system

Abstract

The system according to this embodiment aims to convert user speech into text with high accuracy, perform automatic completion considering grammar and context, and translate into multiple languages. [Solution] The system according to this embodiment comprises a speech recognition unit, an automatic completion unit, and a translation unit. The speech recognition unit converts the user's speech into text. The automatic completion unit performs automatic completion based on grammar and context for the text generated by the speech recognition unit. The translation unit translates the text completed by the automatic completion unit into multiple languages.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there are problems that automatic completion considering grammar and context is not sufficiently performed when converting a user's utterance into text, and translation into multiple languages is difficult.

[0005] The system according to the embodiment aims to accurately convert a user's utterance into text and perform automatic completion considering grammar and context and translation into multiple languages.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a speech recognition unit, an automatic completion unit, and a translation unit. The speech recognition unit converts the user's utterance into text. The automatic completion unit performs automatic completion based on grammar and context for the text generated by the speech recognition unit. The translation unit translates the text completed by the automatic completion unit into multiple languages. [Effects of the Invention]

[0007] The system according to this embodiment can accurately convert user speech into text, perform automatic completion considering grammar and context, and translate into multiple languages. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The AI ​​assistant text input support tool using speech recognition according to an embodiment of the present invention is a system that converts user speech into text with high accuracy and provides an automatic completion function that takes grammar and context into consideration. This system also features support for multiple languages ​​and a translation function, as well as a fashion item styling advice function. First, when a user speaks, the speech recognition unit converts the speech into text with high accuracy. At this time, the speech recognition unit uses AI to analyze the content of the speech and perform accurate text conversion. For example, if a user says, "What's the weather like today?", the content will be displayed as text. Next, an automatic completion function that takes grammar and context into consideration works on the converted text. The automatic completion unit uses AI to analyze grammar and context and perform appropriate completion. For example, if a user inputs, "What are my plans for tomorrow?", the automatic completion unit will complete it to, "What are your plans for tomorrow?". Furthermore, it has support for multiple languages ​​and a translation function. The translation unit uses AI to translate text into other languages. For example, if a user inputs, "Hello", the translation unit will translate it to "Hello". It also has a fashion item styling advice function. The styling advice section uses AI to suggest appropriate fashion items based on the user's input. For example, if the user inputs "Tell me what to wear today," the styling advice section will suggest "A white shirt and black pants would be good." Thus, the present invention is an AI assistant that uses speech recognition to support text input, which has a function to convert user speech into text with high accuracy, an automatic completion function that takes grammar and context into consideration, support and translation functions for multiple languages, and a function to provide styling advice for fashion items. As a result, the AI ​​assistant that uses speech recognition to support text input can convert user speech into text with high accuracy, and is capable of automatic completion that takes grammar and context into consideration, as well as translation into multiple languages.

[0029] The AI ​​assistant text input support tool using speech recognition according to this embodiment comprises a speech recognition unit, an auto-completion unit, and a translation unit. The speech recognition unit converts the user's utterance into text with high accuracy. For example, if the user utters "What's the weather like today?", the speech recognition unit displays the content as text. The speech recognition unit uses AI to analyze the content of the utterance and perform accurate text conversion. For example, the speech recognition unit converts the utterance into text using speech recognition technology. The speech recognition unit converts the utterance into text using speech recognition technology. The speech recognition unit converts the utterance into text using speech recognition technology. The auto-completion unit performs automatic completion of the text generated by the speech recognition unit, taking grammar and context into consideration. For example, if the user inputs "What are my plans for tomorrow?", the auto-completion unit completes it with "What are your plans for tomorrow?". The auto-completion unit uses AI to analyze grammar and context and perform appropriate completion. For example, the auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The automatic completion unit analyzes grammar using grammar analysis technology and context analysis technology. The automatic completion unit analyzes grammar using grammar analysis technology and context analysis technology. The translation unit translates the text completed by the automatic completion unit into multiple languages. For example, if the user inputs "こんにちは" (konnichiwa), the translation unit translates it to "Hello". The translation unit uses AI to translate the text into other languages. For example, the translation unit uses translation technology to translate the text into other languages. The translation unit uses translation technology to translate the text into other languages. The translation unit uses translation technology to translate the text into other languages. As a result, the speech recognition-based text input support tool AI assistant according to this embodiment can convert the user's utterance into text with high accuracy, and enables automatic completion that takes grammar and context into consideration, as well as translation into multiple languages.

[0030] The speech recognition unit accurately converts user speech into text. Specifically, when a user says, "What's the weather like today?", the speech recognition unit displays the content as text. The speech recognition unit uses AI to analyze the content of the speech and perform accurate text conversion. For example, the speech recognition unit converts speech into text using speech recognition technology. The speech recognition unit converts speech into text using speech recognition technology. The speech recognition unit converts speech into text using speech recognition technology. The speech recognition unit utilizes the latest deep learning technology to analyze speech data. Specifically, it converts the speech signal from the time domain to the frequency domain and extracts features such as Mel-frequency cepstrum coefficients (MFCCs). This represents the features of the speech as numerical data, which is then input into a neural network. The neural network is pre-trained on a large amount of speech data, and uses recurrent neural networks (RNNs) and transformer models to improve the accuracy of phoneme and word recognition. As a result, the speech recognition unit is less affected by noise and accent, achieving highly accurate text conversion. Furthermore, the speech recognition unit can learn the user's speech patterns and habits, and perform individual customizations. For example, it can learn phrases and technical terms frequently used by a particular user to improve recognition accuracy. In addition, the speech recognition unit utilizes high-speed hardware and cloud computing to perform real-time processing. This allows it to instantly display what the user says as text, providing a smooth user experience.

[0031] The auto-completion unit performs automatic completion of text generated by the speech recognition unit, taking grammar and context into consideration. Specifically, if a user inputs "What are my plans for tomorrow?", the auto-completion unit will complete it with "What are your plans for tomorrow?". The auto-completion unit uses AI to analyze grammar and context to perform appropriate completion. For example, the auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The auto-completion unit utilizes natural language processing (NLP) technology to analyze the grammatical structure of the input text. Specifically, it performs morphological analysis to identify the part of speech and role of words. Next, it uses dependency structure analysis to clarify the relationships between words in the sentence. This enables grammatically correct completion. Furthermore, the auto-completion unit uses context analysis technology to understand the meaning and intent of the input text. For example, if a user types "What are my plans for tomorrow?", the system will determine from the context that "What are your plans?" is an appropriate completion. Contextual analysis uses large-scale language models such as LLMs to deeply understand the meaning of the context. This allows the auto-completion unit to provide natural completions that align with the user's intent. Furthermore, the auto-completion unit can learn the user's input history and individual usage patterns to perform personalized customization. For example, it can learn frequently used phrases and expressions by specific users to improve the accuracy of completions. In addition, the auto-completion unit utilizes high-speed hardware and cloud computing to perform real-time completions. This allows for instant completion of text entered by the user, providing a smooth user experience.

