is generated. Also, in the case of an exclamation sentence, braille including an exclamation mark can be generated. This makes it possible to select an appropriate braille expression according to the context of the text.

[0112] The braille conversion unit can select the optimal braille generation method by referring to the user's past braille conversion history at the time of braille conversion. The braille conversion unit uses, for example, a database for storing and referring to the user's past braille conversion history. For example, the braille conversion unit stores and analyzes braille data generated by the user in the past. The braille conversion unit selects the optimal braille generation method based on the past braille conversion history. For example, braille is generated based on an expression method that the user previously preferred. In addition, a specific phrase that the user previously used can be preferentially used. This enables optimal braille generation based on the user's past braille conversion history.

[0113] The braille conversion unit can estimate the user's emotion and adjust the braille speed based on the estimated user's emotion. The braille conversion unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the braille conversion unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The braille conversion unit adjusts the braille speed based on the estimated emotion. For example, when the user is nervous, braille is generated at a slow speed. Also, when the user is relaxed, braille can be generated at a normal speed. This makes it possible to adjust the braille speed according to the user's emotion.

[0114] The braille conversion unit can apply a region-specific braille expression in consideration of the geographical location information of the user during braille conversion. The braille conversion unit uses, for example, GPS data to acquire the geographical location information of the user. For example, the braille conversion unit identifies the user's current location and applies the braille expression for that region. The braille conversion unit uses natural language processing technology to apply the region-specific braille expression. For example, the braille conversion unit can apply a braille expression in Kansai dialect to a user in the Kansai region. Also, the braille conversion unit can apply a braille expression in Tohoku dialect to a user in the Tohoku region. This allows more natural braille generation by applying a braille expression specific to the region.

[0115] The Braille conversion unit can analyze the user's social media activity and generate Braille based on related topics during Braille conversion. The Braille conversion unit, for example, collects social media data to analyze the user's social media activity. For example, the Braille conversion unit identifies topics that the user has recently been interested in and generates Braille based on the topics. The Braille conversion unit uses natural language processing technology to analyze the social media activity. For example, the Braille conversion unit analyzes the content posted by the user and extracts related topics. This makes it possible to generate Braille based on the user's interests.

[0116] The navigation support unit can estimate the user's emotion and adjust the tone of the guidance based on the estimated user's emotion. The navigation support unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the navigation support unit analyzes the user's voice and facial expression to estimate the emotion. As emotion recognition technology, voice analysis technology and facial expression recognition technology can be used. The navigation support unit adjusts the tone of the guidance based on the estimated emotion. For example, if the user is nervous, the guidance can be provided in a calm tone. Also, if the user is relaxed, the guidance can be provided in a bright tone. This makes it possible to adjust the guidance tone according to the user's emotion.

[0117] When providing navigation support, the navigation support unit can select an optimal guidance method by referring to the user's past movement history. The navigation support unit, for example, uses a database for storing and referring to the user's past movement history. For example, the navigation support unit stores and analyzes routes the user has traveled in the past. The navigation support unit selects an optimal guidance method based on the past movement history. For example, the navigation support unit proposes an optimal guidance method based on routes the user has used in the past. In addition, a route that avoids congestion can be proposed based on the user's past movement history. This makes it possible to provide optimal guidance based on the user's past movement history.

[0118] The navigation support unit can provide an optimal route by referring to real-time traffic information during navigation support. The navigation support unit uses traffic information data to obtain real-time traffic information, for example. For example, the navigation support unit obtains and analyzes traffic congestion information and the operation status of public transportation. The navigation support unit calculates an optimal route based on the real-time traffic information. For example, the navigation support unit proposes a route that avoids traffic congestion. In addition, the navigation support unit can propose an optimal route taking into account the operation status of public transportation. This makes it possible to provide an optimal route based on real-time traffic information.

[0119] The navigation support unit can estimate the user's emotion and adjust the speed of guidance based on the estimated user's emotion. The navigation support unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the navigation support unit analyzes the user's voice and facial expression to estimate the emotion. As emotion recognition technology, voice analysis technology and facial expression recognition technology can be used. The navigation support unit adjusts the speed of guidance based on the estimated emotion. For example, when the user is nervous, guidance can be provided at a slow speed. Also, when the user is relaxed, guidance can be provided at a normal speed. This makes it possible to adjust the guidance speed according to the user's emotion.

[0120] The navigation support unit can provide region-specific guidance by taking into account the geographical location information of the user when providing navigation support. The navigation support unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the navigation support unit identifies the user's current location and provides region-specific guidance. The navigation support unit uses voice synthesis technology to provide region-specific guidance. For example, the navigation support unit can provide Kansai dialect guidance to a user in the Kansai region, and Tohoku dialect guidance to a user in the Tohoku region. This allows for more natural navigation by providing region-specific guidance.

[0121] During navigation assistance, the navigation assistance unit can analyze the user's social media activity and provide guidance based on related topics. For example, the navigation assistance unit collects social media data to analyze the user's social media activity. For example, the navigation assistance unit identifies topics that the user has recently been interested in and provides guidance based on the topics. The navigation assistance unit uses natural language processing techniques to analyze the social media activity. For example, the navigation assistance unit analyzes the content posted by the user and extracts related topics. This enables guidance based on the user's interests.

