system

Abstract

The system according to the embodiment aims to convert speech into text and use the text to operate a device. [Solution] A system according to an embodiment includes a conversion unit, a storage unit, a reception unit, and an operation unit. The conversion unit converts speech into text. The storage unit stores the text converted by the conversion unit. The reception unit receives a voice command. The operation unit operates a device based on the voice command received by the reception unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately convert speech into text and use that text to operate devices, and there is room for improvement.

[0005] The system according to the embodiment aims to convert speech into text and use the text to operate a device. [Means for solving the problem]

[0006] A system according to an embodiment includes a conversion unit, a storage unit, a reception unit, and an operation unit. The conversion unit converts speech into text. The storage unit stores the text converted by the conversion unit. The reception unit receives a voice command. The operation unit operates a device based on the voice command received by the reception unit. [Effects of the Invention]

[0007] The system according to the embodiment can convert speech into text and use the text to operate a device. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A speech-to-text system according to an embodiment of the present invention is a system that converts speech into text, stores the text, accepts voice commands, and operates a device. This speech-to-text system converts speech into text and provides the text as a memo to be saved. For example, when a user creates a memo by voice, the system converts speech into text and provides the text as a memo to be saved. Next, when the user sends a text message by voice, the system converts speech into text to support message sending. For example, a user can send a message by voice while driving, enabling hands-free communication. Furthermore, the system can accept voice commands to operate a device. For example, the system can play music or turn on lights by voice. This allows the user to create voice memos, send text messages by voice input, and operate a device via voice control. This allows the user to create memos by voice, send text messages by voice, and operate a device by voice commands.

[0029] The speech-to-text system according to the embodiment includes a conversion unit, a storage unit, a reception unit, and an operation unit. The conversion unit converts speech into text. For example, the conversion unit analyzes speech data and converts it into text data using speech recognition technology. For example, the conversion unit analyzes speech data with high accuracy and converts it into text data using natural language processing technology. The conversion unit can also convert speech data into text data using a generation AI. The generation AI converts speech data into text data using an AI model that receives speech data as input and outputs text data. The storage unit stores the text converted by the conversion unit. For example, the storage unit stores the text data in a database. The storage unit can also store the text data in cloud storage. The storage unit can also store the text data in local storage. The reception unit receives a voice command. For example, the reception unit analyzes the voice command and performs appropriate processing. For example, the reception unit analyzes the voice command and instructs a device operation. The reception unit can also analyze the voice command and instruct the sending of a text message. The operation unit operates the device based on the voice command accepted by the acceptance unit. The operation unit controls the device based on the voice command, for example. For example, the operation unit plays music based on the voice command. The operation unit can also turn on a light based on the voice command. In this way, the speech-to-text system according to the embodiment can convert speech into text, store the text, accept voice commands, and operate the device.

[0030] The speech-to-text system includes a preprocessing unit that preprocesses the speech data. The preprocessing unit preprocesses the speech data. The preprocessing unit, for example, performs noise removal. For example, the preprocessing unit removes background noise from the speech data. The preprocessing unit can also adjust the volume. For example, the preprocessing unit adjusts the volume of the speech data to maintain a constant volume. The preprocessing unit can also perform filtering. For example, the preprocessing unit filters to emphasize a specific frequency band of the speech data. This improves conversion accuracy by preprocessing the speech data. Some or all of the above-described processing in the preprocessing unit may be performed using, or without, a generation AI. For example, the preprocessing unit inputs speech data to the generation AI and has the generation AI perform noise removal and volume adjustment.

[0031] The speech-to-text system includes an analysis unit for improving the accuracy of speech recognition. The analysis unit performs analysis for improving the accuracy of speech recognition. The analysis unit, for example, extracts speech features. For example, the analysis unit extracts speech features from speech data to improve the accuracy of speech recognition. The analysis unit can also perform statistical analysis. For example, the analysis unit performs statistical analysis of speech data to improve the accuracy of speech recognition. The analysis unit can also apply a machine learning algorithm. For example, the analysis unit applies a machine learning algorithm to speech data to improve the accuracy of speech recognition. This improves the accuracy of speech recognition. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input speech data to a generation AI and have the generation AI perform extraction of speech features and statistical analysis.

[0032] The speech-to-text system includes a transmitting unit that transmits the converted text as a message. The transmitting unit transmits the converted text as a message. The transmitting unit, for example, transmits a text message. For example, the transmitting unit transmits the converted text as a text message. The transmitting unit can also transmit a voice message. For example, the transmitting unit transmits the converted text as a voice message. The transmitting unit can also transmit an image message. For example, the transmitting unit transmits the converted text as an image message. In this way, the converted text can be transmitted as a message. Some or all of the above-described processing in the transmitting unit may be performed using, or without using, a generation AI. For example, the transmitting unit may input the converted text to the generation AI and cause the generation AI to generate a text message or a voice message.

[0033] The conversion unit can convert speech into text. For example, the conversion unit analyzes speech data and converts it into text data using speech recognition technology. For example, the conversion unit analyzes speech data with high accuracy and converts it into text data using natural language processing technology. The conversion unit can also convert speech data into text data using a generation AI. For example, the generation AI converts speech data into text data using an AI model that inputs speech data and outputs text data. This clarifies the function of converting speech to text. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversion unit can input speech data to the generation AI and have the generation AI generate text data from the speech data.

[0034] The storage unit can store the converted text. The storage unit, for example, stores the text data in a database. For example, the storage unit stores the converted text in a database. The storage unit can also store the text data in cloud storage. For example, the storage unit stores the converted text in cloud storage. The storage unit can also store the text data in local storage. For example, the storage unit stores the converted text in local storage. This clarifies the function of storing the converted text. Some or all of the above-described processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input the converted text to the generation AI and cause the generation AI to store the text data.

[0035] The reception unit can receive a voice command. The reception unit, for example, analyzes the voice command and performs appropriate processing. For example, the reception unit analyzes the voice command and instructs the device to operate. The reception unit can also analyze the voice command and instruct the sending of a text message. This clarifies the function of receiving a voice command. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the voice command to the generation AI and have the generation AI analyze the voice command.

[0036] The operation unit can operate a device based on a voice command. The operation unit, for example, controls a device based on a voice command. For example, the operation unit plays music based on a voice command. The operation unit can also turn on a light based on a voice command. This clarifies the function of operating a device based on a voice command. Some or all of the above-described processing in the operation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the operation unit can input a voice command to a generation AI and have the generation AI execute the device operation.

[0037] The conversion unit can automatically remove background noise from the audio, improving conversion accuracy. For example, the conversion unit has a generation AI analyze the audio data and identify and remove background noise. For example, the conversion unit has a generation AI analyze the audio data and identify and remove background noise. The conversion unit can also have the generation AI perform noise filtering in real time to obtain clear audio data. For example, the conversion unit has the generation AI perform noise filtering in real time to obtain clear audio data. The conversion unit can also have the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. For example, the conversion unit has the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. This removes background noise from the audio, improving conversion accuracy. Some or all of the above-described processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input audio data to the generation AI and have the generation AI remove background noise.

[0038] The conversion unit can identify the speaker of the audio and apply a different conversion algorithm to each speaker. For example, the generation AI in the conversion unit extracts speaker characteristics from the audio data and applies an individual conversion algorithm. For example, the generation AI in the conversion unit extracts speaker characteristics from the audio data and applies an individual conversion algorithm. The conversion unit can also analyze the speaker's tone and accent and select the optimal conversion algorithm. For example, the conversion unit can analyze the speaker's tone and accent and select the optimal conversion algorithm. The conversion unit can also identify multiple speakers and apply an appropriate conversion algorithm to each speaker. For example, the conversion unit can identify multiple speakers and apply an appropriate conversion algorithm to each speaker. This allows the optimal conversion algorithm to be applied to each speaker. Some or all of the above-described processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input speaker characteristic data to the generation AI and have the generation AI apply a different conversion algorithm to each speaker.

[0039] The conversion unit can automatically detect the language of the voice and perform conversion that supports multiple languages. For example, the conversion unit has the generation AI analyze the voice data and automatically identify the language. For example, the conversion unit has the generation AI analyze the voice data and automatically identify the language. The conversion unit can also have the generation AI prepare multiple language models and select an appropriate language model to perform conversion. For example, the conversion unit can have the generation AI prepare multiple language models and select an appropriate language model to perform conversion. The conversion unit can also handle cases where the generation AI switches languages ​​in the voice data and perform conversion seamlessly. For example, the conversion unit can handle cases where the generation AI switches languages ​​in the voice data and perform conversion seamlessly. This enables voice conversion that supports multiple languages. Some or all of the above-mentioned processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input voice data to the generation AI and have the generation AI perform automatic language detection and conversion that supports multiple languages.

[0040] The conversion unit can adjust the speed of the voice to improve conversion accuracy. For example, the conversion unit has the generation AI analyze the speed of the voice data and adjust it to an appropriate speed to perform conversion. For example, the conversion unit has the generation AI analyze the speed of the voice data and adjust it to an appropriate speed to perform conversion. The conversion unit can also slow down the voice speed if the generation AI is too fast to improve conversion accuracy. For example, the conversion unit can slow down the voice speed if the generation AI is too fast to improve conversion accuracy. The conversion unit can also speed up the voice speed if the generation AI is too slow to perform conversion efficiently. For example, the conversion unit can speed up the voice speed if the generation AI is too slow to perform conversion efficiently. In this way, adjusting the voice speed improves conversion accuracy. Some or all of the above-mentioned processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input voice data to the generation AI and have the generation AI adjust the voice speed.

[0041] The storage unit can determine the storage priority based on the importance of the text when saving. For example, the storage unit has the generation AI analyze the content of the text, evaluate the importance, and determine the storage priority. For example, the storage unit has the generation AI analyze the content of the text, evaluate the importance, and determine the storage priority. The storage unit can also have the generation AI evaluate the importance by referring to the user's past saving history. For example, the storage unit has the generation AI evaluate the importance by referring to the user's past saving history. The storage unit can also have the generation AI extract keywords from the text, evaluate the importance, and determine the storage priority. For example, the storage unit has the generation AI extract keywords from the text, evaluate the importance, and determine the storage priority. This makes it possible to determine the storage priority based on the importance of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text importance data to the generation AI and have the generation AI determine the storage priority.

[0042] The storage unit can apply different storage methods depending on the category of the text when saving. For example, the generation AI analyzes the content of the text, automatically determines the category, and selects the storage method. For example, the storage unit analyzes the content of the text, automatically determines the category, and selects the storage method. The storage unit can also suggest an appropriate storage method by having the generation AI refer to the user's past saving history. For example, the storage unit can suggest an appropriate storage method by having the generation AI refer to the user's past saving history. The storage unit can also extract keywords from the text and apply a storage method depending on the category. For example, the storage unit can extract keywords from the text and apply a storage method depending on the category. This makes it possible to apply different storage methods depending on the category of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text category data to the generation AI and have the generation AI select the storage method.