[0032] The translation unit translates text completed by the auto-completion unit into multiple languages. Specifically, if a user enters "こんにちは" (konnichiwa), the translation unit translates it as "Hello". The translation unit uses AI to translate text into other languages. For example, the translation unit uses translation technology to translate text into other languages. The translation unit uses translation technology to translate text into other languages. The translation unit uses translation technology to translate text into other languages. The translation unit utilizes neural machine translation (NMT) technology to translate text with high accuracy. Specifically, it uses an encoder-decoder model to first convert the input text into an intermediate representation, and then convert it into the target language. The encoder understands the meaning of the input text and generates an intermediate representation. The decoder generates text in the target language based on that intermediate representation. This process enables accurate translation while preserving context and meaning. Furthermore, the translation unit is pre-trained on a large amount of multilingual data and can understand nuances and grammatical differences between different languages. For example, it can handle not only Japanese to English translation, but also multiple languages ​​such as French and Spanish. Furthermore, the translation unit can learn from the user's input history and individual usage patterns, allowing for personalized customization. For instance, it can learn specialized terminology and phrases frequently used by specific users to improve translation accuracy. In addition, the translation unit utilizes high-speed hardware and cloud computing to perform real-time translations. This enables instant translation of user-input text, providing a smooth user experience.

[0033] The styling advice unit suggests fashion items based on the user's input. For example, if a user inputs "Tell me what to wear today," the styling advice unit will suggest "A white shirt and black pants would be good." The styling advice unit uses AI to suggest appropriate fashion items based on the user's input. For example, the styling advice unit refers to a database of fashion items and selects appropriate items based on the user's input. The styling advice unit refers to a database of fashion items and selects appropriate items based on the user's input. The styling advice unit refers to a database of fashion items and selects appropriate items based on the user's input. This allows the system to suggest appropriate fashion items based on the user's input.

[0034] The speech recognition unit can analyze the user's speaking speed and tone and select the optimal speech recognition algorithm. For example, if the user speaks quickly, the speech recognition unit can switch to high-speed processing. If the user speaks slowly, the speech recognition unit can switch to high-precision processing. If the user's tone is low, the speech recognition unit can switch to a speech recognition algorithm that corresponds to the low-frequency range. This improves recognition accuracy by selecting the optimal speech recognition algorithm according to the user's speaking speed and tone. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's speech data into a generating AI and have the generating AI select the optimal speech recognition algorithm.

[0035] The speech recognition unit can improve recognition accuracy by filtering out background noise during speech recognition. For example, if a user is speaking in a cafe, the speech recognition unit can filter out background noise and recognize only the speech. If a user is speaking in a car, the speech recognition unit can filter out engine noise and recognize only the speech. If a user is speaking in a windy location, the speech recognition unit can filter out wind noise and recognize only the speech. This improves recognition accuracy by filtering out background noise. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input background sound data into a generating AI and have the generating AI perform the filtering process.

[0036] The speech recognition unit can recognize regionally specific pronunciations and dialects by taking into account the user's geographical location information during speech recognition. For example, if the user is in the Kansai region, the speech recognition unit can recognize the Kansai dialect. If the user is in the Tohoku region, the speech recognition unit can recognize the Tohoku dialect. If the user is overseas, the speech recognition unit can recognize the dialect and accent of that region. This improves recognition accuracy by recognizing regionally specific pronunciations and dialects. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's geographical location data into a generating AI and have the generating AI perform the recognition of regionally specific pronunciations and dialects.

[0037] The speech recognition unit can improve recognition accuracy by referring to the user's past speech history during speech recognition. For example, the speech recognition unit can prioritize the recognition of words and phrases that the user has frequently used in the past. The speech recognition unit can learn the user's past speech patterns and improve recognition accuracy. If the user frequently uses certain technical terms, the speech recognition unit can prioritize the recognition of those terms. This improves recognition accuracy by referring to past speech history. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's past speech data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0038] The auto-completion unit can perform optimal completion by referring to the user's past input history during auto-completion. For example, the auto-completion unit can prioritize completing phrases that the user has frequently used in the past. The auto-completion unit can learn the user's past input patterns and perform optimal completion. If the user frequently uses certain technical terms, the auto-completion unit can prioritize completing those terms. This enables optimal completion by referring to past input history. Some or all of the above processes in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input the user's past input data into a generating AI and have the generating AI perform optimal completion.

[0039] The auto-completion unit can customize the content it completes based on the user's area of ​​expertise and interests. For example, if the user works in the medical field, the auto-completion unit can prioritize completing medical terms. If the user works in the technical field, the auto-completion unit can prioritize completing technical terms. If the user enjoys cooking as a hobby, the auto-completion unit can prioritize completing cooking terms. This allows for more appropriate completion by customizing the content based on the user's area of ​​expertise and interests. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input data about the user's area of ​​expertise and interests into a generating AI and have the generating AI perform the customization of the completion content.

[0040] The auto-completion unit can adjust the timing of completion based on the user's input speed. For example, if the user is typing quickly, the auto-completion unit will complete the text quickly. If the user is typing slowly, the auto-completion unit can perform detailed completion. If the user is typing intermittently, the auto-completion unit can complete the text at the appropriate time. By adjusting the timing of completion based on input speed, more appropriate completion becomes possible. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input user input speed data into a generating AI and have the generating AI adjust the timing of completion.

[0041] The auto-completion unit can provide relevant information based on the user's input during auto-completion. For example, if the user inputs "What's the weather like tomorrow?", the auto-completion unit can provide weather forecast information. If the user inputs "When is the next meeting?", the auto-completion unit can provide calendar information. If the user inputs "What's the news today?", the auto-completion unit can provide the latest news information. In this way, by providing relevant information based on the input, the user can obtain useful information. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input the user's input data into a generating AI and have the generating AI perform the task of providing relevant information.

[0042] The translation unit can perform optimal translations by referring to the user's past translation history. For example, the translation unit can prioritize translating phrases that the user has frequently used in the past. The translation unit can learn the user's past translation patterns and perform optimal translations. If the user frequently uses certain technical terms, the translation unit can prioritize translating those terms. This enables optimal translations by referring to past translation history. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the user's past translation data into a generating AI and have the generating AI perform the optimal translation.