[0122] The voice recognition control unit can estimate the user's emotion and adjust the interpretation method of the voice command based on the estimated user's emotion. The voice recognition control unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the voice recognition control unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The voice recognition control unit adjusts the interpretation method of the voice command based on the estimated emotion. For example, when the user is nervous, a concise and clear voice command is preferentially interpreted. Also, when the user is relaxed, a detailed voice command can be interpreted. This makes it possible to interpret the voice command according to the user's emotion.

[0123] The voice recognition control unit can select the optimal interpretation method by referring to the user's past voice command history during voice recognition. The voice recognition control unit, for example, uses a database for storing and referring to the user's past voice command history. For example, the voice recognition control unit stores and analyzes voice commands used by the user in the past. The voice recognition control unit selects the optimal interpretation method based on the past voice command history. For example, it preferentially interprets specific phrases used by the user in the past. In addition, the voice recognition control unit can analyze the user's past voice command history and select the most efficient interpretation method. This enables optimal interpretation based on the user's past voice command history.

[0124] The voice recognition control unit can automatically select an appropriate command based on the context of the voice during voice recognition. The voice recognition control unit uses natural language processing technology, for example, to analyze the context of the voice and select an appropriate command. For example, the voice recognition control unit analyzes the structure and meaning of the voice and determines the command. A deep learning model can be used as the natural language processing technology. The voice recognition control unit selects an appropriate command based on the analysis result. For example, in the case of a question sentence, an appropriate response command is selected. Also, in the case of an exclamation sentence, a command reflecting the emotion can be selected. This makes it possible to select an appropriate command according to the context of the voice.

[0125] The voice recognition control unit can estimate the user's emotion and determine the priority of voice commands based on the estimated user's emotion. The voice recognition control unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the voice recognition control unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The voice recognition control unit determines the priority of voice commands based on the estimated emotion. For example, if the user is nervous, a concise and clear voice command can be prioritized. Also, if the user is relaxed, a detailed voice command can be prioritized. This makes it possible to determine the priority of voice commands according to the user's emotion.

[0126] The voice recognition control unit can apply region-specific commands during voice recognition, taking into account the geographical location information of the user. The voice recognition control unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the voice recognition control unit identifies the current location of the user and applies region-specific commands. The voice recognition control unit uses natural language processing technology to apply region-specific commands. For example, the voice recognition control unit can apply Kansai dialect voice commands to a user in the Kansai region. Also, the voice recognition control unit can apply Tohoku dialect voice commands to a user in the Tohoku region. This allows for more natural voice recognition by applying region-specific commands.

[0127] During voice recognition, the voice recognition control unit can analyze the user's social media activities and interpret the command based on related topics. For example, the voice recognition control unit collects social media data to analyze the user's social media activities. For example, the voice recognition control unit identifies topics that the user has recently been interested in and interprets the command based on the topics. The voice recognition control unit uses natural language processing techniques to analyze the social media activities. For example, the voice recognition control unit analyzes the content of the user's posts and extracts related topics. This enables the interpretation of the voice command based on the user's interests.

[0128] The visual information interpretation unit can estimate the user's emotion and adjust the interpretation method of the visual information based on the estimated user's emotion. The visual information interpretation unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the visual information interpretation unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The visual information interpretation unit adjusts the interpretation method of the visual information based on the estimated emotion. For example, when the user is nervous, concise and clear visual information is preferentially interpreted. Also, when the user is relaxed, detailed visual information can be interpreted. This makes it possible to interpret visual information according to the user's emotion.

[0129] When interpreting visual information, the visual information interpretation unit can select the optimal interpretation method by referring to the user's past visual information interpretation history. The visual information interpretation unit, for example, uses a database for storing and referring to the user's past visual information interpretation history. For example, the visual information interpretation unit stores and analyzes visual information previously interpreted by the user. The visual information interpretation unit selects the optimal interpretation method based on the past visual information interpretation history. For example, it preferentially interprets a specific pattern previously interpreted by the user. In addition, the user's past visual information interpretation history can be analyzed to select the most efficient interpretation method. This enables optimal interpretation based on the user's past visual information interpretation history.

[0130] The visual information interpretation unit can automatically select an appropriate interpretation based on the context of the environment when interpreting visual information. The visual information interpretation unit uses, for example, environmental recognition technology to analyze the context of the environment and select an appropriate interpretation. For example, the visual information interpretation unit analyzes the structure and meaning of the environment and determines the interpretation. As the environmental recognition technology, deep learning models such as YOLO and Faster R-CNN can be used. The visual information interpretation unit selects an appropriate interpretation based on the analysis result. For example, when indoors, indoor objects can be interpreted preferentially. Also, when outdoors, outdoor objects can be interpreted preferentially. This enables appropriate interpretation according to the context of the environment.

[0131] The visual information interpretation unit can estimate the user's emotion and determine the priority of the visual information based on the estimated user's emotion. The visual information interpretation unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the visual information interpretation unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The visual information interpretation unit determines the priority of the visual information based on the estimated emotion. For example, if the user is nervous, concise and clear visual information can be prioritized. Also, if the user is relaxed, detailed visual information can be prioritized. This makes it possible to determine the priority of the visual information according to the user's emotion.

