System

Abstract

An object of a system according to an embodiment is to smoothly perform communication between different languages and propose an appropriate answering method.SOLUTION: A system according to an embodiment includes a speech recognition unit, a translation unit, and an answer suggestion unit. The voice recognition unit recognizes an utterance of a user. The translation unit translates the speech recognized by the speech recognition unit into the user's native language. The reply suggestion unit suggests an appropriate reply method based on the text translated by the translation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to communicate smoothly between different languages ​​and finding an appropriate way to respond.

[0005] The system according to the embodiment aims to facilitate smooth communication between different languages ​​and to suggest appropriate ways of replying. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, a translation unit, and a reply suggestion unit. The speech recognition unit recognizes a user's speech. The translation unit translates the speech recognized by the speech recognition unit into the user's native language. The reply suggestion unit suggests an appropriate reply based on the text translated by the translation unit. [Effects of the Invention]

[0007] The system according to the embodiment can smoothly communicate between different languages ​​and suggest appropriate ways of replying. [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 translation app according to an embodiment of the present invention is a system that automatically recognizes a user's speech, translates it using a generation AI, and suggests an appropriate response. This makes it easier for people who speak different languages ​​to communicate with each other and promotes international exchange.

[0029] A translation app according to an embodiment includes a speech recognition unit, a translation unit, and a reply suggestion unit. The speech recognition unit recognizes a user's speech. For example, the speech recognition unit converts the user's speech into text data using speech recognition technology. The speech recognition unit can also recognize speech in real time and convert it into text data. The speech recognition unit can also use noise cancellation technology to remove background noise and accurately recognize the speech. For example, when a user says, "Hello, how are you?", the speech recognition unit converts the speech into text data. The translation unit translates the speech recognized by the speech recognition unit into the user's native language. For example, the translation unit uses a generation AI to translate the English utterance "How are you?" into Japanese "How are you?" The translation unit can also support multiple languages ​​using the generation AI. The translation unit can also understand context and provide more natural translations. For example, the translation unit refers to the content of the preceding and following conversations to understand the context and perform translation. The reply suggestion unit suggests an appropriate reply based on the text translated by the translation unit. For example, the reply suggestion unit may use a generation AI to suggest a reply such as "Yes, I'm fine. How about you?" in response to the question "How are you?" The reply suggestion unit may also refer to the user's past conversation history to generate individually optimized replies. The reply suggestion unit may also use an emotion estimation function to suggest replies based on the user's emotions. For example, if the user is sad, the reply suggestion unit may suggest words of comfort. This allows the translation app according to the embodiment to facilitate communication between people who speak different languages ​​and promote international exchange. For example, this allows for smooth conversations with local people when traveling and enables quick and accurate communication in business situations.

[0030] The speech recognition unit can automatically detect a speaker's accent or dialect and introduce an algorithm that adapts to it. For example, the speech recognition unit develops an algorithm that automatically detects a speaker's accent or dialect. For example, it collects accent data for each region and incorporates it into a speech recognition model. The speech recognition unit also detects a speaker's accent or dialect and introduces an algorithm that adapts to it. For example, it dynamically switches a speech recognition model that corresponds to a specific dialect. The speech recognition unit also analyzes a speaker's accent or dialect in real time and introduces an algorithm that adapts to it. For example, it learns the speaker's pronunciation patterns and optimizes the speech recognition model. This makes it possible to recognize speech that adapts to a speaker's accent or dialect.

[0031] The speech recognition unit may incorporate technology to filter background or environmental sounds and minimize the effects of noise. For example, the speech recognition unit may incorporate technology to filter background or environmental sounds. For example, noise canceling technology may be used to extract only the speaker's voice. Furthermore, the speech recognition unit may incorporate technology to analyze background or environmental sounds in real time and minimize the effects of noise to improve the accuracy of speech recognition. For example, the speech recognition unit may detect ambient sounds and adjust a speech recognition model. Furthermore, the speech recognition unit may develop an algorithm to filter background or environmental sounds. For example, a filter that removes specific frequency bands may be applied to reduce the effects of noise. This enables speech recognition with minimal effects of noise.

[0032] The speech recognition unit can display subtitles of conversation content in real time, providing an assistance function for the hearing impaired. The speech recognition unit, for example, uses speech recognition technology to develop a system that displays subtitles of conversation content in real time. For example, subtitles are displayed on the screen of a smartphone or tablet. The speech recognition unit also uses speech recognition technology to display subtitles of conversation content in real time as an assistance function for the hearing impaired. For example, subtitles are displayed during meetings and lectures. The speech recognition unit also uses speech recognition technology to display subtitles of conversation content in real time, providing an assistance function for the hearing impaired. For example, subtitles for television programs and movies are automatically generated. This makes it possible to provide an assistance function for the hearing impaired.