[0043] The translation unit can customize the translation content based on the user's area of ​​expertise and interests. For example, if the user works in the medical field, the translation unit will prioritize translating medical terminology. If the user works in the technical field, the translation unit can prioritize translating technical terminology. If the user enjoys cooking as a hobby, the translation unit can prioritize translating cooking terminology. This allows for more appropriate translations by customizing the translation content based on the user's area of ​​expertise and interests. Some or all of the above processing in the translation unit may be performed using AI, for example, or not. For example, the translation unit can input data on the user's area of ​​expertise and interests into a generating AI and have the generating AI perform the customization of the translation content.

[0044] The translation unit can translate region-specific expressions by considering the user's geographical location during translation. For example, if the user is in the Kansai region, the translation unit can translate in the Kansai dialect. If the user is in the Tohoku region, the translation unit can translate in the Tohoku dialect. If the user is overseas, the translation unit can translate in the local dialect and accent. This allows for appropriate translation of region-specific expressions by considering geographical location. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the user's geographical location data into a generating AI and have the generating AI perform the translation of region-specific expressions.

[0045] The translation unit can provide relevant cultural background information based on the user's input during translation. For example, if the user inputs "hello," the translation unit can provide the cultural background of the greeting in that language. If the user inputs "thank you," the translation unit can provide the cultural background of the expression of gratitude in that language. If the user inputs "goodbye," the translation unit can provide the cultural background of the farewell greeting in that language. By providing relevant cultural background information based on the input, the user can obtain useful information. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the user's input data into a generating AI and have the generating AI perform the provision of cultural background information.

[0046] The styling advice unit can provide optimal advice by referring to the user's past fashion history when giving styling advice. For example, the styling advice unit can provide advice based on items the user has liked to wear in the past. The styling advice unit can provide advice considering seasonal trends based on the user's past fashion history. The styling advice unit can provide advice suitable for similar events based on items the user wore at a specific event. This makes it possible to provide optimal advice by referring to past fashion history. Some or all of the above processes in the styling advice unit may be performed using AI, for example, or without AI. For example, the styling advice unit can input the user's past fashion data into a generating AI and have the generating AI execute the optimal advice.

[0047] The styling advice unit can customize the advice given based on the user's body type and preferences. For example, the styling advice unit can suggest items that fit the user's body type well. The styling advice unit can provide color and design options based on the user's preferences. The styling advice unit can suggest accessory coordination according to the user's body type and preferences. By customizing the advice based on body type and preferences, more appropriate advice can be provided. Some or all of the above processes in the styling advice unit may be performed using AI, for example, or without AI. For example, the styling advice unit can input data about the user's body type and preferences into a generating AI and have the generating AI perform the customization of the advice.

[0048] The styling advice unit can suggest region-specific fashion by considering the user's geographical location when providing styling advice. For example, if the user is in an urban area, the styling advice unit can suggest fashion that reflects urban trends. If the user is in a resort area, the styling advice unit can suggest casual fashion suitable for a resort area. If the user is in a cold region, the styling advice unit can suggest cold-weather gear suitable for cold regions. In this way, by considering geographical location information, region-specific fashion can be appropriately suggested. Some or all of the above processing in the styling advice unit may be performed using AI, for example, or without AI. For example, the styling advice unit can input the user's geographical location data into a generating AI and have the generating AI perform region-specific fashion suggestions.

[0049] The styling advice unit can analyze a user's social media activity and suggest relevant fashion items when providing styling advice. For example, the styling advice unit can suggest similar fashion items based on posts that have received many "likes" on social media. The styling advice unit can suggest relevant items by referencing the styles of influencers that the user follows. The styling advice unit can suggest fashion items related to events that the user plans to attend. In this way, by analyzing social media activity, it can appropriately suggest relevant fashion items. Some or all of the above processes in the styling advice unit may be performed using AI, for example, or not using AI. For example, the styling advice unit can input the user's social media data into a generating AI and have the generating AI suggest relevant fashion items.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The speech recognition unit can automatically search for and provide relevant information based on the user's speech. For example, if a user says, "What's the news today?", the speech recognition unit can convert that into text and search for and display the latest relevant news articles. Similarly, if a user says, "Tell me about nearby restaurants," the speech recognition unit can analyze that and provide information about nearby restaurants. Furthermore, if a user says, "What time is the next train?", the speech recognition unit can analyze that and display the next train schedule. This improves convenience by providing relevant information based on the user's speech.

[0052] The speech recognition unit can set appropriate reminders based on the user's speech. For example, if a user says, "Remind me of tomorrow's meeting," the speech recognition unit converts the content into text and sets a reminder on the calendar. Also, if a user says, "Tell me when to take my medicine," the speech recognition unit analyzes the content and sets a reminder at the specified time. Furthermore, if a user says, "Remind me of the next payment deadline," the speech recognition unit analyzes the content and sets a reminder for the payment deadline. In this way, by setting reminders based on the user's speech, important appointments and tasks can be managed without being forgotten.

[0053] The speech recognition unit can provide appropriate exercise advice based on the user's speech. For example, if a user says, "Tell me today's exercise menu," the speech recognition unit can convert that into text and suggest an appropriate exercise menu. Also, if a user says, "Tell me how to stretch," the speech recognition unit can analyze that and explain how to stretch. Furthermore, if a user says, "Tell me some running tips," the speech recognition unit can analyze that and provide running tips. In this way, by providing exercise advice based on the user's speech, it can support health management.

[0054] The speech recognition unit can provide appropriate cooking recipes based on the user's speech. For example, if a user says, "Tell me a simple dinner recipe," the speech recognition unit can convert that into text and suggest a simple dinner recipe. Similarly, if a user says, "Tell me a healthy breakfast recipe," the speech recognition unit can analyze that and provide a healthy breakfast recipe. Furthermore, if a user says, "Tell me a dessert recipe," the speech recognition unit can analyze that and provide a dessert recipe. In this way, by providing cooking recipes based on the user's speech, it can enrich their eating habits.

[0055] The speech recognition unit can provide appropriate learning advice based on the user's speech. For example, if a user says, "Tell me how to study English," the speech recognition unit can convert that into text and suggest ways to study English. Similarly, if a user says, "Tell me some tips for solving math problems," the speech recognition unit can analyze that and provide tips for solving math problems. Furthermore, if a user says, "Tell me how to study history," the speech recognition unit can analyze that and provide methods for studying history. By providing learning advice based on the user's speech, learning efficiency can be improved.

