system

Abstract

The system according to the embodiment aims to enable hearing impaired people to quickly and accurately understand audio information. [Solution] A system according to an embodiment includes a reception unit, a conversion unit, a generation unit, and a display unit. The reception unit inputs speech. The conversion unit converts the speech input by the reception unit into text. The generation unit converts the text converted by the conversion unit into a sign language video. The display unit displays the text or sign language video generated by the generation unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult for hearing-impaired people to quickly and accurately understand audio information.

[0005] The system according to the embodiment aims to enable hearing impaired people to quickly and accurately understand audio information. [Means for solving the problem]

[0006] A system according to an embodiment includes a reception unit, a conversion unit, a generation unit, and a display unit. The reception unit receives speech input. The conversion unit converts the speech input by the reception unit into text. The generation unit converts the text converted by the conversion unit into a sign language video. The display unit displays the text or sign language video generated by the generation unit. [Effects of the Invention]

[0007] Systems according to embodiments can enable hearing impaired people to quickly and accurately understand audio information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) A system according to an embodiment of the present invention utilizes a generation AI to overcome communication barriers faced by people with hearing impairments in their daily lives. The system includes a reception unit for receiving speech, a conversion unit for converting the speech input by the reception unit into text, a generation unit for converting the text converted by the conversion unit into a sign language video, and a display unit for displaying the text and sign language video generated by the generation unit. For example, a user inputs speech. The speech of the person they are speaking to is picked up by a smartphone microphone. This speech is then input into a generation AI. The generation AI then analyzes the input speech and converts it into text. The generation AI then converts the speech into text using speech recognition technology. For example, if the speech "hello" is input, the generation AI converts it into the text "hello." The converted text is displayed on the user's smartphone or tablet. The user can understand the content of the conversation by reading the displayed text. The generation AI then analyzes the text and generates an appropriate sign language video. The generation AI then understands the content of the text and generates a corresponding sign language video. For example, for the text "hello," the generation AI generates a sign language video of "hello." The generated sign language video is displayed on the user's device. By watching the displayed sign language video, the user can understand the audio information in sign language. This system allows hearing-impaired people to understand audio information in text or sign language, eliminating communication barriers. For example, by picking up the voice of a conversation partner on a smartphone, the generation AI converts it into text, and then generates a sign language video, the hearing-impaired person can understand the content of the conversation. In this way, the system allows hearing-impaired people to understand audio information in text or sign language, eliminating communication barriers.

[0029] A system according to an embodiment includes a reception unit, a conversion unit, a generation unit, and a display unit. The reception unit receives voice input. For example, a user can input voice using a microphone on a smartphone or tablet. The conversion unit converts the voice input by the reception unit into text. For example, the generation AI converts voice into text using speech recognition technology. The generation AI analyzes the voice and converts it into text. For example, if the voice "hello" is input, the generation AI converts it into the text "hello." The generation unit converts the text converted by the conversion unit into a sign language video. For example, the generation AI understands the content of the text and generates a corresponding sign language video. The generation AI analyzes the text and generates an appropriate sign language video. For example, for the text "hello," the generation AI generates a sign language video of "hello." The display unit displays the text and sign language video generated by the generation unit. For example, the text and sign language video can be displayed on the screen of a user's smartphone or tablet. This allows the system to enable hearing-impaired people to understand audio information through text or sign language, eliminating communication barriers.

[0030] The system includes a database unit that uses a sign language database. The database unit uses the sign language database. The sign language database includes the types of sign languages ​​included, the database format, and the access method. For example, the sign language database includes sign languages ​​used in everyday conversation and sign languages ​​for technical terms. The database format can be, for example, an SQL database or a NoSQL database. For example, the database can be accessed via an API. As a result, using the sign language database improves the accuracy of generating sign language videos.

[0031] The system is equipped with a learning management unit that manages the learning method of the generative AI. The learning management unit manages the learning method of the generative AI. Learning methods for the generative AI include supervised learning, unsupervised learning, and reinforcement learning. For example, in supervised learning, the generative AI is trained using labeled data. In unsupervised learning, the generative AI is trained using unlabeled data. In reinforcement learning, the generative AI is trained based on rewards. In this way, by managing the learning method of the generative AI, the accuracy of the system is improved.

[0032] The system includes an accuracy improvement unit that implements technical improvements to improve the accuracy of speech recognition. The accuracy improvement unit implements technical improvements to improve the accuracy of speech recognition. For example, noise cancellation technology can be used to remove ambient noise. The accuracy of speech recognition can also be improved by improving the acoustic model. Furthermore, data augmentation technology can be used to increase the variety of speech data. This improves the accuracy of speech recognition and enables more accurate text conversion.

[0033] The reception unit can input voice using a microphone of a smartphone or tablet. The reception unit inputs voice using, for example, a microphone of a smartphone. Voice is input by the user speaking into the microphone of the smartphone. Voice can also be input using a microphone of a tablet. For example, voice is input by the user speaking into the microphone of the tablet. This allows the user to easily input voice using a smartphone or tablet.

[0034] The display unit can display text or sign language video on the screen of the smartphone or tablet. The display unit displays text on the smartphone screen, for example. The user can understand the audio information by reading the text displayed on the smartphone screen. The display unit can also display sign language video on the tablet screen. For example, the user can understand the audio information in sign language by watching the sign language video displayed on the tablet screen. This allows the user to easily check the information by displaying it on the smartphone or tablet screen.

[0035] The reception unit can analyze the user's past voice input history and select an appropriate input method. For example, the reception unit preferentially suggests voice input methods that the user has frequently used in the past. The reception unit saves the user's past voice input history in a database and analyzes it. For example, the reception unit suggests the optimal input method for a specific time period based on the past voice input history. The reception unit analyzes the user's voice input history in chronological order and selects the optimal input method. For example, the reception unit analyzes the user's past voice input history and selects the most efficient input method. In this way, the reception unit can provide the optimal input method to the user by analyzing the past voice input history.

[0036] The reception unit can filter surrounding environmental sounds to remove noise when voice is input. For example, the reception unit analyzes surrounding environmental sounds in real time when voice is input and removes noise. The reception unit uses noise canceling technology to remove surrounding noise. For example, noise in a specific frequency band is filtered. When voice is input, background noise is reduced to achieve clear voice input. For example, filtering technology for reducing background noise is used when voice is input. As a result, clear voice input is possible by filtering surrounding environmental sounds.