[0033] The speech recognition unit can automatically summarize the content of a conversation, making it possible to understand long conversations in a short time. The speech recognition unit, for example, uses speech recognition technology to develop a system that automatically summarizes the content of a conversation. For example, it automatically generates meeting minutes and extracts key points. The speech recognition unit also uses speech recognition technology to automatically summarize the content of a conversation, making it possible to understand long conversations in a short time. For example, it provides summaries of interviews and lectures. The speech recognition unit also uses speech recognition technology to automatically summarize the content of a conversation, making it possible to understand long conversations in a short time. For example, it generates summaries of podcasts and webinars. This makes it possible to understand long conversations in a short time.

[0034] The translation unit can refer to the content of the preceding and following conversation to understand the context and provide a more natural translation. For example, the translation unit develops an algorithm that refers to the content of the preceding and following conversation when translating and understands the context. For example, it analyzes the flow of the conversation and provides an appropriate translation. The translation unit can also analyze the content of the preceding and following conversation in real time to understand the context and provide a more natural translation. For example, it takes into account the theme and topic of the conversation. The translation unit can also introduce an algorithm that refers to the content of the preceding and following conversation when translating and understands the context. For example, it adjusts the translation based on background information of the conversation. This enables natural translation that understands the context.

[0035] The translation department can automatically learn technical terminology and industry-specific expressions and translate them appropriately. For example, to improve translation accuracy, the translation department develops algorithms that automatically learn technical terminology and industry-specific expressions. For example, it learns medical and technical terminology. The translation department also builds a system that automatically learns technical terminology and industry-specific expressions and translates them appropriately. For example, it reflects legal and financial terminology in translations. The translation department also learns technical terminology and industry-specific expressions in real time and translates them appropriately to improve translation accuracy. For example, it responds to new technologies and trends. This makes it possible to translate text that is compatible with technical terminology and industry-specific expressions.

[0036] The translation department can collect user feedback on the translation results and continuously improve the translation algorithm. For example, the translation department develops a system that collects user feedback on the translation results and continuously improves the translation algorithm. For example, the algorithm is adjusted based on user ratings and comments. The translation department also collects user feedback in real time and improves the translation algorithm. For example, the degree of satisfaction with the translation results is evaluated. The translation department also builds a system that continuously improves the translation algorithm based on user feedback on the translation results. For example, updates are made that reflect user opinions. This allows the translation algorithm to be improved based on user feedback.

[0037] The translation department can perform automatic translation of emails and chats between different languages ​​to facilitate business communication. For example, the translation department uses the translation function to develop a system that performs automatic translation of emails and chats between different languages. For example, it provides automatic translation of business emails. The translation department also performs automatic translation of chats between different languages ​​in real time to facilitate business communication. For example, it supports communication between international teams. The translation department also uses the translation function to perform automatic translation of emails and chats between different languages ​​to build a system that facilitates business communication. For example, it realizes multilingual support for customer support. This facilitates business communication between different languages.

[0038] The translation department can translate local signs and menus in real time for travelers to provide visual support. For example, the translation department uses the translation function to develop a system that translates local signs and menus in real time for travelers. For example, the sign is translated using a smartphone camera. The translation department also translates local signs and menus in real time to provide visual support for travelers. For example, restaurant menus are translated and displayed. The translation department also uses the translation function to build a system that translates local signs and menus in real time for travelers to provide visual support. For example, information boards at tourist spots are translated. This makes it possible to provide visual support to travelers.

[0039] The reply suggestion unit can refer to the user's past conversation history and generate individually optimized replies. For example, when proposing reply methods, the reply suggestion unit develops an algorithm that refers to the user's past conversation history and generates individually optimized replies. For example, it learns past conversation patterns and provides appropriate replies. The reply suggestion unit also analyzes the user's past conversation history in real time and generates individually optimized replies. For example, it provides replies based on the user's preferences and interests. The reply suggestion unit also builds a system that refers to the user's past conversation history when proposing reply methods and generates individually optimized replies. For example, it adjusts replies based on the user's utterance history. This makes it possible to provide replies that are optimized based on the user's past conversation history.

[0040] The reply suggestion unit can automatically adjust the tone and formality of a conversation to provide an appropriate reply. For example, the reply suggestion unit develops an algorithm that automatically adjusts the tone and formality of a conversation when suggesting reply methods. For example, it provides a friendly reply for casual conversations and a formal reply for business conversations. The reply suggestion unit also builds a system that analyzes the tone and formality of a conversation in real time and provides an appropriate reply. For example, it adjusts the reply based on the content and context of the user's remarks. The reply suggestion unit also introduces an algorithm that automatically adjusts the tone and formality of a conversation when suggesting reply methods to provide an appropriate reply. For example, it changes the reply style depending on the purpose of the conversation and the person being spoken to. This makes it possible to provide an appropriate reply according to the tone and formality of the conversation.