[0056] The speech recognition unit can suggest appropriate travel plans based on the user's speech. For example, if a user says, "Tell me some recommended travel destinations for my next vacation," the speech recognition unit can convert that into text and suggest recommended destinations. Similarly, if a user says, "Tell me some nearby tourist spots I can visit on the weekend," the speech recognition unit can analyze that and suggest nearby tourist spots. Furthermore, if a user says, "Tell me some recommended places for a family trip," the speech recognition unit can analyze that and suggest places suitable for a family trip. In this way, by suggesting travel plans based on the user's speech, the system can support travel planning.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The speech recognition unit accurately converts the user's speech into text. For example, if the user says, "What's the weather like today?", the content will be displayed as text. The speech recognition unit uses AI to analyze the content of the speech and perform accurate text conversion. Step 2: The auto-completion unit automatically completes the text generated by the speech recognition unit, taking grammar and context into consideration. For example, if the user enters "What are my plans for tomorrow?", the auto-completion unit will complete it to "What are your plans for tomorrow?". The auto-completion unit uses AI to analyze grammar and context and perform appropriate completion. Step 3: The translation unit translates the text completed by the auto-completion unit into multiple languages. For example, if the user enters "こんにちは" (konnichiwa), the translation unit translates it as "Hello". The translation unit uses AI to translate text into other languages.

[0059] (Example of form 2) The AI ​​assistant text input support tool using speech recognition according to an embodiment of the present invention is a system that converts user speech into text with high accuracy and provides an automatic completion function that takes grammar and context into consideration. This system also features support for multiple languages ​​and a translation function, as well as a fashion item styling advice function. First, when a user speaks, the speech recognition unit converts the speech into text with high accuracy. At this time, the speech recognition unit uses AI to analyze the content of the speech and perform accurate text conversion. For example, if a user says, "What's the weather like today?", the content will be displayed as text. Next, an automatic completion function that takes grammar and context into consideration works on the converted text. The automatic completion unit uses AI to analyze grammar and context and perform appropriate completion. For example, if a user inputs, "What are my plans for tomorrow?", the automatic completion unit will complete it to, "What are your plans for tomorrow?". Furthermore, it has support for multiple languages ​​and a translation function. The translation unit uses AI to translate text into other languages. For example, if a user inputs, "Hello", the translation unit will translate it to "Hello". It also has a fashion item styling advice function. The styling advice section uses AI to suggest appropriate fashion items based on the user's input. For example, if the user inputs "Tell me what to wear today," the styling advice section will suggest "A white shirt and black pants would be good." Thus, the present invention is an AI assistant that uses speech recognition to support text input, which has a function to convert user speech into text with high accuracy, an automatic completion function that takes grammar and context into consideration, support and translation functions for multiple languages, and a function to provide styling advice for fashion items. As a result, the AI ​​assistant that uses speech recognition to support text input can convert user speech into text with high accuracy, and is capable of automatic completion that takes grammar and context into consideration, as well as translation into multiple languages.

[0060] The AI ​​assistant text input support tool using speech recognition according to this embodiment comprises a speech recognition unit, an auto-completion unit, and a translation unit. The speech recognition unit converts the user's utterance into text with high accuracy. For example, if the user utters "What's the weather like today?", the speech recognition unit displays the content as text. The speech recognition unit uses AI to analyze the content of the utterance and perform accurate text conversion. For example, the speech recognition unit converts the utterance into text using speech recognition technology. The speech recognition unit converts the utterance into text using speech recognition technology. The speech recognition unit converts the utterance into text using speech recognition technology. The auto-completion unit performs automatic completion of the text generated by the speech recognition unit, taking grammar and context into consideration. For example, if the user inputs "What are my plans for tomorrow?", the auto-completion unit completes it with "What are your plans for tomorrow?". The auto-completion unit uses AI to analyze grammar and context and perform appropriate completion. For example, the auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The automatic completion unit analyzes grammar using grammar analysis technology and context analysis technology. The automatic completion unit analyzes grammar using grammar analysis technology and context analysis technology. The translation unit translates the text completed by the automatic completion unit into multiple languages. For example, if the user inputs "こんにちは" (konnichiwa), the translation unit translates it to "Hello". The translation unit uses AI to translate the text into other languages. For example, the translation unit uses translation technology to translate the text into other languages. The translation unit uses translation technology to translate the text into other languages. The translation unit uses translation technology to translate the text into other languages. As a result, the speech recognition-based text input support tool AI assistant according to this embodiment can convert the user's utterance into text with high accuracy, and enables automatic completion that takes grammar and context into consideration, as well as translation into multiple languages.

[0061] The speech recognition unit accurately converts user speech into text. Specifically, when a user says, "What's the weather like today?", the speech recognition unit displays the content as text. The speech recognition unit uses AI to analyze the content of the speech and perform accurate text conversion. For example, the speech recognition unit converts speech into text using speech recognition technology. The speech recognition unit converts speech into text using speech recognition technology. The speech recognition unit converts speech into text using speech recognition technology. The speech recognition unit utilizes the latest deep learning technology to analyze speech data. Specifically, it converts the speech signal from the time domain to the frequency domain and extracts features such as Mel-frequency cepstrum coefficients (MFCCs). This represents the features of the speech as numerical data, which is then input into a neural network. The neural network is pre-trained on a large amount of speech data, and uses recurrent neural networks (RNNs) and transformer models to improve the accuracy of phoneme and word recognition. As a result, the speech recognition unit is less affected by noise and accent, achieving highly accurate text conversion. Furthermore, the speech recognition unit can learn the user's speech patterns and habits, and perform individual customizations. For example, it can learn phrases and technical terms frequently used by a particular user to improve recognition accuracy. In addition, the speech recognition unit utilizes high-speed hardware and cloud computing to perform real-time processing. This allows it to instantly display what the user says as text, providing a smooth user experience.

[0062] The auto-completion unit performs automatic completion of text generated by the speech recognition unit, taking grammar and context into consideration. Specifically, if a user inputs "What are my plans for tomorrow?", the auto-completion unit will complete it with "What are your plans for tomorrow?". The auto-completion unit uses AI to analyze grammar and context to perform appropriate completion. For example, the auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The auto-completion unit analyzes grammar using grammar analysis technology and analyzes context using context analysis technology. The auto-completion unit utilizes natural language processing (NLP) technology to analyze the grammatical structure of the input text. Specifically, it performs morphological analysis to identify the part of speech and role of words. Next, it uses dependency structure analysis to clarify the relationships between words in the sentence. This enables grammatically correct completion. Furthermore, the auto-completion unit uses context analysis technology to understand the meaning and intent of the input text. For example, if a user types "What are my plans for tomorrow?", the system will determine from the context that "What are your plans?" is an appropriate completion. Contextual analysis uses large-scale language models such as LLMs to deeply understand the meaning of the context. This allows the auto-completion unit to provide natural completions that align with the user's intent. Furthermore, the auto-completion unit can learn the user's input history and individual usage patterns to perform personalized customization. For example, it can learn frequently used phrases and expressions by specific users to improve the accuracy of completions. In addition, the auto-completion unit utilizes high-speed hardware and cloud computing to perform real-time completions. This allows for instant completion of text entered by the user, providing a smooth user experience.