[0037] When inputting voice, the reception unit can prioritize inputting highly relevant voice by taking into account the user's geographical location information. For example, when the user is in a specific location, the reception unit prioritizes inputting voice related to that location. The reception unit acquires the user's geographical location information using GPS data and prioritizes inputting highly relevant voice. For example, when the user is moving, the reception unit prioritizes inputting highly relevant voice based on the user's current location. When the user is in a specific area, the reception unit prioritizes inputting voice related to that area. In this way, highly relevant voice can be prioritized by taking into account the geographical location information.

[0038] The reception unit can analyze the user's social media activity and input related speech when inputting speech. For example, the reception unit prioritizes input of words frequently used by the user on social media. The user's social media activity is stored in a database and analyzed. For example, related speech is input from the user's social media activity. The content of the user's social media posts is analyzed and related speech is input. In this way, related speech can be input by analyzing social media activity.

[0039] When converting speech to text, the conversion unit can improve conversion accuracy by taking into account the context of the speech. For example, the conversion unit analyzes the context of the speech and converts it into appropriate text. By taking into account the context of the speech, conversion accuracy is improved. For example, the speech context is understood and converted into natural-looking text. To analyze the context of the speech, the generation AI takes into account the content of the conversation before and after and the speaker's intention. In this way, by taking into account the context of the speech, conversion accuracy is improved.

[0040] The conversion unit can perform text conversion taking into account attribute information of the speaker of the voice. For example, if the speaker of the voice is a child, the conversion unit converts the voice into text in simple language. The attribute information of the speaker of the voice is saved in a database and analyzed. For example, if the speaker of the voice is an expert, technical terms are appropriately converted into text. If the speaker of the voice is a foreigner, accent is taken into account when converting into text. This allows for more appropriate text conversion by taking into account speaker attribute information.

[0041] When converting speech to text, the conversion unit can determine the priority of conversion based on the time when the speech was recorded. For example, the conversion unit converts the most recent speech to text with priority. The time when the speech was recorded is obtained using a timestamp and the priority of conversion is determined. For example, speech recorded earlier is converted to text later. Speech recorded within a specific time period is converted to text with priority. In this way, by determining the priority of conversion based on the time when the speech was recorded, the most recent speech can be converted to text with priority.

[0042] When converting speech to text, the conversion unit can improve conversion accuracy by referring to related literature. For example, the conversion unit refers to literature related to the content of the speech and converts it into appropriate text. If the speech contains technical terms, the conversion unit accurately converts it into text by referring to related literature. For example, if the content of the speech is complex, the conversion accuracy is improved by referring to related literature. Related literature includes academic papers and technical documents. In this way, by referring to related literature, conversion accuracy is improved.

[0043] When converting text into sign language video, the generation unit can improve generation accuracy by taking into account the context of the text. For example, the generation unit analyzes the context of the text and converts it into an appropriate sign language video. The generation accuracy is improved by taking into account the context of the text. For example, the context of the text is understood and converted into natural sign language video. To analyze the context of the text, the generation AI takes into account the surrounding sentences and related topics. This improves generation accuracy by taking into account the context of the text.

[0044] The generation unit can apply different sign language video generation algorithms depending on the content of the text. For example, if the content of the text is simple, the generation unit applies a simple sign language video generation algorithm. If the content of the text is complex, the generation unit applies a detailed sign language video generation algorithm. For example, if the content of the text is technical, the generation unit applies a sign language video generation algorithm that corresponds to the technical terminology. Sign language video generation algorithms include rule-based and machine learning-based algorithms. This allows the generation accuracy to be improved by applying an appropriate sign language video generation algorithm depending on the content of the text.

[0045] When converting text into sign language video, the generation unit can determine a generation priority based on the time of submission of the text. For example, the generation unit preferentially converts the most recent text into sign language video. The generation unit obtains the time of submission of the text using a timestamp and determines the generation priority. For example, text submitted earlier is converted into sign language video later. Text submitted within a specific time period is preferentially converted into sign language video. In this way, by determining the generation priority based on the time of submission, the most recent text can be preferentially converted into sign language video.

[0046] When converting text into sign language video, the generation unit can improve generation accuracy by referring to a related sign language database. For example, the generation unit refers to a sign language database related to the content of the text and converts it into an appropriate sign language video. If the text contains technical terms, the generation unit accurately converts it into sign language video by referring to a related sign language database. For example, if the content of the text is complex, the generation accuracy is improved by referring to a related sign language database. The related sign language database includes the types of sign languages ​​included, the database format, the access method, etc. Thus, by referring to a related sign language database, generation accuracy is improved.

[0047] When displaying, the display unit can select an appropriate display method by referring to the user's past display history. For example, the display unit preferentially provides a display method that the user has used favorably in the past. The user's past display history is saved in a database and analyzed. For example, the optimal display method for a specific time period is suggested based on the user's past display history. The user's past display history is analyzed in chronological order to select the optimal display method. For example, the user's past display history is analyzed to select the most efficient display method. In this way, the optimal display method can be provided to the user by referring to the past display history.

[0048] The display unit can customize the display content according to the characteristics of the user's device when displaying. For example, if the user is using a smartphone, the display unit provides display content that matches the screen size. The display unit stores and analyzes the characteristics of the user's device in a database. For example, if the user is using a tablet, the display unit provides display content optimized for a large screen. If the user is using a smartwatch, the display unit provides display content that is concise and highly visible. This allows the display to be customized according to the characteristics of the device, making it easier to see.

[0049] The display unit can select an appropriate display method when displaying information by taking into consideration the user's geographical location information. For example, when the user is in a specific location, the display unit prioritizes displaying information related to that location. The display unit obtains the user's geographical location information using GPS data and prioritizes displaying highly relevant information. For example, when the user is moving, the display unit prioritizes displaying highly relevant information based on the user's current location. When the user is in a specific area, the display unit prioritizes displaying information related to that area. In this way, highly relevant information can be prioritized by taking into consideration the geographical location information.

[0050] The display unit can analyze the user's social media activity and adjust the display content when displaying. For example, the display unit prioritizes displaying words that the user frequently uses on social media. The display unit stores the user's social media activity in a database and analyzes it. For example, it displays related information based on the user's social media activity. It analyzes the content of the user's social media posts and displays related information. In this way, it is possible to display related information by analyzing social media activity.

