system

Abstract

The system according to this embodiment aims to summon a voice assistant without using specific keywords. [Solution] The system according to the embodiment comprises a monitoring unit, an analysis unit, a detection unit, and an execution unit. The monitoring unit constantly monitors the audio. The analysis unit analyzes the audio monitored by the monitoring unit. The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. The execution unit performs an action based on the instructions detected by the detection unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is necessary to use a specific keyword to call a voice assistant, which is troublesome for users.

[0005] The system according to the embodiment aims to call a voice assistant without using a specific keyword.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a monitoring unit, an analysis unit, a detection unit, and an execution unit. The monitoring unit continuously monitors audio. The analysis unit analyzes the audio monitored by the monitoring unit. The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. The execution unit performs actions based on the instructions detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can invoke a voice assistant without using specific keywords. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage �2. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The voice assistant system according to an embodiment of the present invention is a system that eliminates the need to call out to the voice assistant and automatically detects when the voice assistant is being spoken to based on the content of the conversation. The voice assistant system allows the user to give instructions to the voice assistant without using a specific calling phrase. For example, if the user simply says, "Set a timer for 3 minutes," the voice assistant will automatically respond and start the timer. This mechanism eliminates the need for the user to call out to the voice assistant in anger and allows for a quick response in emergencies. First, the voice assistant constantly monitors the audio and analyzes the content of the conversation. Next, it determines from the analyzed content whether an instruction for the voice assistant is included. For example, if the user says, "Set a timer for 3 minutes," the voice assistant detects this instruction and starts the timer. In this case, there is no need to use a specific calling phrase. This mechanism allows the user to give instructions to the voice assistant in a natural conversation, making it easy to operate. It also improves user convenience by allowing for a quick response in emergencies. For example, even if your hands are busy while cooking, you can start the timer simply by saying, "Set a timer for 3 minutes." Furthermore, this mechanism includes technology for the voice assistant to accurately understand the user's intentions and take appropriate action. For example, a voice assistant can analyze the tone and context of the user's voice to determine the urgency of the instruction. This allows the voice assistant to respond quickly and provide appropriate assistance when the user says "help" in an emergency. Thus, the present invention eliminates the need to call out to the voice assistant and provides a mechanism that automatically detects when the voice assistant is being spoken to based on the content of the conversation. This allows the user to give instructions to the voice assistant in a natural conversation, making it easy to operate and enabling a quick response in emergencies. As a result, the voice assistant system can quickly and accurately detect the user's instructions and take appropriate action.

[0029] The voice assistant system according to this embodiment comprises a monitoring unit, an analysis unit, a detection unit, and an execution unit. The monitoring unit continuously monitors voice. For example, the monitoring unit monitors voice in real time and constantly captures the user's speech. The monitoring unit can also perform periodic sampling and collect voice data. For example, the monitoring unit samples voice data every second and transmits it to the analysis unit. The analysis unit analyzes the voice monitored by the monitoring unit. For example, the analysis unit converts the voice data into text data using speech recognition technology. The analysis unit can also analyze the content of the voice data using natural language processing technology. For example, the analysis unit converts the voice data into text data and analyzes the text data to extract instructions. The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. For example, the detection unit detects instructions by detecting specific keywords. The detection unit can also perform contextual analysis to understand the intent of the instructions. For example, the detection unit detects the instruction "set a timer for 3 minutes" and starts the timer. The execution unit performs actions based on instructions detected by the detection unit. For example, the execution unit can operate home appliances. The execution unit can also provide information. For example, the execution unit can start a timer and sound an alarm after 3 minutes. This eliminates the need to call out to the voice assistant system according to the embodiment, and allows the voice assistant to automatically detect from the content of the conversation that it is being spoken to. Some or all of the above-described processes in the monitoring unit, analysis unit, detection unit, and execution unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input voice data into the AI ​​and monitor the voice in real time. The analysis unit can input voice data into the AI ​​and perform speech recognition and natural language processing. The detection unit can input the analyzed text data into the AI ​​and detect instructions. The execution unit can input the detected instructions into the AI ​​and perform actions.