[0043] The storage unit can adjust the order of saving based on the time of submission of the text when saving. For example, the storage unit analyzes the time of submission of the text by the generation AI and determines the order of saving. For example, the storage unit analyzes the time of submission of the text by the generation AI and determines the order of saving. The storage unit can also adjust the order of saving by the generation AI with reference to the user's past submission history. For example, the storage unit can adjust the order of saving by the generation AI with reference to the user's past submission history. The storage unit can also select text to be preferentially saved by the generation AI based on the time of submission of the text. For example, the storage unit selects text to be preferentially saved by the generation AI based on the time of submission of the text. This makes it possible to adjust the order of saving based on the time of submission of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text submission time data into the generation AI and cause the generation AI to adjust the order of saving.

[0044] The storage unit can automatically select a storage folder based on the relevance of the text when saving. For example, the storage unit has the generation AI analyze the content of the text and select a highly relevant folder. For example, the storage unit has the generation AI analyze the content of the text and select a highly relevant folder. The storage unit can also have the generation AI suggest an appropriate folder by referring to the user's past saving history. For example, the storage unit can have the generation AI suggest an appropriate folder by referring to the user's past saving history. The storage unit can also have the generation AI extract keywords from the text and select a storage folder based on relevance. For example, the storage unit has the generation AI extract keywords from the text and select a storage folder based on relevance. This makes it possible to automatically select a storage folder based on the relevance of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text relevance data to the generation AI and have the generation AI select a storage folder.

[0045] When receiving a voice command, the reception unit can select the optimal reception method by referring to the user's past command history. For example, the reception unit uses a generation AI to analyze the user's past voice command history and propose the optimal reception method. For example, the reception unit uses a generation AI to analyze the user's past voice command history and propose the optimal reception method. The reception unit can also prioritize receiving frequently used commands from the user's past command history. For example, the reception unit uses a generation AI to prioritize receiving frequently used commands from the user's past command history. The reception unit can also predict and suggest commands that will be used in a specific time period based on the user's past command history. For example, the reception unit uses a generation AI to predict and suggest commands that will be used in a specific time period based on the user's past command history. This allows the optimal reception method to be selected based on the user's past command history. Some or all of the above-described processing in the reception unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's past command history data into the generation AI and have the generation AI select a reception method.

[0046] The reception unit can filter voice commands based on the user's current situation when receiving them. For example, the reception unit allows the generation AI to analyze the user's current location information and prioritize receiving highly relevant voice commands. For example, the reception unit allows the generation AI to analyze the user's current location information and prioritize receiving highly relevant voice commands. The reception unit can also allow the generation AI to suggest appropriate voice commands by taking into account the user's current activity status. For example, the reception unit allows the generation AI to suggest appropriate voice commands by taking into account the user's current activity status. The reception unit can also allow the generation AI to analyze the user's current device usage status and select the optimal voice command. For example, the reception unit allows the generation AI to analyze the user's current device usage status and select the optimal voice command. This allows the voice commands to be filtered based on the user's current situation. Some or all of the above-described processing in the reception unit can be performed using, or without, the generation AI. For example, the reception unit can input the user's current situation data to the generation AI and have the generation AI perform voice command filtering.

[0047] When receiving a voice command, the reception unit can prioritize receiving highly relevant commands by taking into account the user's geographical location information. For example, the reception unit allows the generation AI to analyze the user's current location and prioritize receiving highly relevant voice commands. For example, the reception unit allows the generation AI to analyze the user's current location and prioritize receiving highly relevant voice commands. The reception unit can also allow the generation AI to suggest appropriate voice commands by referring to the user's past location information. For example, the reception unit allows the generation AI to suggest appropriate voice commands by referring to the user's past location information. The reception unit can also allow the generation AI to select an optimal voice command based on the user's current location. For example, the reception unit allows the generation AI to select an optimal voice command based on the user's current location. This allows highly relevant commands to be preferentially received based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit can input the user's geographical location information data to the generation AI and cause the generation AI to select a voice command.

[0048] When receiving a voice command, the reception unit can analyze the user's social media activity and receive a related command. For example, the reception unit can have a generation AI analyze the user's social media activity and suggest a highly relevant voice command. For example, the reception unit can have a generation AI analyze the user's social media activity and suggest a highly relevant voice command. The reception unit can also have the generation AI select an appropriate voice command by referring to the user's past social media posts. For example, the reception unit can have the generation AI select an appropriate voice command by referring to the user's past social media posts. The reception unit can also receive an optimal voice command by the generation AI based on the user's social media activity. For example, the reception unit can receive an optimal voice command by the generation AI based on the user's social media activity. This allows reception of a relevant command based on the user's social media activity. Some or all of the above-described processing in the reception unit can be performed using, or without, the generation AI. For example, the reception unit can input the user's social media activity data into the generation AI and have the generation AI select a voice command.

[0049] When operating the device, the operation unit can select an optimal operation method by referring to the user's past operation history. For example, the operation unit allows the generation AI to analyze the user's past operation history and propose an optimal operation method. For example, the operation unit allows the generation AI to analyze the user's past operation history and propose an optimal operation method. The operation unit can also allow the generation AI to prioritize frequently used operations from the user's past operation history. For example, the operation unit allows the generation AI to prioritize frequently used operations from the user's past operation history. The operation unit can also allow the generation AI to predict and propose operations to be used in a specific time period based on the user's past operation history. For example, the operation unit allows the generation AI to predict and propose operations to be used in a specific time period based on the user's past operation history. This allows the optimal operation method to be selected based on the user's past operation history. Some or all of the above-described processing in the operation unit may be performed using, or without, the generation AI. For example, the operation unit can input the user's past operation history data into the generation AI and have the generation AI select an operation method.

[0050] The operation unit can determine the priority of operations based on the user's current situation when operating the device. For example, the operation unit allows the generation AI to analyze the user's current location information and prioritize providing highly relevant operations. For example, the operation unit allows the generation AI to analyze the user's current location information and prioritize providing highly relevant operations. The operation unit can also allow the generation AI to suggest appropriate operations by taking into account the user's current activity status. For example, the operation unit allows the generation AI to suggest appropriate operations by taking into account the user's current activity status. The operation unit can also allow the generation AI to analyze the user's current device usage status and select an optimal operation. For example, the operation unit allows the generation AI to analyze the user's current device usage status and select an optimal operation. This makes it possible to determine the priority of operations based on the user's current situation. Some or all of the above-mentioned processing in the operation unit may be performed using, or without, the generation AI. For example, the operation unit can input the user's current situation data to the generation AI and have the generation AI determine the priority of operations.

[0051] When operating a device, the operation unit can select an optimal operation method by taking into account the user's geographical location information. For example, the operation unit allows the generation AI to analyze the user's current location and prioritize providing highly relevant device operations. For example, the operation unit allows the generation AI to analyze the user's current location and prioritize providing highly relevant device operations. The operation unit can also allow the generation AI to suggest appropriate device operations by referring to the user's past location information. For example, the operation unit allows the generation AI to suggest appropriate device operations by referring to the user's past location information. The operation unit can also allow the generation AI to select optimal device operations based on the user's current location. For example, the operation unit allows the generation AI to select optimal device operations based on the user's current location. This allows the optimal operation method to be selected based on the user's geographical location information. Some or all of the above-described processing in the operation unit may be performed using, or without, the generation AI. For example, the operation unit can input the user's geographical location information data to the generation AI and have the generation AI select an operation method.

[0052] The operation unit can analyze the user's social media activity and suggest operation means when operating the device. For example, the operation unit allows the generation AI to analyze the user's social media activity and suggest highly relevant device operations. For example, the operation unit allows the generation AI to analyze the user's social media activity and suggest highly relevant device operations. The operation unit can also allow the generation AI to select appropriate device operations by referring to the user's past social media posts. For example, the operation unit allows the generation AI to select appropriate device operations by referring to the user's past social media posts. The operation unit can also allow the generation AI to suggest optimal device operations based on the user's social media activity. For example, the operation unit allows the generation AI to suggest optimal device operations based on the user's social media activity. This allows the generation AI to suggest optimal operation means based on the user's social media activity. Some or all of the above-described processing in the operation unit can be performed using, or without, the generation AI. For example, the operation unit can input the user's social media activity data into the generation AI and have the generation AI execute the operation means suggestion.

[0053] The preprocessing unit can perform filtering to improve the accuracy of noise removal when preprocessing the audio data. For example, the preprocessing unit allows the generation AI to analyze the audio data and apply optimal noise filtering. For example, the preprocessing unit allows the generation AI to analyze the audio data and apply optimal noise filtering. The preprocessing unit can also allow the generation AI to perform noise filtering in real time to provide clear audio data. For example, the preprocessing unit allows the generation AI to perform noise filtering in real time to provide clear audio data. The preprocessing unit can also allow the generation AI to apply multiple noise removal algorithms and select the optimal noise removal method. For example, the preprocessing unit allows the generation AI to apply multiple noise removal algorithms and select the optimal noise removal method. This allows filtering to improve the accuracy of noise removal. Some or all of the above-described processing in the preprocessing unit can be performed using, or without, the generation AI. For example, the preprocessing unit can input audio data to the generation AI and have the generation AI perform noise filtering.

[0054] The preprocessing unit can identify the speaker of the voice and customize the preprocessing method when preprocessing the voice data. For example, the preprocessing unit allows the generation AI to extract speaker characteristics from the voice data and apply an individual preprocessing method. For example, the preprocessing unit allows the generation AI to extract speaker characteristics from the voice data and apply an individual preprocessing method. The preprocessing unit can also allow the generation AI to analyze the speaker's tone of voice and accent and select the optimal preprocessing method. For example, the preprocessing unit can allow the generation AI to analyze the speaker's tone of voice and accent and select the optimal preprocessing method. The preprocessing unit can also allow the generation AI to identify multiple speakers and apply a preprocessing method appropriate for each speaker. For example, the preprocessing unit can allow the generation AI to identify multiple speakers and apply a preprocessing method appropriate for each speaker. This allows the speaker of the voice to be identified and the preprocessing method to be customized. Some or all of the above-described processing in the preprocessing unit may be performed using, or without, the generation AI. For example, the preprocessing unit can input speaker characteristic data into the generation AI and have the generation AI customize the preprocessing method.