[0051] When updating the database, the database unit can select an appropriate update method by referring to past data. The database unit, for example, analyzes past data and selects the optimal update method. The database unit saves past data in a database and analyzes it. For example, it refers to past data and adjusts the update frequency. It selects the optimal update timing based on past data. In this way, it is possible to select the optimal update method by referring to past data.

[0052] When searching the database, the database unit can provide appropriate search results by taking into account the user's geographical location information. For example, if the user is in a specific location, the database unit provides search results related to that location with priority. The database unit obtains the user's geographical location information using GPS data and provides highly relevant search results. For example, if the user is moving, highly relevant search results are provided based on the user's current location. If the user is in a specific area, search results related to that area are provided with priority. In this way, highly relevant search results can be provided by taking into account the geographical location information.

[0053] During learning, the learning management unit can optimize the learning algorithm by referring to past learning data. For example, the learning management unit analyzes past learning data and selects the optimal learning algorithm. It saves past learning data in a database and analyzes it. For example, it adjusts the parameters of the learning algorithm by referring to past learning data. It optimizes the learning algorithm based on past learning data. In this way, the learning algorithm can be optimized by referring to past learning data.

[0054] During learning, the learning management unit can weight the learning data based on the time of submission of the voice data. For example, the learning management unit prioritizes learning and weighting the most recent voice data. The time of submission of the voice data is obtained using a timestamp and weights the learning data. For example, voice data submitted earlier is learned and weighted later. Voice data submitted within a specific time period is learned and weighted preferentially. In this way, by weighting the learning data based on the time of submission, the most recent data can be learned preferentially.

[0055] When improving the accuracy of speech recognition, the accuracy improvement unit can select an appropriate accuracy improvement method by referring to past speech data. The accuracy improvement unit, for example, analyzes past speech data and selects the optimal accuracy improvement method. The past speech data is stored in a database and analyzed. For example, the parameters of the accuracy improvement method are adjusted by referring to the past speech data. The accuracy improvement method is optimized based on the past speech data. In this way, the optimal accuracy improvement method can be selected by referring to the past speech data.

[0056] When improving the accuracy of speech recognition, the accuracy improvement unit can select an appropriate accuracy improvement method by taking into account the user's geographical location information. For example, if the user is in a specific location, the accuracy improvement unit selects a speech recognition accuracy improvement method related to that location. The accuracy improvement unit acquires the user's geographical location information using GPS data and selects a highly relevant speech recognition accuracy improvement method. For example, if the user is moving, the accuracy improvement unit selects a highly relevant speech recognition accuracy improvement method based on the user's current location. If the user is in a specific region, the accuracy improvement unit selects a speech recognition accuracy improvement method related to that region. In this way, by taking the geographical location information into account, a highly relevant speech recognition accuracy improvement method can be selected.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] When converting speech to text, the conversion unit can improve conversion accuracy by taking into account the context of the speech. For example, it analyzes the context of the speech and converts it into appropriate text. In order to understand the context of the speech and convert it into natural-sounding text, the generation AI takes into account the content of the conversation before and after and the speaker's intention. This improves conversion accuracy by taking into account the context of the speech.

[0059] The reception unit can filter surrounding environmental sounds to remove noise when inputting voice. For example, the reception unit can analyze surrounding environmental sounds in real time when inputting voice and remove noise. The reception unit can use noise canceling technology to remove surrounding noise. For example, it can filter noise in a specific frequency band. The reception unit can reduce background noise when inputting voice and achieve clear voice input. For example, it can use filtering technology to reduce background noise when inputting voice. This allows the reception unit to filter surrounding environmental sounds and achieve clear voice input.

[0060] When converting speech to text, the conversion unit can take into account the attribute information of the speaker of the speech. For example, if the speaker of the speech is a child, the text is converted into simple language. The attribute information of the speaker of the speech is saved in a database and analyzed. For example, if the speaker of the speech is an expert, technical terms are appropriately converted into text. If the speaker of the speech is a foreigner, the accent is taken into account when converting into text. This allows for more appropriate text conversion by taking into account the speaker's attribute information.

[0061] When converting text into sign language video, the generation unit can improve generation accuracy by taking into account the context of the text. For example, it analyzes the context of the text and converts it into an appropriate sign language video. Generation accuracy is improved by taking into account the context of the text. For example, it understands the context of the text and converts it into natural sign language video. To analyze the context of the text, the generation AI takes into account the surrounding sentences and related topics. This improves generation accuracy by taking into account the context of the text.

[0062] When displaying, the display unit can select an appropriate display method by referring to the user's past display history. For example, it can preferentially provide a display method that the user has used favorably in the past. It stores the user's past display history in a database and analyzes it. For example, it can suggest the optimal display method for a specific time period based on the user's past display history. It analyzes the user's past display history in chronological order to select the optimal display method. For example, it can analyze the user's past display history and select the most efficient display method. In this way, it is possible to provide the optimal display method to the user by referring to the past display history.

[0063] During learning, the learning management unit can optimize the learning algorithm by referring to past learning data. For example, it analyzes past learning data and selects the optimal learning algorithm. It saves past learning data in a database and analyzes it. For example, it adjusts the parameters of the learning algorithm by referring to past learning data. It optimizes the learning algorithm based on past learning data. In this way, the learning algorithm can be optimized by referring to past learning data.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The reception unit inputs voice. For example, the user can input voice using a microphone on a smartphone or tablet. Step 2: The conversion unit converts the speech input by the reception unit into text. For example, the generation AI converts speech into text using speech recognition technology. The generation AI analyzes the speech and converts it into text. For example, if the speech "hello" is input, the generation AI converts this into the text "hello." Step 3: The generation unit converts the text converted by the conversion unit into a sign language video. For example, the generation AI understands the content of the text and generates a corresponding sign language video. The generation AI analyzes the text and generates an appropriate sign language video. For example, for the text "Hello," the generation AI generates a sign language video of "Hello." Step 4: The display unit displays the text or sign language video generated by the generation unit. For example, the text or sign language video can be displayed on the screen of the user's smartphone or tablet. This allows the system to enable people with hearing impairments to understand audio information in text or sign language, eliminating communication barriers.