[0041] The reply suggestion unit can automatically generate follow-up questions to gain a deeper understanding of the user's intent and lead to a more appropriate reply. For example, when proposing a reply method, the reply suggestion unit develops an algorithm that automatically generates follow-up questions to gain a deeper understanding of the user's intent. For example, it generates related questions based on the content of the user's statement. The reply suggestion unit also builds a system that automatically generates follow-up questions in real time to gain a deeper understanding of the user's intent and lead to a more appropriate reply. For example, it returns specific questions in response to the user's statement. The reply suggestion unit also introduces an algorithm that automatically generates follow-up questions to gain a deeper understanding of the user's intent and lead to a more appropriate reply when proposing a reply method. For example, it generates questions that clarify ambiguous parts of the user's statement. This allows for a deeper understanding of the user's intent and a more appropriate reply to be provided.

[0042] The reply suggestion unit can build an automated customer support response system and improve the efficiency of customer support. The reply suggestion unit, for example, uses the reply method suggestions to build an automated customer support response system. For example, it automatically provides an appropriate response to a customer inquiry. The reply suggestion unit also builds an automated customer support response system and improves the efficiency of customer support. For example, it provides an automatic response to a frequently asked question. The reply suggestion unit also uses the reply method suggestions to build an automated customer support response system and develop a system that improves the efficiency of customer support. For example, it generates an appropriate response based on the content of the customer inquiry. This allows the automated customer support response system to improve the efficiency of customer support.

[0043] The reply suggestion unit is capable of developing an interactive learning support system in the field of education that provides appropriate replies to students' questions. The reply suggestion unit, for example, uses the reply method suggestions to develop an interactive learning support system in the field of education. For example, it automatically provides appropriate replies to students' questions. The reply suggestion unit is also capable of developing an interactive learning support system in the field of education that provides appropriate replies to students' questions. For example, it provides detailed explanations to questions about learning content. The reply suggestion unit is also capable of developing an interactive learning support system in the field of education that uses the reply method suggestions to build a system that provides appropriate replies to students' questions. For example, it generates replies according to the student's level of understanding. This allows the interactive learning support system in the field of education to provide appropriate replies to students' questions.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The voice recognition unit can analyze the characteristics of a speaker's voice and identify individual speakers. For example, the voice recognition unit can analyze a speaker's voiceprint and identify a specific speaker. The voice recognition unit can also learn the characteristics of a speaker's voice and distinguish between multiple speakers. For example, it can individually recognize the speech of multiple participants in a conference. The voice recognition unit can also analyze the characteristics of a speaker's voice in real time and identify individual speakers. For example, it can identify who is speaking within a family. This makes it possible to provide services customized for each speaker.

[0046] The translation unit can select a translation style according to the user's preferences. For example, if the user prefers casual translations, the translation unit will use casual expressions. The translation unit can also refer to the user's past translation history and provide a translation style according to the user's preferences. For example, it will provide a formal translation in a business setting. The translation unit can also dynamically adjust the translation style based on user feedback. For example, if the user prefers a particular expression, it will use that expression preferentially. This makes it possible to provide translation according to the user's preferences.

[0047] The reply suggestion unit can analyze the user's speech speed and rhythm and suggest appropriate timing for replying. For example, if the user speaks quickly, the reply suggestion unit can suggest a quick reply. The reply suggestion unit can also learn the user's speech speed and rhythm and provide optimal reply timing. For example, if a user speaks slowly, the reply suggestion unit can suggest a reply with pauses. The reply suggestion unit can also analyze the user's speech speed and rhythm in real time and suggest appropriate timing for replying. For example, if the user speaks while thinking, the reply suggestion unit can suggest a short pause before replying. This can provide a more natural conversation experience.

[0048] The translation unit can track the user's learning progress and provide individually optimized learning content. For example, the translation unit can record the words and phrases the user has learned and reflect them in the next study session. The translation unit can also analyze the user's learning progress in real time and suggest appropriate learning content. For example, it can provide learning content that focuses on areas the user is weak in. The translation unit can also track the user's learning progress over a long period of time and optimize the learning plan. For example, it can suggest regular review. This can maximize the user's learning effectiveness.

[0049] The speech recognition unit can analyze the content of a speaker's utterance and automatically search for and provide related information. For example, when a speaker is talking about a specific topic, the speech recognition unit can search for and provide information related to that topic. The speech recognition unit can also analyze the content of a speaker's utterance in real time and provide related information. For example, when a speaker asks a question, the speech recognition unit can search for and provide an answer to that question. The speech recognition unit can also analyze the content of a speaker's utterance over a long period of time and provide related information. For example, related information can be provided based on what the speaker has said in the past. This makes it possible to provide information according to the content of a speaker's utterance.