[0055] The preprocessing unit can automatically detect the language of the speech and adjust the preprocessing method when preprocessing the speech data. For example, the preprocessing unit causes the generation AI to analyze the speech data and automatically identify the language. For example, the preprocessing unit causes the generation AI to analyze the speech data and automatically identify the language. The preprocessing unit can also cause the generation AI to prepare multiple language models and select an appropriate language model to perform preprocessing. For example, the generation AI can prepare multiple language models and select an appropriate language model to perform preprocessing. The preprocessing unit can also handle cases where the generation AI switches languages ​​in the speech data and perform seamless preprocessing. For example, the preprocessing unit can handle cases where the generation AI switches languages ​​in the speech data and perform seamless preprocessing. This allows the language of the speech to be automatically detected and the preprocessing method to be adjusted. Some or all of the above-described processing in the preprocessing unit may be performed using, or without, the generation AI. For example, the preprocessing unit can input speech data to the generation AI and have the generation AI perform automatic language detection and adjustment of the preprocessing method.

[0056] The preprocessing unit can adjust the speed of the voice when preprocessing the voice data to improve the accuracy of the preprocessing. For example, the preprocessing unit analyzes the speed of the voice data by the generation AI, adjusts the speed to an appropriate speed, and performs preprocessing. For example, the preprocessing unit analyzes the speed of the voice data by the generation AI, adjusts the speed to an appropriate speed, and performs preprocessing. The preprocessing unit can also slow down the speed of the voice if the generation AI's voice speed is too fast to improve the accuracy of preprocessing. For example, the preprocessing unit can slow down the speed of the voice if the generation AI's voice speed is too fast to improve the accuracy of preprocessing. The preprocessing unit can also speed up the speed of the voice if the generation AI's voice speed is too slow to efficiently perform preprocessing. For example, the preprocessing unit can speed up the speed of the voice if the generation AI's voice speed is too slow to efficiently perform preprocessing. In this way, the accuracy of preprocessing can be improved by adjusting the speed of the voice. Some or all of the above-mentioned processing in the preprocessing unit may be performed using, or without, the generation AI. For example, the preprocessing unit can input voice data to the generation AI and have the generation AI adjust the speed of the voice.

[0057] The analysis unit can improve analysis accuracy by automatically removing background noise from the voice during voice recognition analysis. For example, the analysis unit has the generation AI analyze the voice data and apply optimal noise filtering. For example, the analysis unit has the generation AI analyze the voice data and apply optimal noise filtering. The analysis unit can also have the generation AI perform noise filtering in real time to provide clear voice data. For example, the analysis unit has the generation AI perform noise filtering in real time to provide clear voice data. The analysis unit can also have the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. For example, the analysis unit has the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. This improves analysis accuracy by removing background noise from the voice. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input voice data to the generation AI and have the generation AI perform noise filtering.

[0058] The analysis unit can identify the speaker of the voice and customize the analysis algorithm when analyzing the voice recognition. For example, the generation AI extracts speaker characteristics from the voice data and applies an individual analysis algorithm to the analysis unit. For example, the analysis unit extracts speaker characteristics from the voice data and applies an individual analysis algorithm to the analysis unit. The analysis unit can also analyze the tone and accent of the speaker's voice and select the optimal analysis algorithm to the analysis unit. For example, the analysis unit can analyze the tone and accent of the speaker's voice and select the optimal analysis algorithm to the analysis unit. The analysis unit can also identify multiple speakers and apply an appropriate analysis algorithm to each speaker. For example, the analysis unit can identify multiple speakers and apply an appropriate analysis algorithm to each speaker. This allows the speaker of the voice to be identified and the analysis algorithm to be customized. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input speaker characteristic data to the generation AI and have the generation AI customize the analysis algorithm.

[0059] The analysis unit can automatically detect the language of the voice during speech recognition analysis and adjust the analysis method. For example, the analysis unit has the generation AI analyze the voice data and automatically identify the language. For example, the analysis unit has the generation AI analyze the voice data and automatically identify the language. The analysis unit can also select an appropriate language model from among multiple language models prepared by the generation AI and perform analysis. For example, the analysis unit can select an appropriate language model from among multiple language models prepared by the generation AI and perform analysis. The analysis unit can also handle cases where the generation AI switches languages ​​within the voice data and perform analysis seamlessly. For example, the analysis unit can handle cases where the generation AI switches languages ​​within the voice data and perform analysis seamlessly. This allows the language of the voice to be automatically detected and the analysis method to be adjusted. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input voice data to the generation AI and have the generation AI automatically detect the language and adjust the analysis method.

[0060] The analysis unit can adjust the speed of the voice during speech recognition analysis to improve analysis accuracy. For example, the analysis unit analyzes the speed of the voice data by the generation AI and adjusts it to an appropriate speed for analysis. For example, the analysis unit analyzes the speed of the voice data by the generation AI and adjusts it to an appropriate speed for analysis. The analysis unit can also slow down the speed of the voice if the generation AI speaks too fast to improve analysis accuracy. For example, the analysis unit can slow down the speed of the voice if the generation AI speaks too fast to improve analysis accuracy. The analysis unit can also speed up the speed of the voice if the generation AI speaks too slow to efficiently analyze. For example, the analysis unit can speed up the speed of the voice if the generation AI speaks too slow to efficiently analyze. In this way, the analysis accuracy can be improved by adjusting the speed of the voice. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input voice data to the generation AI and have the generation AI adjust the speed of the voice.

[0061] When sending a message, the transmission unit can determine the transmission priority based on the importance of the message. For example, the generation AI analyzes the content of the message, evaluates the importance, and determines the transmission priority. For example, the transmission unit analyzes the content of the message, evaluates the importance, and determines the transmission priority. The transmission unit can also evaluate the importance by referring to the user's past sending history. For example, the transmission unit can evaluate the importance by referring to the user's past sending history. The transmission unit can also extract keywords from the message, evaluate the importance, and determine the transmission priority. For example, the transmission unit can extract keywords from the message, evaluate the importance, and determine the transmission priority. In this way, the transmission priority can be determined based on the importance of the message. Some or all of the above-mentioned processing in the transmission unit may be performed using, or without, the generation AI. For example, the transmission unit can input message importance data to the generation AI and have the generation AI determine the transmission priority.

[0062] When sending a message, the sending unit can apply different sending methods depending on the message category. For example, the generation AI analyzes the content of the message, automatically determines the category, and selects the sending method. For example, the generation AI analyzes the content of the message, automatically determines the category, and selects the sending method. The sending unit can also suggest an appropriate sending method by referring to the user's past sending history. For example, the sending unit can suggest an appropriate sending method by referring to the user's past sending history. The sending unit can also extract keywords from the message and apply a sending method depending on the category. For example, the sending unit can extract keywords from the message and apply a sending method depending on the category. This allows different sending methods to be applied depending on the message category. Some or all of the above-mentioned processing in the sending unit may be performed using, or without, the generation AI. For example, the sending unit can input message category data into the generation AI and have the generation AI select the sending method.

[0063] When sending messages, the sending unit can adjust the order of sending based on the time the messages were submitted. For example, the sending unit determines the order of sending by having the generation AI analyze the time the messages were submitted. For example, the sending unit determines the order of sending by having the generation AI analyze the time the messages were submitted. The sending unit can also adjust the order of sending by having the generation AI refer to the user's past submission history. For example, the sending unit can adjust the order of sending by having the generation AI refer to the user's past submission history. The sending unit can also select messages to be sent with priority based on the time the messages were submitted by the generation AI. For example, the sending unit selects messages to be sent with priority based on the time the messages were submitted by the generation AI. This allows the order of sending to be adjusted based on the time the messages were submitted. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the sending unit can input message submission time data into the generation AI and cause the generation AI to adjust the order of sending.

[0064] When sending a message, the sending unit can automatically select a means of transmission based on the relevance of the message. For example, the sending unit has the generation AI analyze the content of the message and select a highly relevant means of transmission. For example, the sending unit has the generation AI analyze the content of the message and select a highly relevant means of transmission. The sending unit can also have the generation AI suggest an appropriate means of transmission based on the user's past sending history. For example, the sending unit can have the generation AI suggest an appropriate means of transmission based on the user's past sending history. The sending unit can also have the generation AI extract keywords from the message and select a means of transmission based on the relevance. For example, the sending unit has the generation AI extract keywords from the message and select a means of transmission based on the relevance. This allows the means of transmission to be automatically selected based on the relevance of the message. Some or all of the above-mentioned processing in the sending unit may be performed using, or without, the generation AI. For example, the sending unit can input message relevance data into the generation AI and have the generation AI select a means of transmission.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The speech-to-text system may further include a summarizing unit that summarizes the content of the user's utterance. The summarizing unit may, for example, summarize the content of the user's utterance and extract important information. For example, if the user gives a long explanation, the summarizing unit may summarize the content to make it concise. In addition, if the user gives multiple instructions, the summarizing unit may summarize them into a single instruction. Furthermore, if the user makes an emotional statement, the summarizing unit may summarize the emotion and provide an appropriate response. In this way, by summarizing the content of the user's utterance, important information may be extracted and an appropriate response may be provided.

[0067] The speech-to-text system may further include an intention estimation unit that estimates the intention of the user's utterance. The intention estimation unit may, for example, analyze the content, tone, and context of the user's utterance to estimate the user's intention. For example, if the user says "I'm in a hurry," the intention estimation unit may estimate that the user is in a hurry and provide a quick response. Also, if the user says "I want to relax," the intention estimation unit may estimate that the user wants to relax and provide a response appropriate for a relaxed state. Furthermore, if the user says "I'm in trouble," the intention estimation unit may estimate that the user is in trouble and provide appropriate support. In this way, by estimating the intention of the user's utterance, an appropriate response can be provided.

[0068] The speech-to-text system may further include an emotion estimation unit that estimates the emotion of the user's speech. The emotion estimation unit may, for example, analyze the content, tone, and speed of the user's speech to estimate the user's emotion. For example, if the user is excited, the emotion estimation unit may estimate that the user is excited and provide an appropriate response. Also, if the user is relaxed, the emotion estimation unit may estimate that the user is relaxed and provide a response appropriate for the relaxed state. Furthermore, if the user is nervous, the emotion estimation unit may estimate that the user is nervous and provide a response that relieves the tension. In this way, an appropriate response can be provided by estimating the emotion of the user's speech.

[0069] The speech-to-text system may further include a background analysis unit that analyzes background information of the user's utterance. The background analysis unit may, for example, analyze the background information of the user's utterance and infer the user's intentions and emotions. For example, if the user says "I'm in a hurry," the background analysis unit may analyze the background information and infer the reason why the user is in a hurry. Furthermore, if the user says "I want to relax," the background analysis unit may analyze the background information and infer the reason why the user wants to relax. Furthermore, if the user says "I'm in trouble," the background analysis unit may analyze the background information and infer the reason why the user is in trouble. In this way, by analyzing the background information of the user's utterance, the user's intentions and emotions can be inferred and an appropriate response can be provided.