[0132] The visual information interpretation unit can provide a region-specific interpretation by taking into account the geographical location information of the user when interpreting visual information. The visual information interpretation unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the visual information interpretation unit identifies the user's current location and provides an interpretation specific to the region. The visual information interpretation unit uses an environmental recognition technology to provide an interpretation specific to the region. For example, the visual information interpretation unit can preferentially interpret objects in the Kansai region for a user in the Kansai region. Also, the visual information interpretation unit can preferentially interpret objects in the Tohoku region for a user in the Tohoku region. This allows for more natural interpretation of visual information by providing an interpretation specific to the region.

[0133] When interpreting visual information, the visual information interpretation unit can analyze the user's social media activity and provide an interpretation based on related topics. The visual information interpretation unit, for example, collects social media data to analyze the user's social media activity. For example, the visual information interpretation unit identifies topics that the user has recently been interested in and provides an interpretation based on the topics. The visual information interpretation unit uses natural language processing techniques to analyze the social media activity. For example, the visual information interpretation unit analyzes the content posted by the user and extracts related topics. This enables visual information interpretation based on the user's interests.

[0134] The barrier-free communication unit can estimate the user's emotion and adjust the sign language interpretation method based on the estimated user's emotion. The barrier-free communication unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the barrier-free communication unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The barrier-free communication unit adjusts the sign language interpretation method based on the estimated emotion. For example, when the user is nervous, the barrier-free communication unit preferentially interprets concise and clear sign language. Also, when the user is relaxed, the barrier-free communication unit can interpret detailed sign language. This makes it possible to interpret sign language according to the user's emotion.

[0135] When recognizing a sign language, the barrier-free communication unit can select an optimal interpretation method by referring to the user's past sign language history. The barrier-free communication unit, for example, uses a database for storing and referring to the user's past sign language history. For example, the barrier-free communication unit stores and analyzes sign languages ​​used by the user in the past. The barrier-free communication unit selects an optimal interpretation method based on the past sign language history. For example, it gives priority to interpreting specific phrases used by the user in the past. In addition, the barrier-free communication unit can analyze the user's past sign language history and select the most efficient interpretation method. This enables optimal interpretation based on the user's past sign language history.

[0136] The barrier-free communication unit can estimate the user's emotion and determine the priority order of sign languages ​​based on the estimated user's emotion. The barrier-free communication unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the barrier-free communication unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The barrier-free communication unit determines the priority order of sign languages ​​based on the estimated emotion. For example, if the user is nervous, a concise and clear sign language can be prioritized. Also, if the user is relaxed, a detailed sign language can be prioritized. This makes it possible to determine the priority order of sign languages ​​according to the user's emotion.

[0137] The barrier-free communication unit can apply a region-specific sign language in consideration of the geographical location information of the user when recognizing the sign language. The barrier-free communication unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the barrier-free communication unit identifies the user's current location and applies the region-specific sign language. The barrier-free communication unit uses natural language processing technology to apply the region-specific sign language. For example, the barrier-free communication unit can apply Kansai dialect sign language to a user in the Kansai region. Also, the barrier-free communication unit can apply Tohoku dialect sign language to a user in the Tohoku region. In this way, applying the region-specific sign language enables more natural sign language recognition.

[0138] The accessible content providing unit can estimate the user's emotion and adjust the content display method based on the estimated user's emotion. The accessible content providing unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the accessible content providing unit analyzes the user's voice and facial expression to estimate the emotion. As emotion recognition technology, voice analysis technology and facial expression recognition technology can be used. The accessible content providing unit adjusts the content display method based on the estimated emotion. For example, if the user is nervous, content in calm colors can be provided. Also, if the user is relaxed, content in bright colors can be provided. This makes it possible to adjust the content display according to the user's emotion.

[0139] When providing content, the accessible content providing unit can select the optimal display method by referring to the user's past content browsing history. The accessible content providing unit, for example, uses a database for storing and referring to the user's past content browsing history. For example, the accessible content providing unit stores and analyzes content previously viewed by the user. The accessible content providing unit selects the optimal display method based on the past content browsing history. For example, the accessible content providing unit provides content based on a display method previously preferred by the user. In addition, a specific format previously used by the user can be preferentially used. This enables optimal display based on the user's past content browsing history.

[0140] The accessible content providing unit can estimate the user's emotion and determine the priority order of content based on the estimated user's emotion. The accessible content providing unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the accessible content providing unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The accessible content providing unit determines the priority order of content based on the estimated emotion. For example, if the user is nervous, concise and clear content can be prioritized. Also, if the user is relaxed, detailed content can be prioritized. This makes it possible to determine the priority order of content according to the user's emotion.

[0141] The accessible content providing unit can provide region-specific content by taking into consideration the geographical location information of the user when providing content. The accessible content providing unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the accessible content providing unit identifies the user's current location and provides content specific to the region. The accessible content providing unit uses natural language processing technology to provide region-specific content. For example, the accessible content providing unit can provide content for the Kansai region to a user in the Kansai region. Also, the accessible content providing unit can provide content for the Tohoku region to a user in the Tohoku region. This allows content to be provided more naturally by providing content specific to the region.