[0063] The translation unit translates text completed by the auto-completion unit into multiple languages. Specifically, if a user enters "こんにちは" (konnichiwa), the translation unit translates it as "Hello". The translation unit uses AI to translate text into other languages. For example, the translation unit uses translation technology to translate text into other languages. The translation unit uses translation technology to translate text into other languages. The translation unit uses translation technology to translate text into other languages. The translation unit utilizes neural machine translation (NMT) technology to translate text with high accuracy. Specifically, it uses an encoder-decoder model to first convert the input text into an intermediate representation, and then convert it into the target language. The encoder understands the meaning of the input text and generates an intermediate representation. The decoder generates text in the target language based on that intermediate representation. This process enables accurate translation while preserving context and meaning. Furthermore, the translation unit is pre-trained on a large amount of multilingual data and can understand nuances and grammatical differences between different languages. For example, it can handle not only Japanese to English translation, but also multiple languages ​​such as French and Spanish. Furthermore, the translation unit can learn from the user's input history and individual usage patterns, allowing for personalized customization. For instance, it can learn specialized terminology and phrases frequently used by specific users to improve translation accuracy. In addition, the translation unit utilizes high-speed hardware and cloud computing to perform real-time translations. This enables instant translation of user-input text, providing a smooth user experience.

[0064] The styling advice unit suggests fashion items based on the user's input. For example, if a user inputs "Tell me what to wear today," the styling advice unit will suggest "A white shirt and black pants would be good." The styling advice unit uses AI to suggest appropriate fashion items based on the user's input. For example, the styling advice unit refers to a database of fashion items and selects appropriate items based on the user's input. The styling advice unit refers to a database of fashion items and selects appropriate items based on the user's input. The styling advice unit refers to a database of fashion items and selects appropriate items based on the user's input. This allows the system to suggest appropriate fashion items based on the user's input.

[0065] The speech recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated emotions. For example, if the user is nervous, the speech recognition unit can increase the sensitivity of speech recognition to accurately recognize even the subtle details of speech. If the user is relaxed, the speech recognition unit can return the sensitivity of speech recognition to normal, allowing for natural speech recognition. If the user is in a hurry, the speech recognition unit can increase the speed of speech recognition to perform text conversion quickly. This improves recognition accuracy by adjusting the accuracy of speech recognition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0066] The speech recognition unit can analyze the user's speaking speed and tone and select the optimal speech recognition algorithm. For example, if the user speaks quickly, the speech recognition unit can switch to high-speed processing. If the user speaks slowly, the speech recognition unit can switch to high-precision processing. If the user's tone is low, the speech recognition unit can switch to a speech recognition algorithm that corresponds to the low-frequency range. This improves recognition accuracy by selecting the optimal speech recognition algorithm according to the user's speaking speed and tone. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's speech data into a generating AI and have the generating AI select the optimal speech recognition algorithm.

[0067] The speech recognition unit can improve recognition accuracy by filtering out background noise during speech recognition. For example, if a user is speaking in a cafe, the speech recognition unit can filter out background noise and recognize only the speech. If a user is speaking in a car, the speech recognition unit can filter out engine noise and recognize only the speech. If a user is speaking in a windy location, the speech recognition unit can filter out wind noise and recognize only the speech. This improves recognition accuracy by filtering out background noise. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input background sound data into a generating AI and have the generating AI perform the filtering process.

[0068] The speech recognition unit can estimate the user's emotions and adjust the order in which the speech recognition results are displayed based on the estimated emotions. For example, if the user is nervous, the speech recognition unit can display important information first. If the user is relaxed, the speech recognition unit can display information in a natural order. If the user is in a hurry, the speech recognition unit can display the main points first. By adjusting the order in which the speech recognition results are displayed according to the user's emotions, it becomes possible to provide the user with the most optimal information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0069] The speech recognition unit can recognize regionally specific pronunciations and dialects by taking into account the user's geographical location information during speech recognition. For example, if the user is in the Kansai region, the speech recognition unit can recognize the Kansai dialect. If the user is in the Tohoku region, the speech recognition unit can recognize the Tohoku dialect. If the user is overseas, the speech recognition unit can recognize the dialect and accent of that region. This improves recognition accuracy by recognizing regionally specific pronunciations and dialects. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's geographical location data into a generating AI and have the generating AI perform the recognition of regionally specific pronunciations and dialects.

[0070] The speech recognition unit can improve recognition accuracy by referring to the user's past speech history during speech recognition. For example, the speech recognition unit can prioritize the recognition of words and phrases that the user has frequently used in the past. The speech recognition unit can learn the user's past speech patterns and improve recognition accuracy. If the user frequently uses certain technical terms, the speech recognition unit can prioritize the recognition of those terms. This improves recognition accuracy by referring to past speech history. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's past speech data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0071] The auto-completion unit can estimate the user's emotions and adjust the way it expresses the completion based on the estimated emotions. For example, if the user is nervous, the auto-completion unit can provide simple and easy-to-understand expressions. If the user is relaxed, it can provide detailed expressions. If the user is in a hurry, it can provide short and to-the-point expressions. This allows for more appropriate completion by adjusting the way the completion is expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or not using AI. For example, the auto-completion unit can input user input data into a generative AI and have the generative AI perform emotion estimation.

[0072] The auto-completion unit can perform optimal completion by referring to the user's past input history during auto-completion. For example, the auto-completion unit can prioritize completing phrases that the user has frequently used in the past. The auto-completion unit can learn the user's past input patterns and perform optimal completion. If the user frequently uses certain technical terms, the auto-completion unit can prioritize completing those terms. This enables optimal completion by referring to past input history. Some or all of the above processes in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input the user's past input data into a generating AI and have the generating AI perform optimal completion.

[0073] The auto-completion unit can customize the content it completes based on the user's area of ​​expertise and interests. For example, if the user works in the medical field, the auto-completion unit can prioritize completing medical terms. If the user works in the technical field, the auto-completion unit can prioritize completing technical terms. If the user enjoys cooking as a hobby, the auto-completion unit can prioritize completing cooking terms. This allows for more appropriate completion by customizing the content based on the user's area of ​​expertise and interests. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input data about the user's area of ​​expertise and interests into a generating AI and have the generating AI perform the customization of the completion content.