[0066] (Example 2) A system according to an embodiment of the present invention utilizes a generation AI to overcome communication barriers faced by people with hearing impairments in their daily lives. The system includes a reception unit for receiving speech, a conversion unit for converting the speech input by the reception unit into text, a generation unit for converting the text converted by the conversion unit into a sign language video, and a display unit for displaying the text and sign language video generated by the generation unit. For example, a user inputs speech. The speech of the person they are speaking to is picked up by a smartphone microphone. This speech is then input into a generation AI. The generation AI then analyzes the input speech and converts it into text. The generation AI then converts the speech into text using speech recognition technology. For example, if the speech "hello" is input, the generation AI converts it into the text "hello." The converted text is displayed on the user's smartphone or tablet. The user can understand the content of the conversation by reading the displayed text. The generation AI then analyzes the text and generates an appropriate sign language video. The generation AI then understands the content of the text and generates a corresponding sign language video. For example, for the text "hello," the generation AI generates a sign language video of "hello." The generated sign language video is displayed on the user's device. By watching the displayed sign language video, the user can understand the audio information in sign language. This system allows hearing-impaired people to understand audio information in text or sign language, eliminating communication barriers. For example, by picking up the voice of a conversation partner on a smartphone, the generation AI converts it into text, and then generates a sign language video, the hearing-impaired person can understand the content of the conversation. In this way, the system allows hearing-impaired people to understand audio information in text or sign language, eliminating communication barriers.

[0067] A system according to an embodiment includes a reception unit, a conversion unit, a generation unit, and a display unit. The reception unit receives voice input. For example, a user can input voice using a microphone on a smartphone or tablet. The conversion unit converts the voice input by the reception unit into text. For example, the generation AI converts voice into text using speech recognition technology. The generation AI analyzes the voice and converts it into text. For example, if the voice "hello" is input, the generation AI converts it into the text "hello." The generation unit converts the text converted by the conversion unit into a sign language video. For example, the generation AI understands the content of the text and generates a corresponding sign language video. The generation AI analyzes the text and generates an appropriate sign language video. For example, for the text "hello," the generation AI generates a sign language video of "hello." The display unit displays the text and sign language video generated by the generation unit. For example, the text and sign language video can be displayed on the screen of a user's smartphone or tablet. This allows the system to enable hearing-impaired people to understand audio information through text or sign language, eliminating communication barriers.

[0068] The system includes a database unit that uses a sign language database. The database unit uses the sign language database. The sign language database includes the types of sign languages ​​included, the database format, and the access method. For example, the sign language database includes sign languages ​​used in everyday conversation and sign languages ​​for technical terms. The database format can be, for example, an SQL database or a NoSQL database. For example, the database can be accessed via an API. As a result, using the sign language database improves the accuracy of generating sign language videos.

[0069] The system is equipped with a learning management unit that manages the learning method of the generative AI. The learning management unit manages the learning method of the generative AI. Learning methods for the generative AI include supervised learning, unsupervised learning, and reinforcement learning. For example, in supervised learning, the generative AI is trained using labeled data. In unsupervised learning, the generative AI is trained using unlabeled data. In reinforcement learning, the generative AI is trained based on rewards. In this way, by managing the learning method of the generative AI, the accuracy of the system is improved.

[0070] The system includes an accuracy improvement unit that implements technical improvements to improve the accuracy of speech recognition. The accuracy improvement unit implements technical improvements to improve the accuracy of speech recognition. For example, noise cancellation technology can be used to remove ambient noise. The accuracy of speech recognition can also be improved by improving the acoustic model. Furthermore, data augmentation technology can be used to increase the variety of speech data. This improves the accuracy of speech recognition and enables more accurate text conversion.

[0071] The reception unit can input voice using a microphone of a smartphone or tablet. The reception unit inputs voice using, for example, a microphone of a smartphone. Voice is input by the user speaking into the microphone of the smartphone. Voice can also be input using a microphone of a tablet. For example, voice is input by the user speaking into the microphone of the tablet. This allows the user to easily input voice using a smartphone or tablet.

[0072] The display unit can display text or sign language video on the screen of the smartphone or tablet. The display unit displays text on the smartphone screen, for example. The user can understand the audio information by reading the text displayed on the smartphone screen. The display unit can also display sign language video on the tablet screen. For example, the user can understand the audio information in sign language by watching the sign language video displayed on the tablet screen. This allows the user to easily check the information by displaying it on the smartphone or tablet screen.

[0073] The reception unit can estimate the user's emotions and adjust the timing of voice input based on the estimated user emotions. For example, if the user is nervous, the reception unit delays the timing of voice input to allow the user to relax. The reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. Furthermore, if the user is relaxed, the timing of voice input is advanced to promote smooth input. The reception unit records the user's voice and estimates the emotion using voice analysis technology. For example, the tone and speed of voice are analyzed to calculate an emotion score. Furthermore, if the user is in a hurry, the timing of voice input is optimized to enable quick input. The reception unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows the timing of voice input to be adjusted according to the user's emotions, enabling more appropriate voice input.

[0074] The reception unit can analyze the user's past voice input history and select an appropriate input method. For example, the reception unit preferentially suggests voice input methods that the user has frequently used in the past. The reception unit saves the user's past voice input history in a database and analyzes it. For example, the reception unit suggests the optimal input method for a specific time period based on the past voice input history. The reception unit analyzes the user's voice input history in chronological order and selects the optimal input method. For example, the reception unit analyzes the user's past voice input history and selects the most efficient input method. In this way, the reception unit can provide the optimal input method to the user by analyzing the past voice input history.

[0075] The reception unit can filter surrounding environmental sounds to remove noise when voice is input. For example, the reception unit analyzes surrounding environmental sounds in real time when voice is input and removes noise. The reception unit uses noise canceling technology to remove surrounding noise. For example, noise in a specific frequency band is filtered. When voice is input, background noise is reduced to achieve clear voice input. For example, filtering technology for reducing background noise is used when voice is input. As a result, clear voice input is possible by filtering surrounding environmental sounds.

[0076] The reception unit can estimate the user's emotions and determine the priority of voice input based on the estimated user emotions. For example, if the user is nervous, the reception unit prioritizes input of important voice. The reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. Furthermore, if the user is relaxed, all voices are input equally. The reception unit records the user's voice and estimates the emotion using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate the emotion score. Furthermore, if the user is in a hurry, the reception unit prioritizes input of the most important voice. The reception unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. In this way, by determining the priority of voices according to the user's emotions, important voices can be input preferentially.