[0142] The customization setting unit can estimate the user's emotion and adjust the customization setting based on the estimated user's emotion. The customization setting unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the customization setting unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The customization setting unit adjusts the customization setting based on the estimated emotion. For example, if the user is nervous, a calm setting can be provided. Also, if the user is relaxed, a bright setting can be provided. This makes it possible to adjust the customization setting according to the user's emotion.

[0143] The customization setting unit can select the optimal setting method by referring to the user's past setting history during customization setting. The customization setting unit, for example, uses a database for storing and referring to the user's past setting history. For example, the customization setting unit stores and analyzes settings used by the user in the past. The customization setting unit selects the optimal setting method based on the past setting history. For example, customization is provided based on settings that the user preferred in the past. Also, specific settings used by the user in the past can be used preferentially. This enables optimal settings based on the user's past setting history.

[0144] The customization setting unit can estimate the user's emotion and determine the priority order of the customization settings based on the estimated user's emotion. The customization setting unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the customization setting unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The customization setting unit determines the priority order of the customization settings based on the estimated emotion. For example, if the user is nervous, a simple and clear setting can be prioritized. Also, if the user is relaxed, a detailed setting can be prioritized. This makes it possible to determine the priority order of the customization settings according to the user's emotion.

[0145] The customization setting unit can provide region-specific settings in consideration of the geographical location information of the user during customization setting. The customization setting unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the customization setting unit identifies the user's current location and provides settings specific to the region. The customization setting unit uses natural language processing technology to provide region-specific settings. For example, the customization setting unit can provide Kansai region settings to a user in the Kansai region. Also, the customization setting unit can provide Tohoku region settings to a user in the Tohoku region. This allows for more natural customization by providing region-specific settings.

[0146] The predictive input unit can estimate the user's emotion and adjust the predictive input method based on the estimated user's emotion. The predictive input unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the predictive input unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The predictive input unit adjusts the predictive input method based on the estimated emotion. For example, when the user is nervous, a concise and clear predictive input can be provided. Also, when the user is relaxed, a detailed predictive input can be provided. This makes it possible to adjust the predictive input according to the user's emotion.

[0147] The predictive input unit can select the optimal prediction method by referring to the user's past input history at the time of predictive input. The predictive input unit uses, for example, a database for storing and referring to the user's past input history. For example, the predictive input unit stores and analyzes contents input by the user in the past. The predictive input unit selects the optimal prediction method based on the past input history. For example, it predicts a specific phrase input by the user in the past with priority. In addition, the predictive input unit can analyze the user's past input history and select the most efficient prediction method. This enables optimal prediction based on the user's past input history.

[0148] The predictive input unit can estimate the user's emotion and determine the priority of the predictive input based on the estimated user's emotion. The predictive input unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the predictive input unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The predictive input unit determines the priority of the predictive input based on the estimated emotion. For example, when the user is nervous, a concise and clear predictive input can be prioritized. Also, when the user is relaxed, a detailed predictive input can be prioritized. This makes it possible to determine the priority of the predictive input according to the user's emotion.

[0149] The predictive input unit can provide a region-specific prediction in consideration of the geographical location information of the user at the time of predictive input. The predictive input unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the predictive input unit identifies the user's current location and provides a region-specific prediction. The predictive input unit uses natural language processing technology to provide a region-specific prediction. For example, the predictive input unit can provide a predictive input for the Kansai region to a user in the Kansai region. Also, the predictive input unit can provide a predictive input for the Tohoku region to a user in the Tohoku region. This allows for more natural predictive input by providing a region-specific prediction.

[0150] The high-precision sign language recognition unit can estimate the user's emotion and adjust the sign language interpretation method based on the estimated user's emotion. The high-precision sign language recognition unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the high-precision sign language recognition unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The high-precision sign language recognition unit adjusts the sign language interpretation method based on the estimated emotion. For example, when the user is nervous, the high-precision sign language recognition unit preferentially interprets concise and clear sign language. Also, when the user is relaxed, detailed sign language can be interpreted. This makes it possible to interpret sign language according to the user's emotion.

[0151] The high-precision sign language recognition unit can select the optimal interpretation method by referring to the user's past sign language history when recognizing a sign language. The high-precision sign language recognition unit, for example, uses a database for storing and referring to the user's past sign language history. For example, the high-precision sign language recognition unit stores and analyzes sign languages ​​used by the user in the past. The high-precision sign language recognition unit selects the optimal interpretation method based on the past sign language history. For example, it gives priority to interpreting specific phrases used by the user in the past. In addition, the high-precision sign language recognition unit can analyze the user's past sign language history and select the most efficient interpretation method. This enables optimal interpretation based on the user's past sign language history.

[0152] The high-precision sign language recognition unit can estimate the user's emotion and determine the priority order of sign languages ​​based on the estimated user's emotion. The high-precision sign language recognition unit uses, for example, emotion recognition technology to estimate the user's emotion. For example, the high-precision sign language recognition unit analyzes the user's voice and facial expression to estimate the emotion. As the emotion recognition technology, a voice analysis technology or a facial expression recognition technology can be used. The high-precision sign language recognition unit determines the priority order of sign languages ​​based on the estimated emotion. For example, if the user is nervous, a concise and clear sign language can be prioritized. Also, if the user is relaxed, a detailed sign language can be prioritized. This makes it possible to determine the priority order of sign languages ​​according to the user's emotion.