[0050] The reply suggestion unit can analyze the content of a user's utterance and suggest related topics. For example, when a user is talking about a specific topic, the reply suggestion unit can suggest other topics related to that topic. The reply suggestion unit can also analyze the content of a user's utterance in real time and suggest related topics. For example, when a user is talking about traveling, the reply suggestion unit can suggest recommended travel spots. The reply suggestion unit can also analyze the content of a user's utterance over a long period of time and suggest related topics. For example, the reply suggestion unit can suggest related topics based on content that the user has spoken in the past. This makes it possible to suggest topics based on the content of a user's utterance.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The voice recognition unit recognizes the user's speech. For example, the voice recognition unit converts the user's speech into text data using voice recognition technology. The voice recognition unit can also recognize speech in real time and convert it into text data. Furthermore, the voice recognition unit can also use noise canceling technology to remove background sounds and accurately recognize speech. For example, when a user says, "Hello, how are you?", the voice is converted into text data. Step 2: The translation unit translates the utterance recognized by the speech recognition unit into the user's native language. For example, the translation unit uses a generation AI to translate the English utterance "How are you?" into Japanese "How are you?". The translation unit can also use generation AI to support multiple languages. Furthermore, the translation unit can understand the context and provide a more natural translation. For example, it refers to the content of the conversation before and after the utterance to understand the context and perform the translation. Step 3: The reply suggestion unit suggests an appropriate response based on the text translated by the translation unit. For example, the reply suggestion unit uses a generation AI to suggest a response such as "Yes, I'm fine. How about you?" in response to the question "How are you?" The reply suggestion unit can also refer to the user's past conversation history to generate individually optimized responses. Furthermore, the reply suggestion unit can use an emotion estimation function to suggest responses based on the user's emotions. For example, if the user is sad, it can suggest words of comfort.

[0053] (Example 2) A translation app according to an embodiment of the present invention is a system that automatically recognizes a user's speech, translates it using a generation AI, and suggests an appropriate response. This makes it easier for people who speak different languages ​​to communicate with each other and promotes international exchange.

[0054] A translation app according to an embodiment includes a speech recognition unit, a translation unit, and a reply suggestion unit. The speech recognition unit recognizes a user's speech. For example, the speech recognition unit converts the user's speech into text data using speech recognition technology. The speech recognition unit can also recognize speech in real time and convert it into text data. The speech recognition unit can also use noise cancellation technology to remove background noise and accurately recognize the speech. For example, when a user says, "Hello, how are you?", the speech recognition unit converts the speech into text data. The translation unit translates the speech recognized by the speech recognition unit into the user's native language. For example, the translation unit uses a generation AI to translate the English utterance "How are you?" into Japanese "How are you?" The translation unit can also support multiple languages ​​using the generation AI. The translation unit can also understand context and provide more natural translations. For example, the translation unit refers to the content of the preceding and following conversations to understand the context and perform translation. The reply suggestion unit suggests an appropriate reply based on the text translated by the translation unit. For example, the reply suggestion unit may use a generation AI to suggest a reply such as "Yes, I'm fine. How about you?" in response to the question "How are you?" The reply suggestion unit may also refer to the user's past conversation history to generate individually optimized replies. The reply suggestion unit may also use an emotion estimation function to suggest replies based on the user's emotions. For example, if the user is sad, the reply suggestion unit may suggest words of comfort. This allows the translation app according to the embodiment to facilitate communication between people who speak different languages ​​and promote international exchange. For example, this allows for smooth conversations with local people when traveling and enables quick and accurate communication in business situations.

[0055] The speech recognition unit can estimate the speaker's emotions and adjust the translation accuracy according to the emotions. The speech recognition unit, for example, analyzes the tone, pitch, speed, etc. of the voice to estimate the speaker's emotions. For example, if the speaker is angry, the emotion is reflected in the translation result. The speech recognition unit also estimates the speaker's emotions and adjusts the translation accuracy according to the emotions. For example, if the speaker is sad, the translation result is expressed more politely. The speech recognition unit also analyzes the speaker's emotions in real time and adjusts the translation accuracy according to the emotions. For example, if the speaker is excited, the translation result is expressed more emphatically. This makes it possible to adjust the translation accuracy according to the speaker's emotions.