[0074] The auto-completion unit can estimate the user's emotions and adjust the length of the completion based on the estimated emotions. For example, if the user is nervous, the auto-completion unit can provide short and concise completion. If the user is relaxed, the auto-completion unit can provide detailed completion. If the user is in a hurry, the auto-completion unit can provide short and to-the-point completion. By adjusting the length of the completion according to the user's emotions, more appropriate completion becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or not using AI. For example, the auto-completion unit can input user input data into a generative AI and have the generative AI perform emotion estimation.

[0075] The auto-completion unit can adjust the timing of completion based on the user's input speed. For example, if the user is typing quickly, the auto-completion unit will complete the text quickly. If the user is typing slowly, the auto-completion unit can perform detailed completion. If the user is typing intermittently, the auto-completion unit can complete the text at the appropriate time. By adjusting the timing of completion based on input speed, more appropriate completion becomes possible. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input user input speed data into a generating AI and have the generating AI adjust the timing of completion.

[0076] The auto-completion unit can provide relevant information based on the user's input during auto-completion. For example, if the user inputs "What's the weather like tomorrow?", the auto-completion unit can provide weather forecast information. If the user inputs "When is the next meeting?", the auto-completion unit can provide calendar information. If the user inputs "What's the news today?", the auto-completion unit can provide the latest news information. In this way, by providing relevant information based on the input, the user can obtain useful information. Some or all of the above processing in the auto-completion unit may be performed using AI, for example, or without AI. For example, the auto-completion unit can input the user's input data into a generating AI and have the generating AI perform the task of providing relevant information.

[0077] The translation unit can estimate the user's emotions and adjust the translation's expression based on the estimated emotions. For example, if the user is nervous, the translation unit will translate in a simple and easy-to-understand manner. If the user is relaxed, the translation unit can translate in detail. If the user is in a hurry, the translation unit can translate in a short and to-the-point manner. By adjusting the translation's expression according to the user's emotions, a more appropriate translation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI, or not using AI. For example, the translation unit can input user input data into a generative AI and have the generative AI perform emotion estimation.

[0078] The translation unit can perform optimal translations by referring to the user's past translation history. For example, the translation unit can prioritize translating phrases that the user has frequently used in the past. The translation unit can learn the user's past translation patterns and perform optimal translations. If the user frequently uses certain technical terms, the translation unit can prioritize translating those terms. This enables optimal translations by referring to past translation history. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the user's past translation data into a generating AI and have the generating AI perform the optimal translation.

[0079] The translation unit can customize the translation content based on the user's area of ​​expertise and interests. For example, if the user works in the medical field, the translation unit will prioritize translating medical terminology. If the user works in the technical field, the translation unit can prioritize translating technical terminology. If the user enjoys cooking as a hobby, the translation unit can prioritize translating cooking terminology. This allows for more appropriate translations by customizing the translation content based on the user's area of ​​expertise and interests. Some or all of the above processing in the translation unit may be performed using AI, for example, or not. For example, the translation unit can input data on the user's area of ​​expertise and interests into a generating AI and have the generating AI perform the customization of the translation content.

[0080] The translation unit can estimate the user's emotions and determine translation priorities based on the estimated emotions. For example, if the user is nervous, the translation unit will translate important information first. If the user is relaxed, the translation unit can translate information in a natural order. If the user is in a hurry, the translation unit can translate the main points first. This allows for the prioritization of important information by determining translation priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI or not using AI. For example, the translation unit can input user input data into a generative AI and have the generative AI perform emotion estimation.

[0081] The translation unit can translate region-specific expressions by considering the user's geographical location during translation. For example, if the user is in the Kansai region, the translation unit can translate in the Kansai dialect. If the user is in the Tohoku region, the translation unit can translate in the Tohoku dialect. If the user is overseas, the translation unit can translate in the local dialect and accent. This allows for appropriate translation of region-specific expressions by considering geographical location. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the user's geographical location data into a generating AI and have the generating AI perform the translation of region-specific expressions.

[0082] The translation unit can provide relevant cultural background information based on the user's input during translation. For example, if the user inputs "hello," the translation unit can provide the cultural background of the greeting in that language. If the user inputs "thank you," the translation unit can provide the cultural background of the expression of gratitude in that language. If the user inputs "goodbye," the translation unit can provide the cultural background of the farewell greeting in that language. By providing relevant cultural background information based on the input, the user can obtain useful information. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the user's input data into a generating AI and have the generating AI perform the provision of cultural background information.

[0083] The styling advice unit can estimate the user's emotions and adjust the way styling advice is expressed based on the estimated emotions. For example, if the user is nervous, the styling advice unit can provide advice using simple and easy-to-understand language. If the user is relaxed, the styling advice unit can provide advice using detailed language. If the user is in a hurry, the styling advice unit can provide advice using short and to-the-point language. By adjusting the way styling advice is expressed according to the user's emotions, more appropriate advice can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the styling advice unit may be performed using AI, or not using AI. For example, the styling advice unit can input user input data into a generative AI and have the generative AI perform emotion estimation.

[0084] The styling advice unit can provide optimal advice by referring to the user's past fashion history when giving styling advice. For example, the styling advice unit can provide advice based on items the user has liked to wear in the past. The styling advice unit can provide advice considering seasonal trends based on the user's past fashion history. The styling advice unit can provide advice suitable for similar events based on items the user wore at a specific event. This makes it possible to provide optimal advice by referring to past fashion history. Some or all of the above processes in the styling advice unit may be performed using AI, for example, or without AI. For example, the styling advice unit can input the user's past fashion data into a generating AI and have the generating AI execute the optimal advice.

[0085] The styling advice unit can customize the advice given based on the user's body type and preferences. For example, the styling advice unit can suggest items that fit the user's body type well. The styling advice unit can provide color and design options based on the user's preferences. The styling advice unit can suggest accessory coordination according to the user's body type and preferences. By customizing the advice based on body type and preferences, more appropriate advice can be provided. Some or all of the above processes in the styling advice unit may be performed using AI, for example, or without AI. For example, the styling advice unit can input data about the user's body type and preferences into a generating AI and have the generating AI perform the customization of the advice.

[0086] The styling advice unit can estimate the user's emotions and determine the priority of styling advice based on the estimated emotions. For example, if the user is nervous, the styling advice unit can provide important advice first. If the user is relaxed, the styling advice unit can provide information in a natural order. If the user is in a hurry, the styling advice unit can provide the main points first. In this way, by determining the priority of styling advice according to the user's emotions, important advice can be provided preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the styling advice unit may be performed using AI, for example, or not using AI. For example, the styling advice unit can input user input data into a generative AI and have the generative AI perform emotion estimation.