[0153] The high-precision sign language recognition unit can apply a region-specific sign language in consideration of the geographical location information of the user during sign language recognition. The high-precision sign language recognition unit, for example, uses GPS data to acquire the geographical location information of the user. For example, the high-precision sign language recognition unit identifies the user's current location and applies the region-specific sign language. The high-precision sign language recognition unit uses natural language processing technology to apply the region-specific sign language. For example, the high-precision sign language recognition unit can apply Kansai dialect sign language to a user in the Kansai region. Also, the high-precision sign language recognition unit can apply Tohoku dialect sign language to a user in the Tohoku region. This allows for more natural sign language recognition by applying the region-specific sign language.

[0154] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0155] The AI ​​assistant system may further include a health management unit that monitors the user's health condition. The health management unit may, for example, measure the user's heart rate and blood pressure and issue an alert if an abnormality is detected. The health management unit may also record the user's amount of exercise and suggest an appropriate exercise plan. Furthermore, the health management unit may record the user's diet and provide advice on nutritional balance. This may support the user's health management and improve the quality of life.

[0156] The barrier-free communication unit can further estimate the user's emotions and adjust the sign language expression method based on the estimated emotions. For example, if the user is nervous, concise and clear sign language is given priority for interpretation. On the other hand, if the user is relaxed, detailed sign language can be interpreted. This makes it possible to interpret sign language according to the user's emotions. The barrier-free communication unit can also refer to the user's past sign language history to select the optimal interpretation method. This makes it possible to perform optimal interpretation based on the user's past sign language history.

[0157] The accessible content providing unit can further refer to the user's learning history to provide optimal learning content. For example, it can suggest what the user should study next based on what the user has studied in the past. The accessible content providing unit can also adjust the difficulty of the content according to the user's learning pace. Furthermore, the accessible content providing unit can customize the way content is displayed to suit the user's learning style. This can improve the user's learning efficiency.

[0158] The customization setting unit can further estimate the user's emotions and adjust the customization settings based on the estimated emotions. For example, if the user is nervous, a calm setting can be provided. Also, if the user is relaxed, a bright setting can be provided. This makes it possible to adjust the customization settings according to the user's emotions. The customization setting unit can also refer to the user's past setting history to select the optimal setting method. This makes it possible to provide optimal settings based on the user's past setting history.

[0159] The predictive input unit can further estimate the user's emotions and adjust the predictive input method based on the estimated emotions. For example, if the user is nervous, a concise and clear predictive input can be provided. Also, if the user is relaxed, a detailed predictive input can be provided. This makes it possible to adjust the predictive input according to the user's emotions. The predictive input unit can also select an optimal prediction method by referring to the user's past input history. This makes it possible to make optimal predictions based on the user's past input history.

[0160] The high-precision sign language recognition unit can further estimate the user's emotions and adjust the sign language interpretation method based on the estimated emotions. For example, if the user is nervous, concise and clear sign language is given priority for interpretation. On the other hand, if the user is relaxed, detailed sign language can be interpreted. This makes it possible to interpret sign language according to the user's emotions. The high-precision sign language recognition unit can also refer to the user's past sign language history to select the optimal interpretation method. This makes it possible to perform optimal interpretation based on the user's past sign language history.

[0161] The voice conversion unit can further apply a region-specific accent by taking into account the geographical location information of the user. For example, the voice conversion unit identifies the user's current location and applies an accent for that region. The voice conversion unit uses a voice synthesis technique to apply a region-specific accent. For example, the voice conversion unit can apply a Kansai dialect accent to a user in the Kansai region, and a Tohoku dialect accent to a user in the Tohoku region. This allows for more natural voice guidance by applying a region-specific accent.

[0162] The text conversion unit can further analyze the user's social media activities and generate text based on related topics. For example, the text conversion unit identifies topics that the user has recently been interested in and generates text based on the topics. The text conversion unit uses natural language processing techniques to analyze the social media activities. For example, the text conversion unit analyzes the content of the user's posts and extracts related topics. This enables text generation based on the user's interests. The text conversion unit can also select an optimal text generation method by referring to the user's past text conversion history. This enables optimal text generation based on the user's past text conversion history.

[0163] The braille conversion unit can further estimate the user's emotions and adjust the braille expression method based on the estimated emotions. For example, if the user is nervous, concise and clear braille can be generated. On the other hand, if the user is relaxed, detailed and richly expressed braille can be generated. This makes it possible to adjust the braille expression according to the user's emotions. The braille conversion unit can also refer to the user's past braille conversion history to select the optimal braille generation method. This makes it possible to generate optimal braille based on the user's past braille conversion history.

[0164] The navigation support unit can further select the optimal guidance method by referring to the user's past movement history. For example, the navigation support unit saves and analyzes routes that the user has traveled in the past. The navigation support unit selects the optimal guidance method based on the past movement history. For example, the navigation support unit can suggest the optimal guidance method based on routes that the user has used in the past. In addition, the navigation support unit can suggest routes that avoid congestion based on the user's past movement history. This makes it possible to provide optimal guidance based on the user's past movement history.