[0070] The speech-to-text system may further include a pattern analysis unit that analyzes the user's speech pattern. The pattern analysis unit may, for example, analyze the user's speech pattern and infer the user's intention or emotion. For example, if the user speaks in a specific pattern, the pattern analysis unit may analyze the pattern and infer the user's intention. Also, if the user speaks with a specific emotion, the pattern analysis unit may analyze the pattern and infer the user's emotion. Furthermore, if the user's speech pattern changes, the pattern analysis unit may analyze the change and infer the change in the user's intention or emotion. In this way, by analyzing the user's speech pattern, the user's intention or emotion can be inferred and an appropriate response can be provided.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The conversion unit converts the voice into text. For example, the conversion unit analyzes the voice data and converts it into text using voice recognition technology. Voice data can also be converted into text using generation AI. Step 2: The storage unit stores the text converted by the conversion unit. For example, the storage unit stores the text data in a database, cloud storage, or local storage. Step 3: The reception unit receives a voice command. The reception unit, for example, analyzes the voice command and issues an instruction to operate a device or send a text message. Step 4: The operation unit operates the device based on the voice command received by the reception unit. For example, the operation unit plays music or turns on a light based on the voice command.

[0073] (Example 2) A speech-to-text system according to an embodiment of the present invention is a system that converts speech into text, stores the text, accepts voice commands, and operates a device. This speech-to-text system converts speech into text and provides the text as a memo to be saved. For example, when a user creates a memo by voice, the system converts speech into text and provides the text as a memo to be saved. Next, when the user sends a text message by voice, the system converts speech into text to support message sending. For example, a user can send a message by voice while driving, enabling hands-free communication. Furthermore, the system can accept voice commands to operate a device. For example, the system can play music or turn on lights by voice. This allows the user to create voice memos, send text messages by voice input, and operate a device via voice control. This allows the user to create memos by voice, send text messages by voice, and operate a device by voice commands.

[0074] The speech-to-text system according to the embodiment includes a conversion unit, a storage unit, a reception unit, and an operation unit. The conversion unit converts speech into text. For example, the conversion unit analyzes speech data and converts it into text data using speech recognition technology. For example, the conversion unit analyzes speech data with high accuracy and converts it into text data using natural language processing technology. The conversion unit can also convert speech data into text data using a generation AI. The generation AI converts speech data into text data using an AI model that receives speech data as input and outputs text data. The storage unit stores the text converted by the conversion unit. For example, the storage unit stores the text data in a database. The storage unit can also store the text data in cloud storage. The storage unit can also store the text data in local storage. The reception unit receives a voice command. For example, the reception unit analyzes the voice command and performs appropriate processing. For example, the reception unit analyzes the voice command and instructs a device operation. The reception unit can also analyze the voice command and instruct the sending of a text message. The operation unit operates the device based on the voice command accepted by the acceptance unit. The operation unit controls the device based on the voice command, for example. For example, the operation unit plays music based on the voice command. The operation unit can also turn on a light based on the voice command. In this way, the speech-to-text system according to the embodiment can convert speech into text, store the text, accept voice commands, and operate the device.

[0075] The speech-to-text system includes a preprocessing unit that preprocesses the speech data. The preprocessing unit preprocesses the speech data. The preprocessing unit, for example, performs noise removal. For example, the preprocessing unit removes background noise from the speech data. The preprocessing unit can also adjust the volume. For example, the preprocessing unit adjusts the volume of the speech data to maintain a constant volume. The preprocessing unit can also perform filtering. For example, the preprocessing unit filters to emphasize a specific frequency band of the speech data. This improves conversion accuracy by preprocessing the speech data. Some or all of the above-described processing in the preprocessing unit may be performed using, or without, a generation AI. For example, the preprocessing unit inputs speech data to the generation AI and has the generation AI perform noise removal and volume adjustment.

[0076] The speech-to-text system includes an analysis unit for improving the accuracy of speech recognition. The analysis unit performs analysis for improving the accuracy of speech recognition. The analysis unit, for example, extracts speech features. For example, the analysis unit extracts speech features from speech data to improve the accuracy of speech recognition. The analysis unit can also perform statistical analysis. For example, the analysis unit performs statistical analysis of speech data to improve the accuracy of speech recognition. The analysis unit can also apply a machine learning algorithm. For example, the analysis unit applies a machine learning algorithm to speech data to improve the accuracy of speech recognition. This improves the accuracy of speech recognition. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input speech data to a generation AI and have the generation AI perform extraction of speech features and statistical analysis.

[0077] The speech-to-text system includes a transmitting unit that transmits the converted text as a message. The transmitting unit transmits the converted text as a message. The transmitting unit, for example, transmits a text message. For example, the transmitting unit transmits the converted text as a text message. The transmitting unit can also transmit a voice message. For example, the transmitting unit transmits the converted text as a voice message. The transmitting unit can also transmit an image message. For example, the transmitting unit transmits the converted text as an image message. In this way, the converted text can be transmitted as a message. Some or all of the above-described processing in the transmitting unit may be performed using, or without using, a generation AI. For example, the transmitting unit may input the converted text to the generation AI and cause the generation AI to generate a text message or a voice message.

[0078] The conversion unit can convert speech into text. For example, the conversion unit analyzes speech data and converts it into text data using speech recognition technology. For example, the conversion unit analyzes speech data with high accuracy and converts it into text data using natural language processing technology. The conversion unit can also convert speech data into text data using a generation AI. For example, the generation AI converts speech data into text data using an AI model that inputs speech data and outputs text data. This clarifies the function of converting speech to text. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversion unit can input speech data to the generation AI and have the generation AI generate text data from the speech data.

[0079] The storage unit can store the converted text. The storage unit, for example, stores the text data in a database. For example, the storage unit stores the converted text in a database. The storage unit can also store the text data in cloud storage. For example, the storage unit stores the converted text in cloud storage. The storage unit can also store the text data in local storage. For example, the storage unit stores the converted text in local storage. This clarifies the function of storing the converted text. Some or all of the above-described processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input the converted text to the generation AI and cause the generation AI to store the text data.

[0080] The reception unit can receive a voice command. The reception unit, for example, analyzes the voice command and performs appropriate processing. For example, the reception unit analyzes the voice command and instructs the device to operate. The reception unit can also analyze the voice command and instruct the sending of a text message. This clarifies the function of receiving a voice command. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the voice command to the generation AI and have the generation AI analyze the voice command.

[0081] The operation unit can operate a device based on a voice command. The operation unit, for example, controls a device based on a voice command. For example, the operation unit plays music based on a voice command. The operation unit can also turn on a light based on a voice command. This clarifies the function of operating a device based on a voice command. Some or all of the above-described processing in the operation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the operation unit can input a voice command to a generation AI and have the generation AI execute the device operation.

[0082] The conversion unit can estimate the user's emotions and adjust the voice conversion accuracy based on the estimated user emotions. For example, when the user is nervous, the conversion unit strengthens noise removal so that the generation AI can improve the voice conversion accuracy. For example, when the user is nervous, the conversion unit causes the generation AI to analyze the voice data and strengthen noise removal. Furthermore, when the user is relaxed, the conversion unit can cause the generation AI to set the voice conversion accuracy to normal mode and perform natural voice conversion. For example, when the user is relaxed, the conversion unit causes the generation AI to analyze the voice data and perform voice conversion in normal mode. Furthermore, when the user is in a hurry, the conversion unit causes the generation AI to prioritize voice conversion speed and convert the voice into text quickly. For example, when the user is in a hurry, the conversion unit causes the generation AI to analyze the voice data and convert the voice into text while prioritizing conversion speed. This allows the voice conversion accuracy to be adjusted based on the user's emotions. Some or all of the above-mentioned processing in the conversion unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the conversion unit can input the user's emotional data into the generation AI and have the generation AI adjust the accuracy of the voice conversion.

[0083] The conversion unit can automatically remove background noise from the audio, improving conversion accuracy. For example, the conversion unit has a generation AI analyze the audio data and identify and remove background noise. For example, the conversion unit has a generation AI analyze the audio data and identify and remove background noise. The conversion unit can also have the generation AI perform noise filtering in real time to obtain clear audio data. For example, the conversion unit has the generation AI perform noise filtering in real time to obtain clear audio data. The conversion unit can also have the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. For example, the conversion unit has the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. This removes background noise from the audio, improving conversion accuracy. Some or all of the above-described processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input audio data to the generation AI and have the generation AI remove background noise.

[0084] The conversion unit can identify the speaker of the audio and apply a different conversion algorithm to each speaker. For example, the generation AI in the conversion unit extracts speaker characteristics from the audio data and applies an individual conversion algorithm. For example, the generation AI in the conversion unit extracts speaker characteristics from the audio data and applies an individual conversion algorithm. The conversion unit can also analyze the speaker's tone and accent and select the optimal conversion algorithm. For example, the conversion unit can analyze the speaker's tone and accent and select the optimal conversion algorithm. The conversion unit can also identify multiple speakers and apply an appropriate conversion algorithm to each speaker. For example, the conversion unit can identify multiple speakers and apply an appropriate conversion algorithm to each speaker. This allows the optimal conversion algorithm to be applied to each speaker. Some or all of the above-described processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input speaker characteristic data to the generation AI and have the generation AI apply a different conversion algorithm to each speaker.

[0085] The conversion unit can estimate the user's emotions and adjust the expression of the converted text based on the estimated user's emotions. For example, if the user is nervous, the conversion unit causes the generation AI to simplify the text and make it easier to read. For example, if the user is nervous, the conversion unit causes the generation AI to simplify the text and make it easier to read. The conversion unit can also cause the generation AI to add detailed information to the text and create richer expressions when the user is relaxed. For example, if the user is relaxed, the conversion unit causes the generation AI to add detailed information to the text and create richer expressions. The conversion unit can also cause the generation AI to shorten the text and include only the main points when the user is in a hurry. For example, if the user is in a hurry, the conversion unit can shorten the text and include only the main points. This allows the expression of the text to be adjusted based on the user's emotions. Some or all of the above-mentioned processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input user emotion data into the generation AI and cause the generation AI to adjust the expression of the text.