[0087] The styling advice unit can suggest region-specific fashion by considering the user's geographical location when providing styling advice. For example, if the user is in an urban area, the styling advice unit can suggest fashion that reflects urban trends. If the user is in a resort area, the styling advice unit can suggest casual fashion suitable for a resort area. If the user is in a cold region, the styling advice unit can suggest cold-weather gear suitable for cold regions. In this way, by considering geographical location information, region-specific fashion can be appropriately suggested. Some or all of the above processing in the styling advice unit may be performed using AI, for example, or without AI. For example, the styling advice unit can input the user's geographical location data into a generating AI and have the generating AI perform region-specific fashion suggestions.

[0088] The styling advice unit can analyze a user's social media activity and suggest relevant fashion items when providing styling advice. For example, the styling advice unit can suggest similar fashion items based on posts that have received many "likes" on social media. The styling advice unit can suggest relevant items by referencing the styles of influencers that the user follows. The styling advice unit can suggest fashion items related to events that the user plans to attend. In this way, by analyzing social media activity, it can appropriately suggest relevant fashion items. Some or all of the above processes in the styling advice unit may be performed using AI, for example, or not using AI. For example, the styling advice unit can input the user's social media data into a generating AI and have the generating AI suggest relevant fashion items.

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

[0090] The speech recognition unit can automatically search for and provide relevant information based on the user's speech. For example, if a user says, "What's the news today?", the speech recognition unit can convert that into text and search for and display the latest relevant news articles. Similarly, if a user says, "Tell me about nearby restaurants," the speech recognition unit can analyze that and provide information about nearby restaurants. Furthermore, if a user says, "What time is the next train?", the speech recognition unit can analyze that and display the next train schedule. This improves convenience by providing relevant information based on the user's speech.

[0091] The speech recognition unit can set appropriate reminders based on the user's speech. For example, if a user says, "Remind me of tomorrow's meeting," the speech recognition unit converts the content into text and sets a reminder on the calendar. Also, if a user says, "Tell me when to take my medicine," the speech recognition unit analyzes the content and sets a reminder at the specified time. Furthermore, if a user says, "Remind me of the next payment deadline," the speech recognition unit analyzes the content and sets a reminder for the payment deadline. In this way, by setting reminders based on the user's speech, important appointments and tasks can be managed without being forgotten.

[0092] The speech recognition unit can estimate the user's emotions and recommend appropriate music based on the estimated emotions. For example, if the user is stressed, it can recommend relaxing music. If the user is in a cheerful mood, it can recommend upbeat music. If the user is sad, it can recommend soothing music. In this way, by recommending appropriate music according to the user's emotions, the user's mood can be improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0093] The speech recognition unit can provide appropriate exercise advice based on the user's speech. For example, if a user says, "Tell me today's exercise menu," the speech recognition unit can convert that into text and suggest an appropriate exercise menu. Also, if a user says, "Tell me how to stretch," the speech recognition unit can analyze that and explain how to stretch. Furthermore, if a user says, "Tell me some running tips," the speech recognition unit can analyze that and provide running tips. In this way, by providing exercise advice based on the user's speech, it can support health management.

[0094] The speech recognition unit can provide appropriate cooking recipes based on the user's speech. For example, if a user says, "Tell me a simple dinner recipe," the speech recognition unit can convert that into text and suggest a simple dinner recipe. Similarly, if a user says, "Tell me a healthy breakfast recipe," the speech recognition unit can analyze that and provide a healthy breakfast recipe. Furthermore, if a user says, "Tell me a dessert recipe," the speech recognition unit can analyze that and provide a dessert recipe. In this way, by providing cooking recipes based on the user's speech, it can enrich their eating habits.

[0095] The speech recognition unit can estimate the user's emotions and, based on the estimated emotions, suggest appropriate relaxation methods. For example, if the user is stressed, it can suggest deep breathing or meditation. If the user is tired, it can suggest light stretching or massage. If the user is anxious, it can suggest relaxing aromatherapy. In this way, by suggesting appropriate relaxation methods according to the user's emotions, it can support the user's mental and physical health. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0096] The speech recognition unit can provide appropriate learning advice based on the user's speech. For example, if a user says, "Tell me how to study English," the speech recognition unit can convert that into text and suggest ways to study English. Similarly, if a user says, "Tell me some tips for solving math problems," the speech recognition unit can analyze that and provide tips for solving math problems. Furthermore, if a user says, "Tell me how to study history," the speech recognition unit can analyze that and provide methods for studying history. By providing learning advice based on the user's speech, learning efficiency can be improved.

[0097] The speech recognition unit can estimate the user's emotions and provide appropriate mental health support based on the estimated emotions. For example, if the user is feeling stressed, it can suggest ways to manage stress. If the user is feeling anxious, it can provide advice to alleviate anxiety. If the user is feeling down, it can suggest ways to improve their mood. In this way, by providing appropriate mental health support according to the user's emotions, the system can support the user's mental well-being. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0098] The speech recognition unit can suggest appropriate travel plans based on the user's speech. For example, if a user says, "Tell me some recommended travel destinations for my next vacation," the speech recognition unit can convert that into text and suggest recommended destinations. Similarly, if a user says, "Tell me some nearby tourist spots I can visit on the weekend," the speech recognition unit can analyze that and suggest nearby tourist spots. Furthermore, if a user says, "Tell me some recommended places for a family trip," the speech recognition unit can analyze that and suggest places suitable for a family trip. In this way, by suggesting travel plans based on the user's speech, the system can support travel planning.

[0099] The speech recognition unit can estimate the user's emotions and, based on the estimated emotions, suggest an appropriate reading list. For example, if the user wants to relax, it can recommend relaxing books. If the user wants to feel energized, it can recommend energizing books. If the user wants to deepen their knowledge, it can recommend academic books. This improves the reading experience by suggesting an appropriate reading list according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0100] The following briefly describes the processing flow for example form 2.