[0165] The process flow of the second embodiment will be briefly described below.

[0166] Step 1: The speech conversion unit converts text into speech. For example, the speech conversion unit receives text as input and generates speech using speech synthesis technology. For example, the speech conversion unit can use deep learning models such as WaveNet and Tacotron as the speech synthesis technology. The speech conversion unit can also evaluate the quality of the generated speech and make adjustments as necessary. For example, the speech conversion unit evaluates the naturalness and clarity of the speech and makes adjustments. Step 2: The text conversion unit converts the speech into text. For example, the text conversion unit receives speech as an input and generates text using speech recognition technology. For example, the text conversion unit can use a deep learning model such as DeepSpeech or Kaldi as the speech recognition technology. The text conversion unit can also evaluate the accuracy of the generated text and make corrections if necessary. For example, the text conversion unit presents the results of the speech recognition to a human proofreader for correction. Step 3: The Braille converter converts the text into Braille. For example, the Braille converter receives the text as input and generates Braille using a Braille conversion algorithm. For example, the Braille converter can use a standard such as Braille ASCII or Unified English Braille as the Braille conversion algorithm. The Braille converter can also evaluate the accuracy of the generated Braille and make corrections if necessary. For example, the Braille converter can evaluate the legibility and accuracy of the Braille and make adjustments. Step 4: The navigation assistance unit provides real-time voice guidance and direction instructions. For example, the navigation assistance unit receives GPS data as input and identifies the user's current location. The navigation assistance unit calculates an optimal route to the user's destination, for example, using map data. The navigation assistance unit also provides real-time voice guidance to the user using voice synthesis technology. For example, the navigation assistance unit provides voice instructions to the user such as "Turn right at the next intersection." Step 5: The voice recognition control unit operates a device or application through a voice command. For example, the voice recognition control unit receives a user's voice command as an input and interprets the command using a voice recognition technology. The voice recognition control unit can use services such as Google Speech-to-Text and Amazon Transcribe as the voice recognition technology. The voice recognition control unit also operates a device or application based on the interpreted command. For example, the voice recognition control unit launches a music player app and plays music based on the user's command "play music." Step 6: The visual information interpretation unit interprets the visual information and assists in describing the environment and recognizing objects. For example, the visual information interpretation unit receives video data from a camera as input and recognizes objects using image recognition technology. The visual information interpretation unit can use deep learning models such as YOLO and Faster R-CNN as image recognition technology. The visual information interpretation unit also provides a description of the environment to the user based on the recognized objects. For example, the visual information interpretation unit provides a voice warning to the user such as "There is an obstacle ahead."

[0167] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0168] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0169] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0170] For example, the voice conversion unit is realized by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the Braille conversion unit is realized by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the navigation support unit is realized by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the voice recognition control unit is realized by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the visual information interpretation unit is realized by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0171] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0172] 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.

[0173] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0174] 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.

[0175] 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 the voice according to instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0177] 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 performed in a secure state.

[0178] Fig. 4 shows an example of 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.

[0179] 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.

[0180] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0181] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0182] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0183] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0184] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0185] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0186] For example, the voice conversion unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the Braille conversion unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the navigation support unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the voice recognition control unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the visual information interpretation unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0187] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0188] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0189] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0190] 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.

[0191] 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 the voice according to instructions from the processor 46.

[0192] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0193] 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 performed in a secure state.

[0194] 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.

[0195] 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.

[0196] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0197] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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 identification processing unit 290 using these models.

[0198] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0199] 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 voice indicating a user input for 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.

[0200] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0201] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0202] For example, the voice conversion unit is realized by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the Braille conversion unit is realized by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the navigation support unit is realized by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the voice recognition control unit is realized by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the visual information interpretation unit is realized by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0203] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0204] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0205] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0206] 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.

[0207] 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 the voice according to instructions from the processor 46.

[0208] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0209] 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 performed in a secure state.

[0210] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0211] 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.

[0212] 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.

[0213] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0214] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 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.

[0215] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0216] 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 a voice indicating a user input for 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.

[0217] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0218] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0219] For example, the voice conversion unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the Braille conversion unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the navigation support unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the voice recognition control unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the visual information interpretation unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0220] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0221] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0222] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0223] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0224] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0225] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0226] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0227] 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.

[0228] 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 Universal Serial Bus (USB) 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.

[0229] In addition, 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 upon request from the data processing device 12.

[0230] 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.