[0086] The conversion unit can automatically detect the language of the voice and perform conversion that supports multiple languages. For example, the conversion unit has the generation AI analyze the voice data and automatically identify the language. For example, the conversion unit has the generation AI analyze the voice data and automatically identify the language. The conversion unit can also have the generation AI prepare multiple language models and select an appropriate language model to perform conversion. For example, the conversion unit can have the generation AI prepare multiple language models and select an appropriate language model to perform conversion. The conversion unit can also handle cases where the generation AI switches languages ​​in the voice data and perform conversion seamlessly. For example, the conversion unit can handle cases where the generation AI switches languages ​​in the voice data and perform conversion seamlessly. This enables voice conversion that supports multiple languages. Some or all of the above-mentioned processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input voice data to the generation AI and have the generation AI perform automatic language detection and conversion that supports multiple languages.

[0087] The conversion unit can adjust the speed of the voice to improve conversion accuracy. For example, the conversion unit has the generation AI analyze the speed of the voice data and adjust it to an appropriate speed to perform conversion. For example, the conversion unit has the generation AI analyze the speed of the voice data and adjust it to an appropriate speed to perform conversion. The conversion unit can also slow down the voice speed if the generation AI is too fast to improve conversion accuracy. For example, the conversion unit can slow down the voice speed if the generation AI is too fast to improve conversion accuracy. The conversion unit can also speed up the voice speed if the generation AI is too slow to perform conversion efficiently. For example, the conversion unit can speed up the voice speed if the generation AI is too slow to perform conversion efficiently. In this way, adjusting the voice speed improves conversion accuracy. Some or all of the above-mentioned processing in the conversion unit may be performed using, or without, the generation AI. For example, the conversion unit can input voice data to the generation AI and have the generation AI adjust the voice speed.

[0088] The storage unit can estimate the user's emotions and adjust the format of the text to be saved based on the estimated user's emotions. For example, if the user is nervous, the storage unit saves the text in a simple, highly visible format. For example, if the user is nervous, the storage unit saves the text in a simple, highly visible format. The storage unit can also save the text in a format including detailed information if the user is relaxed. For example, if the user is relaxed, the storage unit saves the text in a format including detailed information. The storage unit can also save the text in a concise format including only the main points if the user is in a hurry. For example, if the user is in a hurry, the storage unit saves the text in a concise format including only the main points. This allows the text format to be adjusted based on the user's emotions. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, a generation AI. For example, the storage unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the text format.

[0089] The storage unit can determine the storage priority based on the importance of the text when saving. For example, the storage unit has the generation AI analyze the content of the text, evaluate the importance, and determine the storage priority. For example, the storage unit has the generation AI analyze the content of the text, evaluate the importance, and determine the storage priority. The storage unit can also have the generation AI evaluate the importance by referring to the user's past saving history. For example, the storage unit has the generation AI evaluate the importance by referring to the user's past saving history. The storage unit can also have the generation AI extract keywords from the text, evaluate the importance, and determine the storage priority. For example, the storage unit has the generation AI extract keywords from the text, evaluate the importance, and determine the storage priority. This makes it possible to determine the storage priority based on the importance of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text importance data to the generation AI and have the generation AI determine the storage priority.

[0090] The storage unit can apply different storage methods depending on the category of the text when saving. For example, the generation AI analyzes the content of the text, automatically determines the category, and selects the storage method. For example, the storage unit analyzes the content of the text, automatically determines the category, and selects the storage method. The storage unit can also suggest an appropriate storage method by having the generation AI refer to the user's past saving history. For example, the storage unit can suggest an appropriate storage method by having the generation AI refer to the user's past saving history. The storage unit can also extract keywords from the text and apply a storage method depending on the category. For example, the storage unit can extract keywords from the text and apply a storage method depending on the category. This makes it possible to apply different storage methods depending on the category of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text category data to the generation AI and have the generation AI select the storage method.

[0091] The storage unit can estimate the user's emotions and tag the text to be saved based on the estimated user's emotions. For example, if the user is nervous, the storage unit saves the text with a simple tag. For example, if the user is nervous, the storage unit saves the text with a simple tag. Furthermore, if the user is relaxed, the storage unit can save the text with a detailed tag. For example, if the user is relaxed, the storage unit saves the text with a detailed tag. Furthermore, if the user is in a hurry, the storage unit can save the text with a tag that summarizes the main points. For example, if the user is in a hurry, the storage unit saves the text with a tag that summarizes the main points. In this way, the text can be tagged based on the user's emotions. Some or all of the above-described processing in the storage unit may be performed using, or without, a generation AI. For example, the storage unit can input the user's emotion data into the generation AI and cause the generation AI to tag the text.

[0092] The storage unit can adjust the order of saving based on the time of submission of the text when saving. For example, the storage unit analyzes the time of submission of the text by the generation AI and determines the order of saving. For example, the storage unit analyzes the time of submission of the text by the generation AI and determines the order of saving. The storage unit can also adjust the order of saving by the generation AI with reference to the user's past submission history. For example, the storage unit can adjust the order of saving by the generation AI with reference to the user's past submission history. The storage unit can also select text to be preferentially saved by the generation AI based on the time of submission of the text. For example, the storage unit selects text to be preferentially saved by the generation AI based on the time of submission of the text. This makes it possible to adjust the order of saving based on the time of submission of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text submission time data into the generation AI and cause the generation AI to adjust the order of saving.

[0093] The storage unit can automatically select a storage folder based on the relevance of the text when saving. For example, the storage unit has the generation AI analyze the content of the text and select a highly relevant folder. For example, the storage unit has the generation AI analyze the content of the text and select a highly relevant folder. The storage unit can also have the generation AI suggest an appropriate folder by referring to the user's past saving history. For example, the storage unit can have the generation AI suggest an appropriate folder by referring to the user's past saving history. The storage unit can also have the generation AI extract keywords from the text and select a storage folder based on relevance. For example, the storage unit has the generation AI extract keywords from the text and select a storage folder based on relevance. This makes it possible to automatically select a storage folder based on the relevance of the text. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, the generation AI. For example, the storage unit can input text relevance data to the generation AI and have the generation AI select a storage folder.

[0094] The reception unit can estimate the user's emotions and adjust the method of receiving voice commands based on the estimated user emotions. For example, when the user is nervous, the reception unit provides a simple interface and minimizes the steps for receiving voice commands. For example, when the user is nervous, the reception unit provides a simple interface and minimizes the steps for receiving voice commands. The reception unit can also provide detailed voice command options and suggest a customizable reception method when the user is relaxed. For example, when the user is relaxed, the reception unit can provide detailed voice command options and suggest a customizable reception method. The reception unit can also prioritize voice input when the user is in a hurry so that voice commands can be received quickly. For example, when the user is in a hurry, the reception unit prioritizes voice input so that voice commands can be received quickly. This makes it possible to adjust the method of receiving voice commands based on the user's emotions. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input user emotion data into the generation AI and cause the generation AI to adjust the method of receiving voice commands.

[0095] When receiving a voice command, the reception unit can select the optimal reception method by referring to the user's past command history. For example, the reception unit uses a generation AI to analyze the user's past voice command history and propose the optimal reception method. For example, the reception unit uses a generation AI to analyze the user's past voice command history and propose the optimal reception method. The reception unit can also prioritize receiving frequently used commands from the user's past command history. For example, the reception unit uses a generation AI to prioritize receiving frequently used commands from the user's past command history. The reception unit can also predict and suggest commands that will be used in a specific time period based on the user's past command history. For example, the reception unit uses a generation AI to predict and suggest commands that will be used in a specific time period based on the user's past command history. This allows the optimal reception method to be selected based on the user's past command history. Some or all of the above-described processing in the reception unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's past command history data into the generation AI and have the generation AI select a reception method.

[0096] The reception unit can filter voice commands based on the user's current situation when receiving them. For example, the reception unit allows the generation AI to analyze the user's current location information and prioritize receiving highly relevant voice commands. For example, the reception unit allows the generation AI to analyze the user's current location information and prioritize receiving highly relevant voice commands. The reception unit can also allow the generation AI to suggest appropriate voice commands by taking into account the user's current activity status. For example, the reception unit allows the generation AI to suggest appropriate voice commands by taking into account the user's current activity status. The reception unit can also allow the generation AI to analyze the user's current device usage status and select the optimal voice command. For example, the reception unit allows the generation AI to analyze the user's current device usage status and select the optimal voice command. This allows the voice commands to be filtered based on the user's current situation. Some or all of the above-described processing in the reception unit can be performed using, or without, the generation AI. For example, the reception unit can input the user's current situation data to the generation AI and have the generation AI perform voice command filtering.

[0097] The reception unit can estimate the user's emotions and determine the priority of voice commands to be received based on the estimated user's emotions. For example, when the user is nervous, the reception unit prioritizes receiving important voice commands. For example, when the user is nervous, the reception unit prioritizes receiving important voice commands. The reception unit can also prioritize receiving detailed voice commands when the user is relaxed. For example, when the user is relaxed, the reception unit prioritizes receiving detailed voice commands. The reception unit can also prioritize receiving voice commands that require rapid processing when the user is in a hurry. For example, when the user is in a hurry, the reception unit prioritizes receiving voice commands that require rapid processing. This makes it possible to determine the priority of voice commands based on the user's emotions. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit may input user emotion data into the generation AI and cause the generation AI to determine the priority of voice commands.

[0098] When receiving a voice command, the reception unit can prioritize receiving highly relevant commands by taking into account the user's geographical location information. For example, the reception unit allows the generation AI to analyze the user's current location and prioritize receiving highly relevant voice commands. For example, the reception unit allows the generation AI to analyze the user's current location and prioritize receiving highly relevant voice commands. The reception unit can also allow the generation AI to suggest appropriate voice commands by referring to the user's past location information. For example, the reception unit allows the generation AI to suggest appropriate voice commands by referring to the user's past location information. The reception unit can also allow the generation AI to select an optimal voice command based on the user's current location. For example, the reception unit allows the generation AI to select an optimal voice command based on the user's current location. This allows highly relevant commands to be preferentially received based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit can input the user's geographical location information data to the generation AI and cause the generation AI to select a voice command.

[0099] When receiving a voice command, the reception unit can analyze the user's social media activity and receive a related command. For example, the reception unit can have a generation AI analyze the user's social media activity and suggest a highly relevant voice command. For example, the reception unit can have a generation AI analyze the user's social media activity and suggest a highly relevant voice command. The reception unit can also have the generation AI select an appropriate voice command by referring to the user's past social media posts. For example, the reception unit can have the generation AI select an appropriate voice command by referring to the user's past social media posts. The reception unit can also receive an optimal voice command by the generation AI based on the user's social media activity. For example, the reception unit can receive an optimal voice command by the generation AI based on the user's social media activity. This allows reception of a relevant command based on the user's social media activity. Some or all of the above-described processing in the reception unit can be performed using, or without, the generation AI. For example, the reception unit can input the user's social media activity data into the generation AI and have the generation AI select a voice command.