[0056] The speech recognition unit can automatically detect a speaker's accent or dialect and introduce an algorithm that adapts to it. For example, the speech recognition unit develops an algorithm that automatically detects a speaker's accent or dialect. For example, it collects accent data for each region and incorporates it into a speech recognition model. The speech recognition unit also detects a speaker's accent or dialect and introduces an algorithm that adapts to it. For example, it dynamically switches a speech recognition model that corresponds to a specific dialect. The speech recognition unit also analyzes a speaker's accent or dialect in real time and introduces an algorithm that adapts to it. For example, it learns the speaker's pronunciation patterns and optimizes the speech recognition model. This makes it possible to recognize speech that adapts to a speaker's accent or dialect.

[0057] The speech recognition unit may incorporate technology to filter background or environmental sounds and minimize the effects of noise. For example, the speech recognition unit may incorporate technology to filter background or environmental sounds. For example, noise canceling technology may be used to extract only the speaker's voice. Furthermore, the speech recognition unit may incorporate technology to analyze background or environmental sounds in real time and minimize the effects of noise to improve the accuracy of speech recognition. For example, the speech recognition unit may detect ambient sounds and adjust a speech recognition model. Furthermore, the speech recognition unit may develop an algorithm to filter background or environmental sounds. For example, a filter that removes specific frequency bands may be applied to reduce the effects of noise. This enables speech recognition with minimal effects of noise.

[0058] The speech recognition unit can display subtitles of conversation content in real time, providing an assistance function for the hearing impaired. The speech recognition unit, for example, uses speech recognition technology to develop a system that displays subtitles of conversation content in real time. For example, subtitles are displayed on the screen of a smartphone or tablet. The speech recognition unit also uses speech recognition technology to display subtitles of conversation content in real time as an assistance function for the hearing impaired. For example, subtitles are displayed during meetings and lectures. The speech recognition unit also uses speech recognition technology to display subtitles of conversation content in real time, providing an assistance function for the hearing impaired. For example, subtitles for television programs and movies are automatically generated. This makes it possible to provide an assistance function for the hearing impaired.

[0059] The speech recognition unit can automatically summarize the content of a conversation, making it possible to understand long conversations in a short time. The speech recognition unit, for example, uses speech recognition technology to develop a system that automatically summarizes the content of a conversation. For example, it automatically generates meeting minutes and extracts key points. The speech recognition unit also uses speech recognition technology to automatically summarize the content of a conversation, making it possible to understand long conversations in a short time. For example, it provides summaries of interviews and lectures. The speech recognition unit also uses speech recognition technology to automatically summarize the content of a conversation, making it possible to understand long conversations in a short time. For example, it generates summaries of podcasts and webinars. This makes it possible to understand long conversations in a short time.

[0060] The speech recognition unit uses the emotion estimation function to provide speech feedback according to the speaker's emotion, thereby realizing a more natural conversation experience. For example, the speech recognition unit develops a system that uses the emotion estimation function to provide speech feedback according to the speaker's emotion. For example, if the speaker is happy, positive feedback is returned. The speech recognition unit also analyzes the speaker's emotion in real time and provides speech feedback according to the emotion. For example, if the speaker is sad, words of comfort are returned. The speech recognition unit also uses the emotion estimation function to provide speech feedback according to the speaker's emotion, thereby realizing a more natural conversation experience. For example, if the speaker is excited, words of sympathy are returned. In this way, speech feedback according to the speaker's emotion is provided, thereby realizing a more natural conversation experience.

[0061] The translation unit can refer to the content of the preceding and following conversation to understand the context and provide a more natural translation. For example, the translation unit develops an algorithm that refers to the content of the preceding and following conversation when translating and understands the context. For example, it analyzes the flow of the conversation and provides an appropriate translation. The translation unit can also analyze the content of the preceding and following conversation in real time to understand the context and provide a more natural translation. For example, it takes into account the theme and topic of the conversation. The translation unit can also introduce an algorithm that refers to the content of the preceding and following conversation when translating and understands the context. For example, it adjusts the translation based on background information of the conversation. This enables natural translation that understands the context.

[0062] The translation department can automatically learn technical terminology and industry-specific expressions and translate them appropriately. For example, to improve translation accuracy, the translation department develops algorithms that automatically learn technical terminology and industry-specific expressions. For example, it learns medical and technical terminology. The translation department also builds a system that automatically learns technical terminology and industry-specific expressions and translates them appropriately. For example, it reflects legal and financial terminology in translations. The translation department also learns technical terminology and industry-specific expressions in real time and translates them appropriately to improve translation accuracy. For example, it responds to new technologies and trends. This makes it possible to translate text that is compatible with technical terminology and industry-specific expressions.