[0231] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0232] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0233] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0234] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0235] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0236] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0237] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0238] (Appendix 1) A text-to-speech converter; A text conversion unit that converts speech into text; a braille converter for converting text into braille; a navigation assistance unit that provides real-time voice guidance and directions; a voice recognition control unit for operating a device or application through voice commands; A visual information interpretation unit that interprets visual information and assists in describing the environment and recognizing objects. A system characterized by: (Appendix 2) Equipped with a Barrier-Free Communication Department that provides sign language recognition and sign language translation 2. The system of claim 1, (Appendix 3) Equipped with an accessible content provider that improves the accessibility of web pages and documents 2. The system of claim 1, (Appendix 4) Equipped with a customizable settings section that adjusts voice tone, speed, and display settings for each user 2. The system of claim 1, (Appendix 5) Equipped with a predictive input unit that predicts the operation the user wants to perform in response to command input via voice recognition 2. The system of claim 1, (Appendix 6) The barrier-free communication department includes: Equipped with a highly accurate sign language recognition unit that recognizes facial expressions and body movements in addition to hand movements for sign language 3. The system of claim 2, (Appendix 7) The voice conversion unit is Generate audio using the voice of the user's preferred voice actor 2. The system of claim 1, (Appendix 8) The voice conversion unit is Estimating a user's emotion and adjusting the tone of the voice based on the estimated user's emotion 2. The system of claim 1, (Appendix 9) The voice conversion unit is When converting speech, the appropriate intonation is automatically selected based on the context of the sentence. 2. The system of claim 1, (Appendix 10) The voice conversion unit is When converting voice, the system selects the optimal voice generation method by referring to the user's past voice conversion history. 2. The system of claim 1, (Appendix 11) The voice conversion unit is Estimating user emotion and adjusting speech speed based on the estimated user emotion 2. The system of claim 1, (Appendix 12) The voice conversion unit is During voice conversion, regional accents are applied taking into account the user's geographic location 2. The system of claim 1, (Appendix 13) The voice conversion unit is During voice conversion, it analyzes the user's social media activity and generates voice based on relevant topics. 2. The system of claim 1, (Appendix 14) The text conversion unit is Infer user sentiment and adjust text presentation based on the inferred sentiment 2. The system of claim 1, (Appendix 15) The text conversion unit is Automatically inserts appropriate punctuation during transcription based on the context of the audio 2. The system of claim 1, (Appendix 16) The text conversion unit is When converting text, the system selects the optimal text generation method by referring to the user's past text conversion history. 2. The system of claim 1, (Appendix 17) The text conversion unit is Inferring user sentiment and adjusting text length based on the estimated user sentiment 2. The system of claim 1, (Appendix 18) The text conversion unit is When converting text, it takes into account the user's geographic location to apply region-specific expressions. 2. The system of claim 1, (Appendix 19) The text conversion unit is During text conversion, it analyzes the user's social media activity and generates text based on related topics. 2. The system of claim 1, (Appendix 20) The Braille conversion unit includes: Estimating the user's emotions and adjusting the way braille is displayed based on the estimated user's emotions 2. The system of claim 1, (Appendix 21) The Braille conversion unit includes: When converting to braille, automatically select the appropriate braille representation based on the context of the text 2. The system of claim 1, (Appendix 22) The Braille conversion unit includes: When converting to braille, the system selects the optimal braille generation method by referring to the user's past braille conversion history. 2. The system of claim 1, (Appendix 23) The Braille conversion unit includes: Estimate the user's emotion and adjust the braille speed based on the estimated user's emotion. 2. The system of claim 1, (Appendix 24) The Braille conversion unit includes: When converting to braille, the system takes into account the user's geographic location to apply region-specific braille expressions 2. The system of claim 1, (Appendix 25) The Braille conversion unit includes: During braille conversion, the system analyzes the user's social media activity and generates braille based on related topics. 2. The system of claim 1, (Appendix 26) The navigation support unit includes: To estimate a user's emotion and adjust the tone of a guidance based on the estimated user's emotion. 2. The system of claim 1, (Appendix 27) The navigation support unit includes: When providing navigation assistance, the system selects the optimal guidance method by referring to the user's past movement history. 2. The system of claim 1, (Appendix 28) The navigation support unit includes: When providing navigation assistance, real-time traffic information is referenced to provide the optimal route 2. The system of claim 1, (Appendix 29) The navigation support unit includes: To estimate a user's emotion and adjust a speed of guidance based on the estimated user's emotion. 2. The system of claim 1, (Appendix 30) The navigation support unit includes: When providing navigation assistance, the system takes into account the user's geographic location to provide location-specific guidance. 2. The system of claim 1, (Appendix 31) The navigation support unit includes: When assisted with navigation, the app analyzes the user's social media activity and provides guidance based on relevant topics. 2. The system of claim 1, (Appendix 32) The voice recognition control unit Inferring a user's emotions and adjusting how voice commands are interpreted based on the inferred user emotions 2. The system of claim 1, (Appendix 33) The voice recognition control unit During voice recognition, the system selects the best interpretation method by referring to the user's past voice command history. 2. The system of claim 1, (Appendix 34) The voice recognition control unit During voice recognition, the appropriate command is automatically selected based on the context of the speech. 2. The system of claim 1, (Appendix 35) The voice recognition control unit Estimate user emotions and prioritize voice commands based on the estimated user emotions 2. The system of claim 1, (Appendix 36) The voice recognition control unit During voice recognition, take into account the user's geographic location to apply region-specific commands 2. The system of claim 1, (Appendix 37) The voice recognition control unit During voice recognition, it analyzes the user's social media activity and interprets commands based on relevant topics. 