[0100] The operation unit can estimate the user's emotions and adjust the device operation method based on the estimated user's emotions. For example, when the user is nervous, the operation unit provides a simple and intuitive operation method. For example, when the user is nervous, the operation unit provides a simple and intuitive operation method. Furthermore, when the user is relaxed, the operation unit can provide detailed operation options and suggest a customizable operation method. For example, when the user is relaxed, the operation unit can provide detailed operation options and suggest a customizable operation method. Furthermore, when the user is in a hurry, the operation unit can provide a concise operation method so that the operation can be completed quickly. For example, when the user is in a hurry, the operation unit provides a concise operation method so that the operation can be completed quickly. This makes it possible to adjust the device operation method based on the user's emotions. Some or all of the above-described processing in the operation unit may be performed using, or without, a generation AI. For example, the operation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the device operation method.

[0101] When operating the device, the operation unit can select an optimal operation method by referring to the user's past operation history. For example, the operation unit allows the generation AI to analyze the user's past operation history and propose an optimal operation method. For example, the operation unit allows the generation AI to analyze the user's past operation history and propose an optimal operation method. The operation unit can also allow the generation AI to prioritize frequently used operations from the user's past operation history. For example, the operation unit allows the generation AI to prioritize frequently used operations from the user's past operation history. The operation unit can also allow the generation AI to predict and propose operations to be used in a specific time period based on the user's past operation history. For example, the operation unit allows the generation AI to predict and propose operations to be used in a specific time period based on the user's past operation history. This allows the optimal operation method to be selected based on the user's past operation history. Some or all of the above-described processing in the operation unit may be performed using, or without, the generation AI. For example, the operation unit can input the user's past operation history data into the generation AI and have the generation AI select an operation method.

[0102] When operating the device, the operation unit can determine the priority of operations based on the user's current situation. For example, the operation unit allows the generation AI to analyze the user's current location information and prioritize providing highly relevant operations. For example, the operation unit allows the generation AI to analyze the user's current location information and prioritize providing highly relevant operations. The operation unit can also allow the generation AI to suggest appropriate operations by taking into account the user's current activity status. For example, the operation unit allows the generation AI to suggest appropriate operations by taking into account the user's current activity status. The operation unit can also allow the generation AI to analyze the user's current device usage status and select an optimal operation. For example, the operation unit allows the generation AI to analyze the user's current device usage status and select an optimal operation. This makes it possible to determine the priority of operations based on the user's current situation. Some or all of the above-mentioned processing in the operation unit may be performed using, or without, the generation AI. For example, the operation unit can input the user's current situation data to the generation AI and have the generation AI determine the priority of operations.

[0103] The operation unit can estimate the user's emotions and determine the priority of devices to be operated based on the estimated user's emotions. For example, when the user is nervous, the operation unit can prioritize providing operations for important devices. For example, when the user is nervous, the operation unit can prioritize providing operations for important devices. The operation unit can also provide detailed device operation options when the user is relaxed. For example, when the user is relaxed, the operation unit can provide detailed device operation options. The operation unit can also provide concise device operations so that operations can be completed quickly when the user is in a hurry. For example, when the user is in a hurry, the operation unit provides concise device operations so that operations can be completed quickly. This makes it possible to determine the priority of devices to be operated based on the user's emotions. Some or all of the above-described processing in the operation unit may be performed using, or without, a generation AI. For example, the operation unit can input user emotion data into the generation AI and have the generation AI determine the device priority.

[0104] When operating a device, the operation unit can select an optimal operation method by taking into account the user's geographical location information. For example, the operation unit allows the generation AI to analyze the user's current location and prioritize providing highly relevant device operations. For example, the operation unit allows the generation AI to analyze the user's current location and prioritize providing highly relevant device operations. The operation unit can also allow the generation AI to suggest appropriate device operations by referring to the user's past location information. For example, the operation unit allows the generation AI to suggest appropriate device operations by referring to the user's past location information. The operation unit can also allow the generation AI to select optimal device operations based on the user's current location. For example, the operation unit allows the generation AI to select optimal device operations based on the user's current location. This allows the optimal operation method to be selected based on the user's geographical location information. Some or all of the above-described processing in the operation unit may be performed using, or without, the generation AI. For example, the operation unit can input the user's geographical location information data to the generation AI and have the generation AI select an operation method.

[0105] The operation unit can analyze the user's social media activity and suggest operation means when operating the device. For example, the operation unit allows the generation AI to analyze the user's social media activity and suggest highly relevant device operations. For example, the operation unit allows the generation AI to analyze the user's social media activity and suggest highly relevant device operations. The operation unit can also allow the generation AI to select appropriate device operations by referring to the user's past social media posts. For example, the operation unit allows the generation AI to select appropriate device operations by referring to the user's past social media posts. The operation unit can also allow the generation AI to suggest optimal device operations based on the user's social media activity. For example, the operation unit allows the generation AI to suggest optimal device operations based on the user's social media activity. This allows the generation AI to suggest optimal operation means based on the user's social media activity. Some or all of the above-described processing in the operation unit can be performed using, or without, the generation AI. For example, the operation unit can input the user's social media activity data into the generation AI and have the generation AI execute the operation means suggestion.

[0106] The preprocessing unit can estimate the user's emotions and adjust the preprocessing method for the voice data based on the estimated user's emotions. For example, when the user is nervous, the preprocessing unit causes the generation AI to enhance noise reduction and provide clear voice data. For example, when the user is nervous, the preprocessing unit causes the generation AI to enhance noise reduction and provide clear voice data. The preprocessing unit can also cause the generation AI to apply a normal preprocessing method and provide natural voice data when the user is relaxed. For example, when the user is relaxed, the preprocessing unit causes the generation AI to apply a normal preprocessing method and provide natural voice data. The preprocessing unit can also cause the generation AI to prioritize preprocessing speed and quickly process the voice data when the user is in a hurry. For example, when the user is in a hurry, the preprocessing unit causes the generation AI to prioritize preprocessing speed and quickly process the voice data. This allows the preprocessing method for the voice data to be adjusted based on the user's emotions. Some or all of the above-described processing in the preprocessing unit can be performed using, or without, the generation AI. For example, the preprocessing unit can input user emotion data to the generation AI and have the generation AI adjust the preprocessing method.

[0107] The preprocessing unit can perform filtering to improve the accuracy of noise removal when preprocessing the audio data. For example, the preprocessing unit allows the generation AI to analyze the audio data and apply optimal noise filtering. For example, the preprocessing unit allows the generation AI to analyze the audio data and apply optimal noise filtering. The preprocessing unit can also allow the generation AI to perform noise filtering in real time to provide clear audio data. For example, the preprocessing unit allows the generation AI to perform noise filtering in real time to provide clear audio data. The preprocessing unit can also allow the generation AI to apply multiple noise removal algorithms and select the optimal noise removal method. For example, the preprocessing unit allows the generation AI to apply multiple noise removal algorithms and select the optimal noise removal method. This allows filtering to improve the accuracy of noise removal. Some or all of the above-described processing in the preprocessing unit can be performed using, or without, the generation AI. For example, the preprocessing unit can input audio data to the generation AI and have the generation AI perform noise filtering.

[0108] The preprocessing unit can identify the speaker of the voice and customize the preprocessing method when preprocessing the voice data. For example, the preprocessing unit allows the generation AI to extract speaker characteristics from the voice data and apply an individual preprocessing method. For example, the preprocessing unit allows the generation AI to extract speaker characteristics from the voice data and apply an individual preprocessing method. The preprocessing unit can also allow the generation AI to analyze the speaker's tone of voice and accent and select the optimal preprocessing method. For example, the preprocessing unit can allow the generation AI to analyze the speaker's tone of voice and accent and select the optimal preprocessing method. The preprocessing unit can also allow the generation AI to identify multiple speakers and apply a preprocessing method appropriate for each speaker. For example, the preprocessing unit can allow the generation AI to identify multiple speakers and apply a preprocessing method appropriate for each speaker. This allows the speaker of the voice to be identified and the preprocessing method to be customized. Some or all of the above-described processing in the preprocessing unit may be performed using, or without, the generation AI. For example, the preprocessing unit can input speaker characteristic data into the generation AI and have the generation AI customize the preprocessing method.

[0109] The preprocessing unit can estimate the user's emotions and determine the priority of the voice data to be preprocessed based on the estimated user's emotions. For example, when the user is nervous, the preprocessing unit prioritizes preprocessing of important voice data. For example, when the user is nervous, the preprocessing unit prioritizes preprocessing of important voice data. The preprocessing unit can also prioritize preprocessing of detailed voice data when the user is relaxed. For example, when the user is relaxed, the preprocessing unit prioritizes preprocessing of detailed voice data. The preprocessing unit can also prioritize preprocessing of voice data that requires rapid processing when the user is in a hurry. For example, when the user is in a hurry, the preprocessing unit prioritizes preprocessing of voice data that requires rapid processing. This makes it possible to determine the priority of the voice data to be preprocessed based on the user's emotions. Some or all of the above-described processing in the preprocessing unit may be performed using, or without, a generation AI. For example, the preprocessing unit can input user emotion data to the generation AI and have the generation AI determine the priority of the voice data.

[0110] The preprocessing unit can automatically detect the language of the speech and adjust the preprocessing method when preprocessing the speech data. For example, the preprocessing unit causes the generation AI to analyze the speech data and automatically identify the language. For example, the preprocessing unit causes the generation AI to analyze the speech data and automatically identify the language. The preprocessing unit can also cause the generation AI to prepare multiple language models and select an appropriate language model to perform preprocessing. For example, the generation AI can prepare multiple language models and select an appropriate language model to perform preprocessing. The preprocessing unit can also handle cases where the generation AI switches languages ​​in the speech data and perform seamless preprocessing. For example, the preprocessing unit can handle cases where the generation AI switches languages ​​in the speech data and perform seamless preprocessing. This allows the language of the speech to be automatically detected and the preprocessing method to be adjusted. Some or all of the above-described processing in the preprocessing unit may be performed using, or without, the generation AI. For example, the preprocessing unit can input speech data to the generation AI and have the generation AI perform automatic language detection and adjustment of the preprocessing method.