[0101] Step 1: The speech recognition unit accurately converts the user's speech into text. For example, if the user says, "What's the weather like today?", the content will be displayed as text. The speech recognition unit uses AI to analyze the content of the speech and perform accurate text conversion. Step 2: The auto-completion unit automatically completes the text generated by the speech recognition unit, taking grammar and context into consideration. For example, if the user enters "What are my plans for tomorrow?", the auto-completion unit will complete it to "What are your plans for tomorrow?". The auto-completion unit uses AI to analyze grammar and context and perform appropriate completion. Step 3: The translation unit translates the text completed by the auto-completion unit into multiple languages. For example, if the user enters "こんにちは" (konnichiwa), the translation unit translates it as "Hello". The translation unit uses AI to translate text into other languages.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

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

[0105] For example, the speech recognition unit detects the user's speech using the microphone 38B of the smart device 14, the control unit 46A analyzes the speech data, and the specific processing unit 290 of the data processing device 12 performs high-precision text conversion. The automatic completion unit analyzes grammar and context using the specific processing unit 290 of the data processing device 12 and performs appropriate completion. The translation unit translates text into another language using the specific processing unit 290 of the data processing device 12. The styling advice unit suggests appropriate fashion items based on the user's input using the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0106] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0107] As shown in Figure 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.

[0108] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0112] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0113] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0114] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0115] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0116] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0118] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0120] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0121] For example, the speech recognition unit detects the user's speech using the microphone 238 of the smart glasses 214, the control unit 46A analyzes the speech data, and the specific processing unit 290 of the data processing device 12 performs high-precision text conversion. The automatic completion unit analyzes grammar and context using the specific processing unit 290 of the data processing device 12 and performs appropriate completion. The translation unit translates text into another language using the specific processing unit 290 of the data processing device 12. The styling advice unit suggests appropriate fashion items based on the user's input using the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0122] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0123] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0125] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0126] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0128] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0129] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0130] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0131] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0132] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0136] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0137] For example, the speech recognition unit detects the user's speech using the microphone 238 of the headset terminal 314, the control unit 46A analyzes the speech data, and the specific processing unit 290 of the data processing device 12 performs high-precision text conversion. The automatic completion unit analyzes grammar and context using the specific processing unit 290 of the data processing device 12 and performs appropriate completion. The translation unit translates text into another language using the specific processing unit 290 of the data processing device 12. The styling advice unit suggests appropriate fashion items based on the user's input using the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0138] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0139] As shown in Figure 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.

[0140] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0142] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0144] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0145] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0146] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] For example, the speech recognition unit detects the user's speech using the microphone 238 of the robot 414, the control unit 46A analyzes the speech data, and the specific processing unit 290 of the data processing unit 12 performs high-precision text conversion. The automatic completion unit analyzes grammar and context using the specific processing unit 290 of the data processing unit 12 and performs appropriate completion. The translation unit translates text into another language using the specific processing unit 290 of the data processing unit 12. The styling advice unit suggests appropriate fashion items based on the user's input using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0155] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0157] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0158] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0159] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0163] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0164] 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.

[0165] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0166] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0167] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0168] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0170] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0171] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0172] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0173] (Note 1) A speech recognition unit that converts user speech into text, An automatic completion unit that performs grammatical and context-based automatic completion on the text generated by the speech recognition unit, A translation unit that translates the text completed by the aforementioned auto-completion unit into multiple languages, Equipped with A system characterized by the following features. (Note 2) It features a styling advice section that suggests fashion items based on user input. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned speech recognition unit, The system analyzes the user's speaking speed and tone to select a speech recognition algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned speech recognition unit, Filtering out background noise during speech recognition improves recognition accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the order in which the speech recognition results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned speech recognition unit, During speech recognition, the system takes into account the user's geographical location to recognize regional pronunciations and dialects. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned speech recognition unit, During speech recognition, the system improves recognition accuracy by referencing the user's past speech history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned automatic completion unit, It estimates the user's emotions and adjusts the way the supplementary expressions are presented based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned automatic completion unit, When auto-completion is performed, the system refers to the user's past input history to complete the text. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned automatic completion unit, When auto-completion is performed, the content of the auto-completion is customized based on the user's area of ​​expertise and interests. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned automatic completion unit, It estimates the user's emotions and adjusts the length of the interpolation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned automatic completion unit, When auto-completion is enabled, the timing of completion is adjusted based on the user's typing speed. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned automatic completion unit, When auto-completion is performed, relevant information is provided based on the user's input. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned translation department, It estimates the user's emotions and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned translation department, During translation, the system references the user's past translation history to produce the most optimal translation. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned translation department, During translation, the translation content is customized based on the user's area of ​​expertise and interests. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned translation department, It estimates the user's emotions and determines translation priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned translation department, During translation, the system takes the user's geographical location into account and translates region-specific expressions accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned translation department, During translation, relevant cultural background information is provided based on the user's input. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned styling advice unit is The system estimates the user's emotions and adjusts the way styling advice is presented based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 22) The aforementioned styling advice unit is When providing styling advice, the system refers to the user's past fashion history to offer the most suitable advice. The system described in Appendix 2, characterized by the features described herein. (Note 23) The aforementioned styling advice unit is When providing styling advice, the advice is customized based on the user's body type and preferences. The system described in Appendix 2, characterized by the features described herein. (Note 24) The aforementioned styling advice unit is It estimates the user's emotions and prioritizes styling advice based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 25) The aforementioned styling advice unit is When providing styling advice, we take the user's geographical location into consideration and suggest fashion trends specific to their region. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned styling advice unit is When providing styling advice, we analyze the user's social media activity and suggest relevant fashion items. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A speech recognition unit that converts user speech into text, An automatic completion unit that performs grammatical and context-based automatic completion on the text generated by the speech recognition unit, A translation unit that translates the text completed by the aforementioned auto-completion unit into multiple languages, Equipped with A system characterized by the following features.

2. The system includes a styling advice unit that suggests fashion items based on the user's input. The system according to feature 1.

3. The aforementioned speech recognition unit, The system estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated emotions of the user. The system according to feature 1.

4. The aforementioned speech recognition unit, The user's speaking speed and tone are analyzed, and a speech recognition algorithm is selected. The system according to feature 1.

5. The aforementioned speech recognition unit, During speech recognition, the user's background noise is filtered to improve recognition accuracy. The system according to feature 1.

6. The aforementioned speech recognition unit, The system estimates the user's emotions and adjusts the order in which the speech recognition results are displayed based on the estimated emotions of the user. The system according to feature 1.

7. The aforementioned speech recognition unit, During speech recognition, the system recognizes regional pronunciations and dialects by taking into account the user's geographical location. The system according to feature 1.

8. The aforementioned speech recognition unit, During speech recognition, the system improves recognition accuracy by referring to the user's past speech history. The system according to feature 1.

9. The aforementioned automatic completion unit, The system estimates the user's emotions and adjusts the method of expression for the supplement based on the estimated user's emotions. The system according to feature 1.

Images