2. The system of claim 1, (Appendix 38) The visual information interpretation unit is Inferring a user's emotions and adjusting how visual information is interpreted based on the inferred user's emotions 2. The system of claim 1, (Appendix 39) The visual information interpretation unit is When interpreting visual information, the system selects the optimal interpretation method by referring to the user's past visual information interpretation history. 2. The system of claim 1, (Appendix 40) The visual information interpretation unit is When interpreting visual information, automatically choose the appropriate interpretation based on the context of the environment 2. The system of claim 1, (Appendix 41) The visual information interpretation unit is Estimate the user's emotions and prioritize visual information based on the estimated user's emotions. 2. The system of claim 1, (Appendix 42) The visual information interpretation unit is When interpreting visual information, take into account the user's geographic location to provide a location-specific interpretation 2. The system of claim 1, (Appendix 43) The visual information interpretation unit is When interpreting visual information, it analyzes the user's social media activity and provides interpretations based on related topics. 2. The system of claim 1, (Appendix 44) The barrier-free communication department includes: Estimating a user's emotions and adjusting the way in which sign language is interpreted based on the estimated user's emotions 3. The system of claim 2, (Appendix 45) The barrier-free communication department includes: When recognizing sign language, the system selects the optimal interpretation method by referring to the user's past sign language history. 3. The system of claim 2, (Appendix 46) The barrier-free communication department includes: Estimate the user's emotions and prioritize sign languages ​​based on the estimated user's emotions. 3. The system of claim 2, (Appendix 47) The barrier-free communication department includes: During sign language recognition, region-specific sign language is applied taking into account the user's geographic location information. 3. The system of claim 2, (Appendix 48) The accessible content providing unit, Inferring user emotion and adjusting how content is displayed based on the estimated user emotion 4. The system of claim 3. (Appendix 49) The accessible content providing unit, When providing content, the optimal display method is selected by referring to the user's past content browsing history. 4. The system of claim 3. (Appendix 50) The accessible content providing unit, Estimating user sentiment and prioritizing content based on the estimated user sentiment 4. The system of claim 3. (Appendix 51) The accessible content providing unit, When providing content, the site takes into account the user's geographic location to provide region-specific content. 4. The system of claim 3. (Appendix 52) The customization setting unit includes: Inferring a user's emotion and adjusting customization settings based on the inferred user emotion 5. The system of claim 4. (Appendix 53) The customization setting unit includes: When customizing settings, select the optimal setting method by referring to the user's past setting history. 5. The system of claim 4. (Appendix 54) The customization setting unit includes: Inferring a user's emotions and prioritizing customization settings based on the estimated user's emotions 5. The system of claim 4. (Appendix 55) The customization setting unit includes: During customization, consider the user's geographic location to provide region-specific settings 5. The system of claim 4. (Appendix 56) The prediction input unit is Inferring a user's emotions and adjusting the predictive input method based on the estimated user's emotions 6. The system of claim 5, (Appendix 57) The prediction input unit is When making predictions, the system selects the optimal prediction method by referring to the user's past input history. 6. The system of claim 5, (Appendix 58) The prediction input unit is Inferring user emotions and prioritizing predictive inputs based on the estimated user emotions 6. The system of claim 5, (Appendix 59) The prediction input unit is When typing predictions, they take into account the user's geographic location to provide region-specific predictions. 6. The system of claim 5, (Appendix 60) The high-precision sign language recognition unit includes: Estimating a user's emotions and adjusting the way in which sign language is interpreted based on the estimated user's emotions 7. The system of claim 6, (Appendix 61) The high-precision sign language recognition unit includes: When recognizing sign language, the system selects the optimal interpretation method by referring to the user's past sign language history. 7. The system of claim 6, (Appendix 62) The high-precision sign language recognition unit includes: Estimate the user's emotions and prioritize sign languages ​​based on the estimated user's emotions. 7. The system of claim 6, (Appendix 63) The high-precision sign language recognition unit includes: During sign language recognition, region-specific sign language is applied taking into account the user's geographic location information. 7. The system of claim 6, [Explanation of symbols]

[0239] 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 text-to-speech converter; A text conversion unit that converts speech into text; a braille converter for converting text into braille; a navigation assistance unit that provides real-time voice guidance and directions; a voice recognition control unit for operating a device or application through voice commands; A visual information interpretation unit that interprets visual information and assists in describing the environment and recognizing objects. A system characterized by:

2. Equipped with a Barrier-Free Communication Department that provides sign language recognition and sign language translation 2. The system of claim 1 .

3. Equipped with an accessible content provider that improves the accessibility of web pages and documents 2. The system of claim 1 .

4. Equipped with a customizable settings section that adjusts voice tone, speed, and display settings for each user 2. The system of claim 1 .

5. Equipped with a predictive input unit that predicts the operation the user wants to perform in response to command input via voice recognition 2. The system of claim 1 .

6. The barrier-free communication department includes: Equipped with a highly accurate sign language recognition unit that recognizes facial expressions and body movements in addition to hand movements for sign language 3. The system of claim 2.

7. The voice conversion unit is Generate audio using the voice of the user's preferred voice actor 2. The system of claim 1 .

8. The voice conversion unit is Estimating a user's emotion and adjusting the tone of the voice based on the estimated user's emotion 2. The system of claim 1 .

Images