[0030] The monitoring unit continuously monitors audio. For example, it monitors audio in real time and constantly captures user speech. Specifically, the monitoring unit uses high-sensitivity microphones to collect ambient sound and noise cancellation technology to remove environmental noise. This allows for clear capture of user speech. The monitoring unit can also collect audio data by performing periodic sampling. For example, the monitoring unit samples audio data every second and sends it to the analysis unit. The sampled audio data is efficiently transmitted using compression technology, minimizing the amount of data. Furthermore, the monitoring unit can optimize the audio signal using adaptive filtering technology to maintain the quality of the audio data. This allows the monitoring unit to consistently collect and provide high-quality audio data to the analysis unit. The monitoring unit can also monitor audio data in real time using AI. For example, the monitoring unit can input audio data into AI to detect specific speech patterns and keywords. This allows for rapid capture of user speech and transmission to the analysis unit. The monitoring unit can also implement sound source localization technology using multiple microphones to pinpoint the user's location. This allows for prioritizing monitoring of a specific user's messages, even when multiple users are speaking simultaneously.

[0031] The analysis unit analyzes the audio monitored by the monitoring unit. For example, the analysis unit converts audio data into text data using speech recognition technology. Specifically, the analysis unit uses a deep learning-based speech recognition model to achieve highly accurate speech recognition. The speech recognition model is pre-trained using a large amount of audio data and can handle various accents and speaking styles. The analysis unit can also analyze the content of the audio data using natural language processing technology. For example, the analysis unit converts audio data into text data and then analyzes that text data to extract instructions. Natural language processing techniques include tokenization, part-of-speech tagging, and dependency analysis, which are combined to understand the meaning of the audio data. The analysis unit can also analyze audio data using AI. For example, the analysis unit can input audio data into AI for speech recognition and natural language processing. The AI ​​can understand the context of the audio data and accurately grasp the user's intent. Furthermore, based on the analysis results of the audio data, the analysis unit can infer the intent of the user's statements and generate appropriate responses. This allows the analysis unit to quickly and accurately analyze user statements and improve the overall system response performance.

[0032] The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. For example, the detection unit detects instructions by detecting specific keywords. Specifically, the detection unit matches the analyzed text data with a pre-set keyword list and detects matching keywords. The detection unit can also perform contextual analysis to understand the intent of the instructions. For example, the detection unit detects the instruction "set a timer for 3 minutes" and starts the timer. Contextual analysis includes techniques that use natural language processing to understand the meaning of text data and accurately grasp the user's intent. The detection unit can also analyze the analyzed text data using AI to detect instructions. For example, the detection unit can input the analyzed text data into the AI ​​to understand the intent of the instructions. The AI ​​can infer the user's intent based on past data and the user's speech history and detect appropriate instructions. Furthermore, if multiple instructions are detected simultaneously, the detection unit can set priorities and execute the most important instruction first. This allows the detection unit to accurately and quickly detect instructions from user speech and improve the overall response performance of the system.

[0033] The execution unit performs actions based on instructions detected by the detection unit. For example, the execution unit can operate home appliances. Specifically, it can work with smart home devices to turn lights on and off, adjust air conditioner temperatures, change TV channels, and so on. The execution unit can also provide information. For example, it can start a timer and sound an alarm after 3 minutes. Furthermore, based on user instructions, the execution unit can provide information such as weather forecasts, news broadcasts, and calendar schedule checks. The execution unit can also analyze detected instructions using AI and perform the optimal action. For example, the execution unit can input detected instructions into the AI ​​and perform the action. The AI ​​can recommend and perform the optimal action based on past data and user preferences. Furthermore, the execution unit can perform multiple actions simultaneously. For example, if a user instructs, "Turn off the lights and turn on the air conditioner," the execution unit can simultaneously turn off the lights and turn on the air conditioner. This allows the execution unit to perform actions quickly and accurately based on user instructions, improving the overall convenience of the system.

[0034] The tone analysis unit can analyze the tone and context of the user's voice. For example, the tone analysis unit can analyze the pitch and volume of the voice. For instance, the tone analysis unit can analyze the tone of the user's voice and detect changes in emotion. The tone analysis unit can also analyze the content of preceding and succeeding statements in order to analyze context. For example, the tone analysis unit can analyze the context before and after the user's statement to understand the intent of the statement. Furthermore, the tone analysis unit can also analyze related topics. For example, the tone analysis unit can analyze keywords used in the user's statement and identify related topics. As a result, by analyzing the tone and context of the user's voice, the tone analysis unit can enable the voice assistant to understand the user's intent more accurately. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input voice data into AI to analyze the pitch and volume of the voice.