[0077] When inputting voice, the reception unit can prioritize inputting highly relevant voice by taking into account the user's geographical location information. For example, when the user is in a specific location, the reception unit prioritizes inputting voice related to that location. The reception unit acquires the user's geographical location information using GPS data and prioritizes inputting highly relevant voice. For example, when the user is moving, the reception unit prioritizes inputting highly relevant voice based on the user's current location. When the user is in a specific area, the reception unit prioritizes inputting voice related to that area. In this way, highly relevant voice can be prioritized by taking into account the geographical location information.

[0078] The reception unit can analyze the user's social media activity and input related speech when inputting speech. For example, the reception unit prioritizes input of words frequently used by the user on social media. The user's social media activity is stored in a database and analyzed. For example, related speech is input from the user's social media activity. The content of the user's social media posts is analyzed and related speech is input. In this way, related speech can be input by analyzing social media activity.

[0079] The conversion unit can estimate the user's emotions and adjust the expression method for text conversion based on the estimated user emotions. For example, if the user is nervous, the conversion unit uses a simple and easy-to-understand expression method. The conversion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. Furthermore, if the user is relaxed, a detailed expression method is used. The conversion unit records the user's voice and estimates the emotion using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, if the user is in a hurry, a concise expression method is used. The conversion unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows for more appropriate text conversion by adjusting the expression method for text conversion according to the user's emotions.

[0080] When converting speech to text, the conversion unit can improve conversion accuracy by taking into account the context of the speech. For example, the conversion unit analyzes the context of the speech and converts it into appropriate text. By taking into account the context of the speech, conversion accuracy is improved. For example, the speech context is understood and converted into natural-looking text. To analyze the context of the speech, the generation AI takes into account the content of the conversation before and after and the speaker's intention. In this way, by taking into account the context of the speech, conversion accuracy is improved.

[0081] The conversion unit can perform text conversion taking into account attribute information of the speaker of the voice. For example, if the speaker of the voice is a child, the conversion unit converts the voice into text in simple language. The attribute information of the speaker of the voice is saved in a database and analyzed. For example, if the speaker of the voice is an expert, technical terms are appropriately converted into text. If the speaker of the voice is a foreigner, accent is taken into account when converting into text. This allows for more appropriate text conversion by taking into account speaker attribute information.

[0082] The conversion unit can estimate the user's emotions and adjust the length of the text conversion based on the estimated user emotions. For example, if the user is in a hurry, the conversion unit converts the text into short, to-the-point text. The conversion unit captures the user's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. If the user is relaxed, the conversion unit converts the text into longer text with detailed explanations. The conversion unit records the user's voice and estimates their emotions using voice analysis technology. For example, the conversion unit analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, if the user is excited, the conversion unit converts the text into text with visually stimulating effects. The conversion unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates their emotions using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows for more appropriate text conversion by adjusting the length of the text conversion according to the user's emotions.

[0083] When converting speech to text, the conversion unit can determine the priority of conversion based on the time when the speech was recorded. For example, the conversion unit converts the most recent speech to text with priority. The time when the speech was recorded is obtained using a timestamp and the priority of conversion is determined. For example, speech recorded earlier is converted to text later. Speech recorded within a specific time period is converted to text with priority. In this way, by determining the priority of conversion based on the time when the speech was recorded, the most recent speech can be converted to text with priority.

[0084] When converting speech to text, the conversion unit can improve conversion accuracy by referring to related literature. For example, the conversion unit refers to literature related to the content of the speech and converts it into appropriate text. If the speech contains technical terms, the conversion unit accurately converts it into text by referring to related literature. For example, if the content of the speech is complex, the conversion accuracy is improved by referring to related literature. Related literature includes academic papers and technical documents. In this way, by referring to related literature, conversion accuracy is improved.

[0085] The generation unit can estimate the user's emotions and adjust the sign language video generation method based on the estimated user emotions. For example, if the user is relaxed, the generation unit generates a sign language video that progresses at a leisurely pace. The generation unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expressions. If the user is in a hurry, the generation unit generates a sign language video that emphasizes the shortest route. The generation unit records the user's voice and estimates their emotions using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, if the user is excited, the generation unit generates a sign language video with visually stimulating effects. The generation unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. In this way, the generation unit adjusts the sign language video generation method according to the user's emotions, thereby generating more appropriate sign language videos.

[0086] When converting text into sign language video, the generation unit can improve generation accuracy by taking into account the context of the text. For example, the generation unit analyzes the context of the text and converts it into an appropriate sign language video. The generation accuracy is improved by taking into account the context of the text. For example, the context of the text is understood and converted into natural sign language video. To analyze the context of the text, the generation AI takes into account the surrounding sentences and related topics. This improves generation accuracy by taking into account the context of the text.

[0087] The generation unit can apply different sign language video generation algorithms depending on the content of the text. For example, if the content of the text is simple, the generation unit applies a simple sign language video generation algorithm. If the content of the text is complex, the generation unit applies a detailed sign language video generation algorithm. For example, if the content of the text is technical, the generation unit applies a sign language video generation algorithm that corresponds to the technical terminology. Sign language video generation algorithms include rule-based and machine learning-based algorithms. This allows the generation accuracy to be improved by applying an appropriate sign language video generation algorithm depending on the content of the text.

[0088] The generation unit can estimate the user's emotions and adjust the display order of sign language videos based on the estimated user emotions. For example, if the user is nervous, the generation unit prioritizes displaying important sign language videos. The generation unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Furthermore, if the user is relaxed, all sign language videos are displayed equally. The generation unit records the user's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, if the user is in a hurry, it prioritizes displaying the most important sign language videos. The generation unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on heart rate fluctuations. As a result, important information can be prioritized by adjusting the display order of sign language videos according to the user's emotions.

[0089] When converting text into sign language video, the generation unit can determine a generation priority based on the time of submission of the text. For example, the generation unit preferentially converts the most recent text into sign language video. The generation unit obtains the time of submission of the text using a timestamp and determines the generation priority. For example, text submitted earlier is converted into sign language video later. Text submitted within a specific time period is preferentially converted into sign language video. In this way, by determining the generation priority based on the time of submission, the most recent text can be preferentially converted into sign language video.

[0090] When converting text into sign language video, the generation unit can improve generation accuracy by referring to a related sign language database. For example, the generation unit refers to a sign language database related to the content of the text and converts it into an appropriate sign language video. If the text contains technical terms, the generation unit accurately converts it into sign language video by referring to a related sign language database. For example, if the content of the text is complex, the generation accuracy is improved by referring to a related sign language database. The related sign language database includes the types of sign languages ​​included, the database format, the access method, etc. Thus, by referring to a related sign language database, generation accuracy is improved.