[0111] The preprocessing unit can adjust the speed of the voice when preprocessing the voice data to improve the accuracy of the preprocessing. For example, the preprocessing unit analyzes the speed of the voice data by the generation AI, adjusts the speed to an appropriate speed, and performs preprocessing. For example, the preprocessing unit analyzes the speed of the voice data by the generation AI, adjusts the speed to an appropriate speed, and performs preprocessing. The preprocessing unit can also slow down the speed of the voice if the generation AI's voice speed is too fast to improve the accuracy of preprocessing. For example, the preprocessing unit can slow down the speed of the voice if the generation AI's voice speed is too fast to improve the accuracy of preprocessing. The preprocessing unit can also speed up the speed of the voice if the generation AI's voice speed is too slow to efficiently perform preprocessing. For example, the preprocessing unit can speed up the speed of the voice if the generation AI's voice speed is too slow to efficiently perform preprocessing. In this way, the accuracy of preprocessing can be improved by adjusting the speed of the voice. Some or all of the above-mentioned processing in the preprocessing unit may be performed using, or without, the generation AI. For example, the preprocessing unit can input voice data to the generation AI and have the generation AI adjust the speed of the voice.

[0112] The analysis unit can estimate the user's emotions and adjust the voice recognition analysis method based on the estimated user's emotions. For example, when the user is nervous, the analysis unit causes the generation AI to strengthen noise reduction and provide clear voice data. For example, when the user is nervous, the analysis unit causes the generation AI to strengthen noise reduction and provide clear voice data. Furthermore, when the user is relaxed, the analysis unit can cause the generation AI to apply a normal analysis method and provide natural voice data. For example, when the user is relaxed, the analysis unit causes the generation AI to apply a normal analysis method and provide natural voice data. Furthermore, when the user is in a hurry, the analysis unit can cause the generation AI to prioritize analysis speed and quickly analyze the voice data. For example, when the user is in a hurry, the analysis unit can prioritize analysis speed and quickly analyze the voice data. This allows the voice recognition analysis method to be adjusted based on the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the analysis method.

[0113] The analysis unit can improve analysis accuracy by automatically removing background noise from the voice during voice recognition analysis. For example, the analysis unit has the generation AI analyze the voice data and apply optimal noise filtering. For example, the analysis unit has the generation AI analyze the voice data and apply optimal noise filtering. The analysis unit can also have the generation AI perform noise filtering in real time to provide clear voice data. For example, the analysis unit has the generation AI perform noise filtering in real time to provide clear voice data. The analysis unit can also have the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. For example, the analysis unit has the generation AI apply multiple noise removal algorithms and select the optimal noise removal method. This improves analysis accuracy by removing background noise from the voice. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input voice data to the generation AI and have the generation AI perform noise filtering.

[0114] The analysis unit can identify the speaker of the voice and customize the analysis algorithm when analyzing the voice recognition. For example, the generation AI extracts speaker characteristics from the voice data and applies an individual analysis algorithm to the analysis unit. For example, the analysis unit extracts speaker characteristics from the voice data and applies an individual analysis algorithm to the analysis unit. The analysis unit can also analyze the tone and accent of the speaker's voice and select the optimal analysis algorithm to the analysis unit. For example, the analysis unit can analyze the tone and accent of the speaker's voice and select the optimal analysis algorithm to the analysis unit. The analysis unit can also identify multiple speakers and apply an appropriate analysis algorithm to each speaker. For example, the analysis unit can identify multiple speakers and apply an appropriate analysis algorithm to each speaker. This allows the speaker of the voice to be identified and the analysis algorithm to be customized. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input speaker characteristic data to the generation AI and have the generation AI customize the analysis algorithm.

[0115] The analysis unit can estimate the user's emotions and determine the priority of the voice data to be analyzed based on the estimated user's emotions. For example, when the user is nervous, the analysis unit prioritizes analyzing important voice data. For example, when the user is nervous, the analysis unit prioritizes analyzing important voice data. The analysis unit can also prioritize analyzing detailed voice data when the user is relaxed. For example, when the user is relaxed, the analysis unit prioritizes analyzing detailed voice data. The analysis unit can also prioritize analyzing voice data that requires rapid processing when the user is in a hurry. For example, when the user is in a hurry, the analysis unit prioritizes analyzing voice data that requires rapid processing. This makes it possible to determine the priority of the voice data to be analyzed based on the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of the voice data.

[0116] The analysis unit can automatically detect the language of the voice during speech recognition analysis and adjust the analysis method. For example, the analysis unit has the generation AI analyze the voice data and automatically identify the language. For example, the analysis unit has the generation AI analyze the voice data and automatically identify the language. The analysis unit can also select an appropriate language model from among multiple language models prepared by the generation AI and perform analysis. For example, the analysis unit can select an appropriate language model from among multiple language models prepared by the generation AI and perform analysis. The analysis unit can also handle cases where the generation AI switches languages ​​within the voice data and perform analysis seamlessly. For example, the analysis unit can handle cases where the generation AI switches languages ​​within the voice data and perform analysis seamlessly. This allows the language of the voice to be automatically detected and the analysis method to be adjusted. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input voice data to the generation AI and have the generation AI automatically detect the language and adjust the analysis method.

[0117] The analysis unit can adjust the speed of the voice during speech recognition analysis to improve analysis accuracy. For example, the analysis unit analyzes the speed of the voice data by the generation AI and adjusts it to an appropriate speed for analysis. For example, the analysis unit analyzes the speed of the voice data by the generation AI and adjusts it to an appropriate speed for analysis. The analysis unit can also slow down the speed of the voice if the generation AI speaks too fast to improve analysis accuracy. For example, the analysis unit can slow down the speed of the voice if the generation AI speaks too fast to improve analysis accuracy. The analysis unit can also speed up the speed of the voice if the generation AI speaks too slow to efficiently analyze. For example, the analysis unit can speed up the speed of the voice if the generation AI speaks too slow to efficiently analyze. In this way, the analysis accuracy can be improved by adjusting the speed of the voice. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input voice data to the generation AI and have the generation AI adjust the speed of the voice.

[0118] The transmission unit can estimate the user's emotions and adjust the expression method of the message to be sent based on the estimated user's emotions. For example, if the user is nervous, the transmission unit transmits a simple, highly visible message. For example, if the user is nervous, the transmission unit transmits a simple, highly visible message. The transmission unit can also transmit a message including detailed information if the user is relaxed. For example, if the user is relaxed, the transmission unit transmits a message including detailed information. The transmission unit can also transmit a concise message including only the main points if the user is in a hurry. For example, if the user is in a hurry, the transmission unit transmits a concise message including only the main points. This allows the expression method of the message to be adjusted based on the user's emotions. Some or all of the above-mentioned processing in the transmission unit may be performed using, or without, a generation AI. For example, the transmission unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the expression method of the message.

[0119] When sending a message, the transmission unit can determine the transmission priority based on the importance of the message. For example, the generation AI analyzes the content of the message, evaluates the importance, and determines the transmission priority. For example, the transmission unit analyzes the content of the message, evaluates the importance, and determines the transmission priority. The transmission unit can also evaluate the importance by referring to the user's past sending history. For example, the transmission unit can evaluate the importance by referring to the user's past sending history. The transmission unit can also extract keywords from the message, evaluate the importance, and determine the transmission priority. For example, the transmission unit can extract keywords from the message, evaluate the importance, and determine the transmission priority. In this way, the transmission priority can be determined based on the importance of the message. Some or all of the above-mentioned processing in the transmission unit may be performed using, or without, the generation AI. For example, the transmission unit can input message importance data to the generation AI and have the generation AI determine the transmission priority.

[0120] When sending a message, the sending unit can apply different sending methods depending on the message category. For example, the generation AI analyzes the content of the message, automatically determines the category, and selects the sending method. For example, the generation AI analyzes the content of the message, automatically determines the category, and selects the sending method. The sending unit can also suggest an appropriate sending method by referring to the user's past sending history. For example, the sending unit can suggest an appropriate sending method by referring to the user's past sending history. The sending unit can also extract keywords from the message and apply a sending method depending on the category. For example, the sending unit can extract keywords from the message and apply a sending method depending on the category. This allows different sending methods to be applied depending on the message category. Some or all of the above-mentioned processing in the sending unit may be performed using, or without, the generation AI. For example, the sending unit can input message category data into the generation AI and have the generation AI select the sending method.

[0121] The sending unit can estimate the user's emotions and adjust the length of the message to be sent based on the estimated user's emotions. For example, if the user is nervous, the sending unit sends a simple and short message. For example, if the user is nervous, the sending unit sends a simple and short message. The sending unit can also send a longer message including detailed information if the user is relaxed. For example, if the user is relaxed, the sending unit sends a longer message including detailed information. The sending unit can also send a concise message including only the main points if the user is in a hurry. For example, if the user is in a hurry, the sending unit sends a concise message including only the main points. This allows the length of the message to be adjusted based on the user's emotions. Some or all of the above-mentioned processing in the sending unit may be performed using, or without, a generation AI. For example, the sending unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the length of the message.

[0122] When sending messages, the sending unit can adjust the order of sending based on the time the messages were submitted. For example, the sending unit determines the order of sending by having the generation AI analyze the time the messages were submitted. For example, the sending unit determines the order of sending by having the generation AI analyze the time the messages were submitted. The sending unit can also adjust the order of sending by having the generation AI refer to the user's past submission history. For example, the sending unit can adjust the order of sending by having the generation AI refer to the user's past submission history. The sending unit can also select messages to be sent with priority based on the time the messages were submitted by the generation AI. For example, the sending unit selects messages to be sent with priority based on the time the messages were submitted by the generation AI. This allows the order of sending to be adjusted based on the time the messages were submitted. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the sending unit can input message submission time data into the generation AI and cause the generation AI to adjust the order of sending.