[0035] The emergency response unit can respond quickly in emergencies. For example, the emergency response unit can detect emergencies by detecting specific keywords. For example, the emergency response unit can detect the keyword "help" and respond quickly. The emergency response unit can also analyze the tone of voice to determine the degree of urgency. For example, if the tone of the user's voice is raised, the emergency response unit will determine it is an emergency and respond quickly. Furthermore, the emergency response unit can analyze the context to understand the intent of the emergency. For example, the emergency response unit can analyze the context before and after the user's statement to identify the intent of the emergency. As a result, the emergency response unit can ensure the user's safety by responding quickly in emergencies. Some or all of the above processes in the emergency response unit may be performed using AI, for example, or not. For example, the emergency response unit can input voice data into AI to detect emergencies.

[0036] The analysis unit can analyze the tone and context of the user's voice to determine the urgency of the instructions. For example, the analysis unit can analyze the tone of voice to determine the urgency. For instance, if the user's voice tone is high, the analysis unit will determine that the urgency is high. The analysis unit can also analyze the context to determine the urgency. For example, the analysis unit can analyze the context before and after the user's statement to determine the urgency. Furthermore, the analysis unit can detect specific keywords to determine the urgency. For example, if the analysis unit detects the keyword "help," it will determine that the urgency is high. In this way, the analysis unit can determine the urgency of the instructions by analyzing the tone and context of the user's voice and take appropriate action. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input voice data into AI to analyze the tone and context of the voice.

[0037] The execution unit can respond quickly and provide appropriate assistance when a user says "help." For example, the execution unit can detect the keyword "help" and respond quickly. For example, the execution unit can detect the instruction "help" and notify emergency contacts. The execution unit can also provide instructions for first aid. For example, the execution unit can guide the user through first aid procedures. Furthermore, the execution unit can execute emergency response procedures. For example, the execution unit can provide appropriate assistance by following emergency response procedures. In this way, the execution unit can respond quickly and provide appropriate assistance when a user says "help," enabling emergency response. Some or all of the above processing in the execution unit may be performed using AI, for example, or not using AI. For example, the execution unit can input voice data into AI, detect the instruction "help," and provide appropriate assistance.

[0038] The monitoring unit can learn the user's past voice patterns and prioritize monitoring specific voice patterns. For example, the monitoring unit can learn phrases that the user frequently uses and prioritize monitoring when those phrases are uttered. For example, the monitoring unit can analyze past voice data and learn specific phrases. The monitoring unit can also learn phrases used during specific time periods from the user's past voice patterns and prioritize monitoring during those time periods. For example, the monitoring unit can analyze past voice data and learn phrases used during specific time periods. The monitoring unit can also analyze the user's past voice patterns and prioritize monitoring phrases used in specific emotional states. For example, the monitoring unit can analyze past voice data and learn phrases used in specific emotional states. In this way, the monitoring unit can prioritize monitoring specific voice patterns by learning the user's past voice patterns. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past voice data into a generating AI and have it learn specific voice patterns.

[0039] The monitoring unit can filter ambient noise and monitor only the user's voice. For example, the monitoring unit can remove background noise and extract and monitor only the user's voice. For example, the monitoring unit can remove background noise using noise cancellation technology. The monitoring unit can also filter specific frequency bands from ambient noise and prioritize monitoring of the user's voice. For example, the monitoring unit filters specific frequency bands and extracts the user's voice. The monitoring unit can also analyze fluctuations in ambient noise in real time and effectively extract and monitor the user's voice. For example, the monitoring unit analyzes fluctuations in ambient noise and extracts the user's voice. As a result, the monitoring unit can monitor only the user's voice by filtering ambient noise. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input ambient noise data into a generating AI and extract the user's voice.

[0040] The monitoring unit can prioritize monitoring audio at specific locations by taking into account the user's geographical location information. For example, if the user is at home, the monitoring unit can prioritize monitoring instructions within the home. For example, the monitoring unit can acquire geographical location information and detect that the user is at home. If the user is at the office, the monitoring unit can also prioritize monitoring work-related instructions. For example, the monitoring unit can acquire geographical location information and detect that the user is at the office. If the user is out, the monitoring unit can also prioritize monitoring urgent instructions. For example, the monitoring unit can acquire geographical location information and detect that the user is out. This allows the monitoring unit to prioritize monitoring audio at specific locations by taking into account the user's geographical location information. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input geographical location information into a generating AI and prioritize monitoring audio at specific locations.