[0063] The translation department can collect user feedback on the translation results and continuously improve the translation algorithm. For example, the translation department develops a system that collects user feedback on the translation results and continuously improves the translation algorithm. For example, the algorithm is adjusted based on user ratings and comments. The translation department also collects user feedback in real time and improves the translation algorithm. For example, the degree of satisfaction with the translation results is evaluated. The translation department also builds a system that continuously improves the translation algorithm based on user feedback on the translation results. For example, updates are made that reflect user opinions. This allows the translation algorithm to be improved based on user feedback.

[0064] The translation department can perform automatic translation of emails and chats between different languages ​​to facilitate business communication. For example, the translation department uses the translation function to develop a system that performs automatic translation of emails and chats between different languages. For example, it provides automatic translation of business emails. The translation department also performs automatic translation of chats between different languages ​​in real time to facilitate business communication. For example, it supports communication between international teams. The translation department also uses the translation function to perform automatic translation of emails and chats between different languages ​​to build a system that facilitates business communication. For example, it realizes multilingual support for customer support. This facilitates business communication between different languages.

[0065] The translation department can translate local signs and menus in real time for travelers to provide visual support. For example, the translation department uses the translation function to develop a system that translates local signs and menus in real time for travelers. For example, the sign is translated using a smartphone camera. The translation department also translates local signs and menus in real time to provide visual support for travelers. For example, restaurant menus are translated and displayed. The translation department also uses the translation function to build a system that translates local signs and menus in real time for travelers to provide visual support. For example, information boards at tourist spots are translated. This makes it possible to provide visual support to travelers.

[0066] The translation unit can use the emotion estimation function to analyze the user's emotional response to the translated text and select a translation style according to the emotion. The translation unit, for example, uses the emotion estimation function to develop a system that analyzes the user's emotional response to the translated text. For example, the translation unit analyzes the user's facial expressions and voice and calculates an emotion score. The translation unit also selects a translation style according to the emotion based on the user's emotional response. For example, a casual translation style is provided for positive emotions, and a formal translation style is provided for negative emotions. The translation unit also uses the emotion estimation function to build a system that analyzes the user's emotional response to the translated text in real time and selects a translation style according to the emotion. For example, the translation style is dynamically adjusted according to changes in the user's emotions. This makes it possible to select a translation style according to the user's emotions.

[0067] The reply suggestion unit can refer to the user's past conversation history and generate individually optimized replies. For example, when proposing reply methods, the reply suggestion unit develops an algorithm that refers to the user's past conversation history and generates individually optimized replies. For example, it learns past conversation patterns and provides appropriate replies. The reply suggestion unit also analyzes the user's past conversation history in real time and generates individually optimized replies. For example, it provides replies based on the user's preferences and interests. The reply suggestion unit also builds a system that refers to the user's past conversation history when proposing reply methods and generates individually optimized replies. For example, it adjusts replies based on the user's utterance history. This makes it possible to provide replies that are optimized based on the user's past conversation history.

[0068] The reply suggestion unit can automatically adjust the tone and formality of a conversation to provide an appropriate reply. For example, the reply suggestion unit develops an algorithm that automatically adjusts the tone and formality of a conversation when suggesting reply methods. For example, it provides a friendly reply for casual conversations and a formal reply for business conversations. The reply suggestion unit also builds a system that analyzes the tone and formality of a conversation in real time and provides an appropriate reply. For example, it adjusts the reply based on the content and context of the user's remarks. The reply suggestion unit also introduces an algorithm that automatically adjusts the tone and formality of a conversation when suggesting reply methods to provide an appropriate reply. For example, it changes the reply style depending on the purpose of the conversation and the person being spoken to. This makes it possible to provide an appropriate reply according to the tone and formality of the conversation.

[0069] The reply suggestion unit can automatically generate follow-up questions to gain a deeper understanding of the user's intent and lead to a more appropriate reply. For example, when proposing a reply method, the reply suggestion unit develops an algorithm that automatically generates follow-up questions to gain a deeper understanding of the user's intent. For example, it generates related questions based on the content of the user's statement. The reply suggestion unit also builds a system that automatically generates follow-up questions in real time to gain a deeper understanding of the user's intent and lead to a more appropriate reply. For example, it returns specific questions in response to the user's statement. The reply suggestion unit also introduces an algorithm that automatically generates follow-up questions to gain a deeper understanding of the user's intent and lead to a more appropriate reply when proposing a reply method. For example, it generates questions that clarify ambiguous parts of the user's statement. This allows for a deeper understanding of the user's intent and a more appropriate reply to be provided.

[0070] The reply suggestion unit can build an automated customer support response system and improve the efficiency of customer support. The reply suggestion unit, for example, uses the reply method suggestions to build an automated customer support response system. For example, it automatically provides an appropriate response to a customer inquiry. The reply suggestion unit also builds an automated customer support response system and improves the efficiency of customer support. For example, it provides an automatic response to a frequently asked question. The reply suggestion unit also uses the reply method suggestions to build an automated customer support response system and develop a system that improves the efficiency of customer support. For example, it generates an appropriate response based on the content of the customer inquiry. This allows the automated customer support response system to improve the efficiency of customer support.