[0123] When sending a message, the sending unit can automatically select a means of transmission based on the relevance of the message. For example, the sending unit has the generation AI analyze the content of the message and select a highly relevant means of transmission. For example, the sending unit has the generation AI analyze the content of the message and select a highly relevant means of transmission. The sending unit can also have the generation AI suggest an appropriate means of transmission based on the user's past sending history. For example, the sending unit can have the generation AI suggest an appropriate means of transmission based on the user's past sending history. The sending unit can also have the generation AI extract keywords from the message and select a means of transmission based on the relevance. For example, the sending unit has the generation AI extract keywords from the message and select a means of transmission based on the relevance. This allows the means of transmission to be automatically selected based on the relevance of the message. Some or all of the above-mentioned processing in the sending unit may be performed using, or without, the generation AI. For example, the sending unit can input message relevance data into the generation AI and have the generation AI select a means of transmission. === Hard Collateral 1-1 === Each of the multiple elements, including the conversion unit, storage unit, reception unit, operation unit, preprocessing unit, analysis unit, and transmission unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the smart device 14 and converts voice data into text data. The storage unit stores the text data in, for example, the database 24 of the data processing device 12. The reception unit receives voice commands using the microphone 38B of the smart device 14. The operation unit operates the device via the control unit 46A of the smart device 14. The preprocessing unit removes noise from the voice data and adjusts the volume via the processor 46 of the smart device 14. The analysis unit performs analysis to improve the accuracy of voice recognition via the specific processing unit 290 of the data processing device 12. The transmission unit transmits the converted text as a message via the communication I / F 44 of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the above-described conversion unit, storage unit, reception unit, operation unit, preprocessing unit, analysis unit, and transmission unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the smart glasses 214 and converts voice data into text data. The storage unit stores the text data in, for example, the database 24 of the data processing device 12. The reception unit receives voice commands using the microphone 238 of the smart glasses 214. The operation unit operates the device via the control unit 46A of the smart glasses 214. The preprocessing unit removes noise from the voice data and adjusts the volume via the processor 46 of the smart glasses 214. The analysis unit performs analysis to improve the accuracy of voice recognition via the specific processing unit 290 of the data processing device 12. The transmission unit transmits the converted text as a message using the communication I / F 44 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned conversion unit, storage unit, reception unit, operation unit, preprocessing unit, analysis unit, and transmission unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the headset type terminal 314 and converts voice data into text data. The storage unit stores the text data in, for example, the database 24 of the data processing device 12. The reception unit receives voice commands using the microphone 238 of the headset type terminal 314. The operation unit operates the device via the control unit 46A of the headset type terminal 314. The preprocessing unit removes noise from the voice data and adjusts the volume via the processor 46 of the headset type terminal 314. The analysis unit performs analysis to improve the accuracy of voice recognition via the specific processing unit 290 of the data processing device 12. The transmission unit transmits the converted text as a message using the communication I / F 44 of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned conversion unit, storage unit, reception unit, operation unit, preprocessing unit, analysis unit, and transmission unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the robot 414 and converts voice data into text data. The storage unit stores the text data in, for example, the database 24 of the data processing device 12. The reception unit receives voice commands using the microphone 238 of the robot 414. The operation unit operates the device via the control unit 46A of the robot 414. The preprocessing unit removes noise from the voice data and adjusts the volume via the processor 46 of the robot 414. The analysis unit performs analysis to improve the accuracy of voice recognition via the specific processing unit 290 of the data processing device 12. The transmission unit transmits the converted text as a message using the communication I / F 44 of the robot 414.

[0124] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0125] The speech-to-text system may further include a tone analysis unit that analyzes the tone and pitch of the user's voice. The tone analysis unit may, for example, analyze the tone and pitch of the user's voice to more accurately estimate the user's emotions and intentions. For example, if the user's voice is high-pitched, the tone analysis unit may estimate that the user is excited and provide an appropriate response. Alternatively, if the user's voice is low and calm, the tone analysis unit may estimate that the user is relaxed and provide a response appropriate for the relaxed state. Furthermore, if the tone of the user's voice changes suddenly, the tone analysis unit may estimate that the user is surprised and provide an appropriate response to the surprise. Thus, by analyzing the tone and pitch of the user's voice, the user's emotions and intentions may be more accurately estimated and an appropriate response may be provided.

[0126] The speech-to-text system may further include a speed analysis unit that analyzes the user's speaking speed. The speed analysis unit may, for example, analyze the user's speaking speed and infer the user's emotions and intentions. For example, if the user's speaking speed is fast, the speed analysis unit may infer that the user is in a hurry and provide a quick response. If the user's speaking speed is slow, the speed analysis unit may infer that the user is relaxed and provide a response appropriate for that relaxed state. Furthermore, if the user's speaking speed is irregular, the speed analysis unit may infer that the user is nervous and provide a response that relieves the tension. In this way, by analyzing the user's speaking speed, the user's emotions and intentions can be inferred and an appropriate response can be provided.

[0127] The speech-to-text system may further include a content analysis unit that analyzes the content of the user's utterance. The content analysis unit may, for example, analyze the content of the user's utterance and infer the user's intentions and goals. For example, if the user says "I'm in a hurry," the content analysis unit may infer that the user is in a hurry and provide a prompt response. Also, if the user says "I want to relax," the content analysis unit may infer that the user wants to relax and provide a response appropriate for a relaxed state. Furthermore, if the user says "I'm in trouble," the content analysis unit may infer that the user is in trouble and provide appropriate support. In this way, by analyzing the content of the user's utterance, the user's intentions and goals can be inferred and an appropriate response can be provided.

[0128] The speech-to-text system may further include a context analysis unit that analyzes the context of the user's utterance. The context analysis unit may, for example, analyze the context before and after the user's utterance to infer the user's intentions and emotions. For example, if a user says "I'm in a hurry" and then "Hurry up," the context analysis unit may infer that the user is in a hurry and provide a prompt response. Alternatively, if a user says "I want to relax" and then "Play some music," the context analysis unit may infer that the user wants to relax and provide a response appropriate for a relaxed state. Furthermore, if a user says "I'm in trouble" and then "Help me," the context analysis unit may infer that the user is in trouble and provide appropriate support. Thus, by analyzing the context of the user's utterance, the user's intentions and emotions can be inferred and an appropriate response can be provided.

[0129] The speech-to-text system may further include a frequency analysis unit that analyzes the frequency of a user's utterances. The frequency analysis unit may, for example, analyze the frequency of a user's utterances and infer the user's emotions and intentions. For example, if the user's utterance frequency is high, the frequency analysis unit may infer that the user is excited and provide an appropriate response. Alternatively, if the user's utterance frequency is low, the frequency analysis unit may infer that the user is relaxed and provide a response appropriate for a relaxed state. Furthermore, if the user's utterance frequency is irregular, the frequency analysis unit may infer that the user is nervous and provide a response that relieves the tension. In this way, by analyzing the frequency of a user's utterances, the user's emotions and intentions may be inferred and an appropriate response may be provided.

[0130] The speech-to-text system may further include a summarizing unit that summarizes the content of the user's utterance. The summarizing unit may, for example, summarize the content of the user's utterance and extract important information. For example, if the user gives a long explanation, the summarizing unit may summarize the content to make it concise. In addition, if the user gives multiple instructions, the summarizing unit may summarize them into a single instruction. Furthermore, if the user makes an emotional statement, the summarizing unit may summarize the emotion and provide an appropriate response. In this way, by summarizing the content of the user's utterance, important information may be extracted and an appropriate response may be provided.

[0131] The speech-to-text system may further include an intention estimation unit that estimates the intention of the user's utterance. The intention estimation unit may, for example, analyze the content, tone, and context of the user's utterance to estimate the user's intention. For example, if the user says "I'm in a hurry," the intention estimation unit may estimate that the user is in a hurry and provide a quick response. Also, if the user says "I want to relax," the intention estimation unit may estimate that the user wants to relax and provide a response appropriate for a relaxed state. Furthermore, if the user says "I'm in trouble," the intention estimation unit may estimate that the user is in trouble and provide appropriate support. In this way, by estimating the intention of the user's utterance, an appropriate response can be provided.

[0132] The speech-to-text system may further include an emotion estimation unit that estimates the emotion of the user's speech. The emotion estimation unit may, for example, analyze the content, tone, and speed of the user's speech to estimate the user's emotion. For example, if the user is excited, the emotion estimation unit may estimate that the user is excited and provide an appropriate response. Also, if the user is relaxed, the emotion estimation unit may estimate that the user is relaxed and provide a response appropriate for the relaxed state. Furthermore, if the user is nervous, the emotion estimation unit may estimate that the user is nervous and provide a response that relieves the tension. In this way, an appropriate response can be provided by estimating the emotion of the user's speech.

[0133] The speech-to-text system may further include a background analysis unit that analyzes background information of the user's utterance. The background analysis unit may, for example, analyze the background information of the user's utterance and infer the user's intentions and emotions. For example, if the user says "I'm in a hurry," the background analysis unit may analyze the background information and infer the reason why the user is in a hurry. Furthermore, if the user says "I want to relax," the background analysis unit may analyze the background information and infer the reason why the user wants to relax. Furthermore, if the user says "I'm in trouble," the background analysis unit may analyze the background information and infer the reason why the user is in trouble. In this way, by analyzing the background information of the user's utterance, the user's intentions and emotions can be inferred and an appropriate response can be provided.

[0134] The speech-to-text system may further include a pattern analysis unit that analyzes the user's speech pattern. The pattern analysis unit may, for example, analyze the user's speech pattern and infer the user's intention or emotion. For example, if the user speaks in a specific pattern, the pattern analysis unit may analyze the pattern and infer the user's intention. Also, if the user speaks with a specific emotion, the pattern analysis unit may analyze the pattern and infer the user's emotion. Furthermore, if the user's speech pattern changes, the pattern analysis unit may analyze the change and infer the change in the user's intention or emotion. In this way, by analyzing the user's speech pattern, the user's intention or emotion can be inferred and an appropriate response can be provided.

[0135] The processing flow of the second embodiment will be briefly explained below.

[0136] Step 1: The conversion unit converts the voice into text. For example, the conversion unit analyzes the voice data and converts it into text using voice recognition technology. Voice data can also be converted into text using generation AI. Step 2: The storage unit stores the text converted by the conversion unit. For example, the storage unit stores the text data in a database, cloud storage, or local storage. Step 3: The reception unit receives a voice command. The reception unit, for example, analyzes the voice command and issues an instruction to operate a device or send a text message. Step 4: The operation unit operates the device based on the voice command received by the reception unit. For example, the operation unit plays music or turns on a light based on the voice command.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0139] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0142] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0158] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0164] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0165] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0167] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0174] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0175] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0176] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0177] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0179] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0180] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0181] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0182] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0183] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0184] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0185] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0187] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0189] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0190] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0191] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0192] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0193] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0194] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0195] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0196] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0197] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0198] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0199] 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.

[0200] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0201] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0202] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0203] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0204] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0205] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0206] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0207] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0208] [Explanation of symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a converter for converting speech to text; a storage unit for storing the text converted by the conversion unit; a reception unit that receives a voice command; an operation unit that operates a device based on the voice command received by the reception unit; A system characterized by:

2. Equipped with a pre-processing unit that pre-processes audio data 2. The system of claim 1.

3. Equipped with an analysis unit to improve the accuracy of voice recognition 2. The system of claim 1.

4. A sending unit is provided for sending the converted text as a message.

2. The system of claim 1.

5. The conversion unit Convert speech to text 2. The system of claim 1.

6. The storage unit Save the converted text 2. The system of claim 1.

7. The reception unit Accept voice commands 2. The system of claim 1.

8. The operation unit includes: Control your device based on voice commands 2. The system of claim 1.

9. The conversion unit Estimate the user's emotions and adjust the speech conversion accuracy based on the estimated user emotions.

2. The system of claim 1.

Images