[0091] The display unit can estimate the user's emotions and adjust the display method based on the estimated user emotions. For example, if the user is nervous, the display unit provides a simple, highly visible display method. The display unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. Furthermore, if the user is relaxed, a display method including detailed information is provided. The display unit records the user's voice and estimates the emotion using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, if the user is in a hurry, a display method that focuses on the main points is provided. The display unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows the display method to be adjusted according to the user's emotions, making it possible to display more appropriate information.

[0092] When displaying, the display unit can select an appropriate display method by referring to the user's past display history. For example, the display unit preferentially provides a display method that the user has used favorably in the past. The user's past display history is saved in a database and analyzed. For example, the optimal display method for a specific time period is suggested based on the user's past display history. The user's past display history is analyzed in chronological order to select the optimal display method. For example, the user's past display history is analyzed to select the most efficient display method. In this way, the optimal display method can be provided to the user by referring to the past display history.

[0093] The display unit can customize the display content according to the characteristics of the user's device when displaying. For example, if the user is using a smartphone, the display unit provides display content that matches the screen size. The display unit stores and analyzes the characteristics of the user's device in a database. For example, if the user is using a tablet, the display unit provides display content optimized for a large screen. If the user is using a smartwatch, the display unit provides display content that is concise and highly visible. This allows the display to be customized according to the characteristics of the device, making it easier to see.

[0094] The display unit can estimate the user's emotions and determine display priorities based on the estimated user emotions. For example, if the user is nervous, the display unit prioritizes displaying important information. The display unit captures the user's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. Furthermore, if the user is relaxed, all information is displayed equally. The display unit records the user's voice and estimates their emotions using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, if the user is in a hurry, the display unit prioritizes displaying the most important information. The display unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates their emotions using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows the display priority to be determined according to the user's emotions, thereby prioritizing the display of important information.

[0095] The display unit can select an appropriate display method when displaying information by taking into consideration the user's geographical location information. For example, when the user is in a specific location, the display unit prioritizes displaying information related to that location. The display unit obtains the user's geographical location information using GPS data and prioritizes displaying highly relevant information. For example, when the user is moving, the display unit prioritizes displaying highly relevant information based on the user's current location. When the user is in a specific area, the display unit prioritizes displaying information related to that area. In this way, highly relevant information can be prioritized by taking into consideration the geographical location information.

[0096] The display unit can analyze the user's social media activity and adjust the display content when displaying. For example, the display unit prioritizes displaying words that the user frequently uses on social media. The display unit stores the user's social media activity in a database and analyzes it. For example, it displays related information based on the user's social media activity. It analyzes the content of the user's social media posts and displays related information. In this way, it is possible to display related information by analyzing social media activity.

[0097] The database unit can estimate the user's emotions and adjust database search results based on the estimated user emotions. For example, if the user is nervous, the database unit provides simple and easy-to-understand search results. The database unit captures the user's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Furthermore, if the user is relaxed, it provides detailed search results. The database unit records the user's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, if the user is in a hurry, it provides search results that focus on the main points. The database unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on heart rate fluctuations. This allows the database unit to adjust the search results according to the user's emotions and provide more appropriate search results.

[0098] When updating the database, the database unit can select an appropriate update method by referring to past data. The database unit, for example, analyzes past data and selects the optimal update method. The database unit saves past data in a database and analyzes it. For example, it refers to past data and adjusts the update frequency. It selects the optimal update timing based on past data. In this way, it is possible to select the optimal update method by referring to past data.

[0099] The database unit can estimate the user's emotions and adjust the database search frequency based on the estimated user emotions. For example, if the user is nervous, the database unit sets the search frequency low and provides simple search results. The database unit captures the user's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expression. Furthermore, if the user is relaxed, it sets the search frequency high and provides detailed search results. The database unit records the user's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, if the user is in a hurry, it optimizes the search frequency and provides quick search results. The database unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on heart rate fluctuations. This allows the database unit to adjust the search frequency according to the user's emotions and provide more appropriate search results.

[0100] When searching the database, the database unit can provide appropriate search results by taking into account the user's geographical location information. For example, if the user is in a specific location, the database unit provides search results related to that location with priority. The database unit obtains the user's geographical location information using GPS data and provides highly relevant search results. For example, if the user is moving, highly relevant search results are provided based on the user's current location. If the user is in a specific area, search results related to that area are provided with priority. In this way, highly relevant search results can be provided by taking into account the geographical location information.

[0101] The learning management unit can estimate the user's emotions and select learning data based on the estimated user emotions. For example, if the user is nervous, the learning management unit selects simple and easy-to-understand learning data. The learning management unit captures the user's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expression. Furthermore, if the user is relaxed, it selects detailed learning data. It records the user's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, if the user is in a hurry, it selects learning data that focuses on the main points. It collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on heart rate fluctuations. This allows for more appropriate learning by selecting learning data according to the user's emotions.

[0102] During learning, the learning management unit can optimize the learning algorithm by referring to past learning data. For example, the learning management unit analyzes past learning data and selects the optimal learning algorithm. It saves past learning data in a database and analyzes it. For example, it adjusts the parameters of the learning algorithm by referring to past learning data. It optimizes the learning algorithm based on past learning data. In this way, the learning algorithm can be optimized by referring to past learning data.

[0103] The learning management unit can estimate the user's emotions and adjust the learning frequency based on the estimated user emotions. For example, if the user is nervous, the learning management unit sets the learning frequency low and provides simple learning data. The learning management unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Furthermore, if the user is relaxed, the learning frequency is set high and detailed learning data is provided. The learning management unit records the user's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, if the user is in a hurry, the learning frequency is optimized and quick learning data is provided. The user's biometric data (heart rate and electrodermal activity) is collected with a sensor and the emotion is estimated using an emotion estimation algorithm. For example, it calculates an emotion score based on heart rate fluctuations. This allows the learning frequency to be adjusted according to the user's emotions, enabling more appropriate learning.

[0104] During learning, the learning management unit can weight the learning data based on the time of submission of the voice data. For example, the learning management unit prioritizes learning and weighting the most recent voice data. The time of submission of the voice data is obtained using a timestamp and weights the learning data. For example, voice data submitted earlier is learned and weighted later. Voice data submitted within a specific time period is learned and weighted preferentially. In this way, by weighting the learning data based on the time of submission, the most recent data can be learned preferentially.