[0071] The reply suggestion unit is capable of developing an interactive learning support system in the field of education that provides appropriate replies to students' questions. The reply suggestion unit, for example, uses the reply method suggestions to develop an interactive learning support system in the field of education. For example, it automatically provides appropriate replies to students' questions. The reply suggestion unit is also capable of developing an interactive learning support system in the field of education that provides appropriate replies to students' questions. For example, it provides detailed explanations to questions about learning content. The reply suggestion unit is also capable of developing an interactive learning support system in the field of education that uses the reply method suggestions to build a system that provides appropriate replies to students' questions. For example, it generates replies according to the student's level of understanding. This allows the interactive learning support system in the field of education to provide appropriate replies to students' questions.

[0072] The reply suggestion unit uses the emotion estimation function to suggest replies that correspond to the user's emotions, thereby realizing more empathetic communication. The reply suggestion unit, for example, uses the emotion estimation function to develop a system that suggests replies that correspond to the user's emotions. For example, if the user is sad, it returns words of comfort. The reply suggestion unit also analyzes the user's emotions in real time and suggests replies that correspond to the emotions. For example, if the user is happy, it returns words of empathy. The reply suggestion unit also uses the emotion estimation function to suggest replies that correspond to the user's emotions, thereby building a system that realizes more empathetic communication. For example, it adjusts replies in response to changes in the user's emotions. This allows it to suggest replies that correspond to the user's emotions and realize more empathetic communication.

[0073] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0074] The voice recognition unit can analyze the characteristics of a speaker's voice and identify individual speakers. For example, the voice recognition unit can analyze a speaker's voiceprint and identify a specific speaker. The voice recognition unit can also learn the characteristics of a speaker's voice and distinguish between multiple speakers. For example, it can individually recognize the speech of multiple participants in a conference. The voice recognition unit can also analyze the characteristics of a speaker's voice in real time and identify individual speakers. For example, it can identify who is speaking within a family. This makes it possible to provide services customized for each speaker.

[0075] The translation unit can select a translation style according to the user's preferences. For example, if the user prefers casual translations, the translation unit will use casual expressions. The translation unit can also refer to the user's past translation history and provide a translation style according to the user's preferences. For example, it will provide a formal translation in a business setting. The translation unit can also dynamically adjust the translation style based on user feedback. For example, if the user prefers a particular expression, it will use that expression preferentially. This makes it possible to provide translation according to the user's preferences.

[0076] The reply suggestion unit can analyze the user's speech speed and rhythm and suggest appropriate timing for replying. For example, if the user speaks quickly, the reply suggestion unit can suggest a quick reply. The reply suggestion unit can also learn the user's speech speed and rhythm and provide optimal reply timing. For example, if a user speaks slowly, the reply suggestion unit can suggest a reply with pauses. The reply suggestion unit can also analyze the user's speech speed and rhythm in real time and suggest appropriate timing for replying. For example, if the user speaks while thinking, the reply suggestion unit can suggest a short pause before replying. This can provide a more natural conversation experience.

[0077] The voice recognition unit can estimate the speaker's health condition and provide health advice. For example, the voice recognition unit can analyze the speaker's tone of voice and breathing sounds to estimate the stress level. The voice recognition unit can also analyze the speaker's health condition in real time and provide health advice. For example, if the speaker is tired, the voice recognition unit can suggest that the speaker take a rest. The voice recognition unit can also monitor the speaker's health condition over a long period of time and support health management. For example, the voice recognition unit can provide reminders for regular health checks. This can support the speaker's health management.

[0078] The translation unit can track the user's learning progress and provide individually optimized learning content. For example, the translation unit can record the words and phrases the user has learned and reflect them in the next study session. The translation unit can also analyze the user's learning progress in real time and suggest appropriate learning content. For example, it can provide learning content that focuses on areas the user is weak in. The translation unit can also track the user's learning progress over a long period of time and optimize the learning plan. For example, it can suggest regular review. This can maximize the user's learning effectiveness.

[0079] The reply suggestion unit can estimate the user's emotions and suggest replies that correspond to those emotions. For example, if the user is nervous, the reply suggestion unit can suggest replies that will relax the user. The reply suggestion unit can also analyze the user's emotions in real time and suggest replies that correspond to those emotions. For example, if the user is happy, the reply suggestion unit can return words of empathy. The reply suggestion unit can also monitor the user's emotions over a long period of time and suggest replies that correspond to changes in emotions. For example, if the user is depressed, the reply suggestion unit can return words of encouragement. In this way, it is possible to provide replies that correspond to the user's emotions.