[0041] The monitoring unit can analyze a user's social media activity and prioritize monitoring relevant audio. For example, the monitoring unit can prioritize monitoring phrases that a user frequently uses on social media. For example, the monitoring unit can analyze social media posts and detect specific phrases. The monitoring unit can also prioritize monitoring audio related to specific events from a user's social media activity. For example, the monitoring unit can analyze social media posts and detect audio related to specific events. The monitoring unit can also analyze a user's social media activity and prioritize monitoring audio related to specific topics. For example, the monitoring unit can analyze social media posts and detect audio related to specific topics. In this way, the monitoring unit can prioritize monitoring relevant audio by analyzing a user's social media activity. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input social media data into a generating AI and prioritize monitoring relevant audio.

[0042] The analysis unit can remove background noise from the audio and analyze clear audio data. For example, the analysis unit can remove background noise and extract and analyze only the user's voice. For example, the analysis unit can remove background noise using noise cancellation technology. The analysis unit can also filter specific frequency bands from ambient noise and prioritize the analysis of the user's voice. For example, the analysis unit filters specific frequency bands and extracts the user's voice. The analysis unit can also analyze fluctuations in ambient noise in real time and effectively extract and analyze the user's voice. For example, the analysis unit analyzes fluctuations in ambient noise and extracts the user's voice. As a result, the analysis unit can analyze clear audio data by removing background noise from the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input ambient sound data into a generating AI and extract the user's voice.

[0043] The analysis unit can refer to the user's past utterance history to more accurately analyze the intent of a utterance. For example, the analysis unit can analyze the intent of a utterance based on phrases the user has used in the past. For example, the analysis unit can analyze past utterance data and detect specific phrases. The analysis unit can also analyze the intent in a specific context from the user's past utterance history. For example, the analysis unit can analyze past utterance data and identify the intent in a specific context. The analysis unit can also analyze the intent in a specific emotional state by analyzing the user's past utterance history. For example, the analysis unit can analyze past utterance data and identify the intent in a specific emotional state. As a result, the analysis unit can more accurately analyze the intent of a utterance by referring to the user's past utterance history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past utterance data into a generating AI and analyze the intent of the utterance.

[0044] The analysis unit can prioritize the analysis of voices from specific locations by taking into account the user's geographical location information. For example, if the user is at home, the analysis unit will prioritize the analysis of instructions within the home. For example, the analysis unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the analysis unit can also prioritize the analysis of work-related instructions. For example, the analysis unit will acquire geographical location information and detect that the user is at the office. If the user is out, the analysis unit can also prioritize the analysis of urgent instructions. For example, the analysis unit will acquire geographical location information and detect that the user is out. This allows the analysis unit to prioritize the analysis of voices from specific locations by taking into account the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical location information into a generating AI and prioritize the analysis of voices from specific locations.

[0045] The analysis unit can analyze a user's social media activity and prioritize the analysis of relevant audio. For example, the analysis unit can prioritize the analysis of phrases that the user frequently uses on social media. For example, the analysis unit can analyze the content of social media posts and detect specific phrases. The analysis unit can also prioritize the analysis of audio related to specific events from the user's social media activity. For example, the analysis unit can analyze the content of social media posts and detect audio related to specific events. The analysis unit can also analyze a user's social media activity and prioritize the analysis of audio related to specific topics. For example, the analysis unit can analyze the content of social media posts and detect audio related to specific topics. In this way, the analysis unit can prioritize the analysis of relevant audio by analyzing the user's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input social media data into a generating AI and prioritize the analysis of relevant audio.

[0046] The detection unit can refer to the user's past instruction history and prioritize the detection of specific instructions. For example, the detection unit can prioritize the detection of instructions that the user has frequently used in the past. For example, the detection unit can analyze past instruction data and detect specific instructions. The detection unit can also prioritize the detection of instructions used during specific time periods from the user's past instruction history. For example, the detection unit can analyze past instruction data and detect instructions used during specific time periods. The detection unit can also analyze the user's past instruction history and prioritize the detection of instructions used in specific emotional states. For example, the detection unit can analyze past instruction data and detect instructions used in specific emotional states. In this way, the detection unit can prioritize the detection of specific instructions by referring to the user's past instruction history. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input past instruction data into a generating AI and detect specific instructions.