[0105] The accuracy improvement unit can estimate the user's emotions and adjust the speech recognition accuracy improvement method based on the estimated user emotions. For example, if the user is nervous, the accuracy improvement unit uses a simple and easy-to-understand speech recognition method. The user's facial expression is captured with a camera and the emotion is estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. On the other hand, if the user is relaxed, a detailed speech recognition method is used. The user's voice is recorded and the emotion is estimated using speech analysis technology. For example, the tone and speed of the voice are analyzed and an emotion score is calculated. Furthermore, if the user is in a hurry, a speech recognition method that focuses on the main points is used. The user's biometric data (heart rate and electrodermal activity) is collected with a sensor and the emotion is estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows the speech recognition accuracy improvement method to be adjusted according to the user's emotions, enabling more appropriate speech recognition.

[0106] When improving the accuracy of speech recognition, the accuracy improvement unit can select an appropriate accuracy improvement method by referring to past speech data. The accuracy improvement unit, for example, analyzes past speech data and selects the optimal accuracy improvement method. The past speech data is stored in a database and analyzed. For example, the parameters of the accuracy improvement method are adjusted by referring to the past speech data. The accuracy improvement method is optimized based on the past speech data. In this way, the optimal accuracy improvement method can be selected by referring to the past speech data.

[0107] The accuracy improvement unit can estimate the user's emotions and determine the priority of improving the accuracy of voice recognition based on the estimated user emotions. For example, if the user is nervous, the accuracy improvement unit prioritizes improving the accuracy of important voice recognition. The accuracy improvement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. Furthermore, if the user is relaxed, the accuracy improvement unit equally improves the accuracy of all voice recognition. The accuracy improvement unit records the user's voice and estimates the emotion using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, if the user is in a hurry, the accuracy improvement of the most important voice recognition is prioritized. The user's biometric data (heart rate and electrodermal activity) is collected with a sensor and the emotion is estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. In this way, by determining the priority of accuracy improvement according to the user's emotions, it is possible to prioritize improving the accuracy of important voice recognition.

[0108] When improving the accuracy of speech recognition, the accuracy improvement unit can select an appropriate accuracy improvement method by taking into account the user's geographical location information. For example, if the user is in a specific location, the accuracy improvement unit selects a speech recognition accuracy improvement method related to that location. The accuracy improvement unit acquires the user's geographical location information using GPS data and selects a highly relevant speech recognition accuracy improvement method. For example, if the user is moving, the accuracy improvement unit selects a highly relevant speech recognition accuracy improvement method based on the user's current location. If the user is in a specific region, the accuracy improvement unit selects a speech recognition accuracy improvement method related to that region. In this way, by taking the geographical location information into account, a highly relevant speech recognition accuracy improvement method can be selected. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, conversion unit, generation unit, display unit, database unit, learning management unit, and accuracy improvement unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit inputs voice using the microphone 38B of the smart device 14. The conversion unit converts the voice into text using the specific processing unit 290 of the data processing device 12. The generation unit converts the text into sign language video using the specific processing unit 290 of the data processing device 12. The display unit displays the text and sign language video on the display 40A of the smart device 14. The database unit accesses the sign language database using the database 24 of the data processing device 12. The learning management unit manages the learning method of the generation AI using the specific processing unit 290 of the data processing device 12. The accuracy improvement unit uses the specific processing unit 290 of the data processing device 12 to implement technical improvements to improve the accuracy of voice recognition. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, conversion unit, generation unit, display unit, database unit, learning management unit, and accuracy improvement unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit inputs voice using the microphone 238 of the smart glasses 214. The conversion unit converts the voice into text using the specific processing unit 290 of the data processing device 12. The generation unit converts the text into sign language video using the specific processing unit 290 of the data processing device 12. The display unit displays the text and sign language video on the display of the smart glasses 214. The database unit accesses the sign language database using the database 24 of the data processing device 12. The learning management unit manages the learning method of the generation AI using the specific processing unit 290 of the data processing device 12. The accuracy improvement unit implements technical improvements to improve the accuracy of voice recognition using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, conversion unit, generation unit, display unit, database unit, learning management unit, and accuracy improvement unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit inputs voice using the microphone 238 of the headset-type terminal 314. The conversion unit converts the voice into text using the specific processing unit 290 of the data processing device 12. The generation unit converts the text into sign language video using the specific processing unit 290 of the data processing device 12. The display unit displays the text and sign language video on the display 343 of the headset-type terminal 314. The database unit accesses the sign language database using the database 24 of the data processing device 12. The learning management unit manages the learning method of the generation AI using the specific processing unit 290 of the data processing device 12. The accuracy improvement unit uses the specific processing unit 290 of the data processing device 12 to implement technical improvements to improve the accuracy of voice recognition. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, conversion unit, generation unit, display unit, database unit, learning management unit, and accuracy improvement unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit inputs voice using the microphone 238 of the robot 414. The conversion unit converts the voice into text using the specific processing unit 290 of the data processing device 12. The generation unit converts the text into sign language video using the specific processing unit 290 of the data processing device 12. The display unit displays the text and sign language video on the display of the robot 414. The database unit accesses the sign language database using the database 24 of the data processing device 12. The learning management unit manages the learning method of the generation AI using the specific processing unit 290 of the data processing device 12. The accuracy improvement unit implements technical improvements to improve the accuracy of voice recognition using the specific processing unit 290 of the data processing device 12.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The reception unit can analyze the tone and speed of the voice when the user inputs voice and estimate the user's emotions. For example, if the user speaks quickly and in a high tone, it can estimate that the user is excited and adjust the timing of the voice input. On the other hand, if the user speaks slowly and in a low tone, it can estimate that the user is relaxed and optimize the timing of the voice input. Furthermore, it can analyze fluctuations in the user's voice in real time and adjust the voice input method according to changes in emotion. This makes it possible to input voice according to the user's emotions.

[0111] When converting speech to text, the conversion unit can improve conversion accuracy by taking into account the context of the speech. For example, it analyzes the context of the speech and converts it into appropriate text. In order to understand the context of the speech and convert it into natural-sounding text, the generation AI takes into account the content of the conversation before and after and the speaker's intention. This improves conversion accuracy by taking into account the context of the speech.