[0080] The speech recognition unit can analyze the content of a speaker's utterance and automatically search for and provide related information. For example, when a speaker is talking about a specific topic, the speech recognition unit can search for and provide information related to that topic. The speech recognition unit can also analyze the content of a speaker's utterance in real time and provide related information. For example, when a speaker asks a question, the speech recognition unit can search for and provide an answer to that question. The speech recognition unit can also analyze the content of a speaker's utterance over a long period of time and provide related information. For example, related information can be provided based on what the speaker has said in the past. This makes it possible to provide information according to the content of a speaker's utterance.

[0081] The translation unit can estimate the user's emotions and select a translation style according to the emotions. For example, if the user is angry, the translation unit provides a calm translation style. The translation unit can also analyze the user's emotions in real time and select a translation style according to the emotions. For example, if the user is sad, the translation unit provides a gentle translation style. The translation unit can also monitor the user's emotions over a long period of time and select a translation style according to changes in emotions. For example, if the user is excited, the translation unit provides a calm translation style. This makes it possible to provide translation according to the user's emotions.

[0082] The reply suggestion unit can analyze the content of a user's utterance and suggest related topics. For example, when a user is talking about a specific topic, the reply suggestion unit can suggest other topics related to that topic. The reply suggestion unit can also analyze the content of a user's utterance in real time and suggest related topics. For example, when a user is talking about traveling, the reply suggestion unit can suggest recommended travel spots. The reply suggestion unit can also analyze the content of a user's utterance over a long period of time and suggest related topics. For example, the reply suggestion unit can suggest related topics based on content that the user has spoken in the past. This makes it possible to suggest topics based on the content of a user's utterance.

[0083] The speech recognition unit can estimate the speaker's emotions and suggest music that corresponds to the emotions. For example, if the speaker wants to relax, the speech recognition unit can suggest relaxing music. The speech recognition unit can also analyze the speaker's emotions in real time and suggest music that corresponds to the emotions. For example, if the speaker wants to cheer up, the speech recognition unit can suggest upbeat music. The speech recognition unit can also monitor the speaker's emotions over a long period of time and suggest music that corresponds to changes in emotions. For example, if the speaker is feeling down, the speech recognition unit can suggest encouraging music. This makes it possible to suggest music that corresponds to the speaker's emotions.

[0084] The processing flow of the second embodiment will be briefly explained below.

[0085] Step 1: The voice recognition unit recognizes the user's speech. For example, the voice recognition unit converts the user's speech into text data using voice recognition technology. The voice recognition unit can also recognize speech in real time and convert it into text data. Furthermore, the voice recognition unit can also use noise canceling technology to remove background sounds and accurately recognize speech. For example, when a user says, "Hello, how are you?", the voice is converted into text data. Step 2: The translation unit translates the utterance recognized by the speech recognition unit into the user's native language. For example, the translation unit uses a generation AI to translate the English utterance "How are you?" into Japanese "How are you?". The translation unit can also use generation AI to support multiple languages. Furthermore, the translation unit can understand the context and provide a more natural translation. For example, it refers to the content of the conversation before and after the utterance to understand the context and perform the translation. Step 3: The reply suggestion unit suggests an appropriate response based on the text translated by the translation unit. For example, the reply suggestion unit uses a generation AI to suggest a response such as "Yes, I'm fine. How about you?" in response to the question "How are you?" The reply suggestion unit can also refer to the user's past conversation history to generate individually optimized responses. Furthermore, the reply suggestion unit can use an emotion estimation function to suggest responses based on the user's emotions. For example, if the user is sad, it can suggest words of comfort.

[0086] 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.

[0087] 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 generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0088] 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.

[0089] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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).

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] 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.

[0104] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0105] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0115] 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.

[0116] 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.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] 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.

[0119] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0120] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0129] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0132] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0134] The data processing system 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0140] 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."

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0153] 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 speech recognition unit that recognizes a user's speech; a translation unit that translates the speech recognized by the speech recognition unit into the user's native language; a reply suggestion unit that suggests an appropriate reply method based on the text translated by the translation unit; A system characterized by:

2. The voice recognition unit Estimates the speaker's emotions and adjusts translation accuracy accordingly 2. The system of claim 1.

3. The voice recognition unit Implement algorithms that automatically detect and adapt to the speaker's accent or dialect 2. The system of claim 1.

4. The voice recognition unit Incorporate technology to filter background or environmental sounds and minimize the impact of noise 2. The system of claim 1.

5. The voice recognition unit Provide real-time subtitles of conversations and assistive features for the hearing impaired The system of claim 1 .

Images