[0112] The generation unit can estimate the user's emotions and adjust the sign language video generation method based on the estimated user emotions. For example, if the user is relaxed, a sign language video that progresses at a leisurely pace is generated. The user's facial expressions are captured with a camera and their emotions are estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expressions. If the user is in a hurry, a sign language video that emphasizes the shortest route is generated. The user's voice is recorded and their emotions are estimated using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, if the user is excited, a sign language video with visually stimulating effects is generated. The user's biometric data (heart rate and electrodermal activity) is collected with a sensor and their emotions are estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. In this way, the sign language video generation method can be adjusted according to the user's emotions, thereby generating more appropriate sign language videos.

[0113] The display unit can estimate the user's emotions and adjust the display method based on the estimated user emotions. For example, if the user is nervous, a simple, highly visible display method is provided. The user's facial expression is captured with a camera and their emotions are estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expression. Furthermore, if the user is relaxed, a display method including detailed information is provided. The user's voice is recorded and their emotions are estimated using voice analysis technology. For example, the tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, if the user is in a hurry, a display method that focuses on the main points is provided. The user's biometric data (heart rate and electrodermal activity) is collected with a sensor and their emotions are estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows the display method to be adjusted according to the user's emotions, making it possible to display more appropriate information.

[0114] The database unit can estimate the user's emotions and adjust database search results based on the estimated user emotions. For example, if the user is nervous, simple and easy-to-understand search results are provided. The user's facial expression is captured with a camera and their emotions are estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on changes in facial expressions. If the user is relaxed, detailed search results are provided. The user's voice is recorded and their emotions are estimated using voice analysis technology. For example, the tone and speed of voice are analyzed to calculate an emotion score. Furthermore, if the user is in a hurry, search results that focus on the main points are provided. The user's biometric data (heart rate and electrodermal activity) is collected with a sensor and their emotions are estimated using an emotion estimation algorithm. For example, an emotion score is calculated based on heart rate fluctuations. This allows the search results to be adjusted according to the user's emotions, thereby providing more appropriate search results.

[0115] The reception unit can filter surrounding environmental sounds to remove noise when inputting voice. For example, the reception unit can analyze surrounding environmental sounds in real time when inputting voice and remove noise. The reception unit can use noise canceling technology to remove surrounding noise. For example, it can filter noise in a specific frequency band. The reception unit can reduce background noise when inputting voice and achieve clear voice input. For example, it can use filtering technology to reduce background noise when inputting voice. This allows the reception unit to filter surrounding environmental sounds and achieve clear voice input.

[0116] When converting speech to text, the conversion unit can take into account the attribute information of the speaker of the speech. For example, if the speaker of the speech is a child, the text is converted into simple language. The attribute information of the speaker of the speech is saved in a database and analyzed. For example, if the speaker of the speech is an expert, technical terms are appropriately converted into text. If the speaker of the speech is a foreigner, the accent is taken into account when converting into text. This allows for more appropriate text conversion by taking into account the speaker's attribute information.

[0117] When converting text into sign language video, the generation unit can improve generation accuracy by taking into account the context of the text. For example, it analyzes the context of the text and converts it into an appropriate sign language video. Generation accuracy is improved by taking into account the context of the text. For example, it understands the context of the text and converts it into natural sign language video. To analyze the context of the text, the generation AI takes into account the surrounding sentences and related topics. This improves generation accuracy by taking into account the context of the text.

[0118] When displaying, the display unit can select an appropriate display method by referring to the user's past display history. For example, it can preferentially provide a display method that the user has used favorably in the past. It stores the user's past display history in a database and analyzes it. For example, it can suggest the optimal display method for a specific time period based on the user's past display history. It analyzes the user's past display history in chronological order to select the optimal display method. For example, it can analyze the user's past display history and select the most efficient display method. In this way, it is possible to provide the optimal display method to the user by referring to the past display history.

[0119] During learning, the learning management unit can optimize the learning algorithm by referring to past learning data. For example, it analyzes past learning data and selects the optimal learning algorithm. It saves past learning data in a database and analyzes it. For example, it adjusts the parameters of the learning algorithm by referring to past learning data. It optimizes the learning algorithm based on past learning data. In this way, the learning algorithm can be optimized by referring to past learning data.

[0120] The processing flow of the second embodiment will be briefly explained below.

[0121] Step 1: The reception unit inputs voice. For example, the user can input voice using a microphone on a smartphone or tablet. Step 2: The conversion unit converts the speech input by the reception unit into text. For example, the generation AI converts speech into text using speech recognition technology. The generation AI analyzes the speech and converts it into text. For example, if the speech "hello" is input, the generation AI converts this into the text "hello." Step 3: The generation unit converts the text converted by the conversion unit into a sign language video. For example, the generation AI understands the content of the text and generates a corresponding sign language video. The generation AI analyzes the text and generates an appropriate sign language video. For example, for the text "Hello," the generation AI generates a sign language video of "Hello." Step 4: The display unit displays the text or sign language video generated by the generation unit. For example, the text or sign language video can be displayed on the screen of the user's smartphone or tablet. This allows the system to enable people with hearing impairments to understand audio information in text or sign language, eliminating communication barriers.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0124] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] 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.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] 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.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 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.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] 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.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] 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.

[0150] 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.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0156] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 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.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] 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.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0166] 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.

[0167] 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.

[0168] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0169] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0170] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0172] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0173] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0174] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0175] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0176] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0177] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0178] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0179] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0180] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0182] 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.

[0183] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0184] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0185] 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.

[0186] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0187] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0188] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0189] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0190] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0191] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0192] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0193] [Explanation of symbols]

[0194] 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 reception unit for inputting voice; a conversion unit that converts the voice input by the reception unit into text; a generation unit that converts the text converted by the conversion unit into a sign language video; a display unit that displays the text or sign language video generated by the generation unit; Equipped with A system characterized by:

2. Equipped with a database section that uses a sign language database 2. The system of claim 1.

3. Equipped with a learning management unit that manages the learning method of the generative AI 2. The system of claim 1.

4. Equipped with an accuracy improvement department that implements technical improvements to improve the accuracy of voice recognition 2. The system of claim 1.

5. The reception unit Input audio using the microphone on your smartphone or tablet 2. The system of claim 1.

6. The display unit Display text or sign language videos on your smartphone or tablet screen 2. The system of claim 1.

7. The reception unit Estimate the user's emotions and adjust the timing of voice input based on the estimated user emotions.

2. The system of claim 1.

8. The reception unit Analyze the user's past voice input history and select the appropriate input method 2. The system of claim 1.

Images