[0047] The detection unit can analyze the context of the audio and more accurately detect the intent of the instruction. For example, the detection unit can analyze the context before and after the user's utterance to accurately detect the intent of the instruction. For example, the detection unit analyzes the audio data to identify the context. The detection unit can also analyze keywords used in the user's utterance to accurately detect the intent of the instruction. For example, the detection unit analyzes the audio data to detect specific keywords. The detection unit can also analyze the tone and emotion of the user's utterance to accurately detect the intent of the instruction. For example, the detection unit analyzes the audio data to estimate the user's emotion. As a result, the detection unit can more accurately detect the intent of the instruction by analyzing the context of the audio. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input audio data into a generating AI to analyze the context.

[0048] The detection unit can prioritize detecting instructions for specific locations by taking into account the user's geographical location information. For example, if the user is at home, the detection unit will prioritize detecting instructions within the home. For example, the detection unit will acquire geographical location information and detect that the user is at home. The detection unit can also prioritize detecting work-related instructions if the user is at the office. For example, the detection unit will acquire geographical location information and detect that the user is at the office. The detection unit can also prioritize detecting urgent instructions if the user is out. For example, the detection unit will acquire geographical location information and detect that the user is out. In this way, the detection unit can prioritize detecting instructions for specific locations by taking into account the user's geographical location information. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input geographical location information into a generating AI and prioritize detecting instructions for specific locations.

[0049] The detection unit can analyze a user's social media activity and prioritize the detection of relevant instructions. For example, the detection unit can prioritize the detection of phrases that the user frequently uses on social media. For example, the detection unit can analyze the content of social media posts and detect specific phrases. The detection unit can also prioritize the detection of instructions related to specific events from a user's social media activity. For example, the detection unit can analyze the content of social media posts and detect instructions related to specific events. The detection unit can also analyze a user's social media activity and prioritize the detection of instructions related to specific topics. For example, the detection unit can analyze the content of social media posts and detect instructions related to specific topics. In this way, the detection unit can prioritize the detection of relevant instructions by analyzing a user's social media activity. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input social media data into a generating AI and prioritize the detection of relevant instructions.

[0050] The execution unit can refer to the user's past action history and prioritize the execution of specific actions. For example, the execution unit can prioritize actions that the user has frequently performed in the past. For example, the execution unit can analyze past action data and detect specific actions. The execution unit can also prioritize actions performed during specific time periods based on the user's past action history. For example, the execution unit can analyze past action data and detect actions performed during specific time periods. The execution unit can also analyze the user's past action history and prioritize actions performed during specific emotional states. For example, the execution unit can analyze past action data and detect actions performed during specific emotional states. In this way, the execution unit can prioritize the execution of specific actions by referring to the user's past action history. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input past action data into a generating AI and execute a specific action.

[0051] The execution unit can analyze the context of the speech and execute the intent of the action more accurately. For example, the execution unit can analyze the context before and after the user's utterance and execute the intent of the action accurately. For example, the execution unit can analyze the speech data and identify the surrounding context. The execution unit can also analyze keywords used in the user's utterance and execute the intent of the action accurately. For example, the execution unit can analyze the speech data and detect specific keywords. The execution unit can also analyze the tone and emotion of the user's utterance and execute the intent of the action accurately. For example, the execution unit can analyze the speech data and estimate the user's emotion. As a result, the execution unit can execute the intent of the action more accurately by analyzing the context of the speech. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input speech data into a generating AI and analyze the context.

[0052] The execution unit can prioritize actions performed in specific locations by considering the user's geographical location. For example, if the user is at home, the execution unit will prioritize actions performed within the home. For example, the execution unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the execution unit can also prioritize work-related actions. For example, the execution unit will acquire geographical location information and detect that the user is at the office. If the user is out, the execution unit can also prioritize urgent actions. For example, the execution unit will acquire geographical location information and detect that the user is out. This allows the execution unit to prioritize actions performed in specific locations by considering the user's geographical location. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input geographical location information into a generating AI and prioritize actions performed in specific locations.

[0053] The execution unit can analyze the user's social media activity and prioritize the execution of relevant actions. For example, the execution unit can prioritize actions related to phrases that the user frequently uses on social media. For example, the execution unit can analyze social media posts and detect specific phrases. The execution unit can also prioritize actions related to specific events from the user's social media activity. For example, the execution unit can analyze social media posts and detect actions related to specific events. The execution unit can also analyze the user's social media activity and prioritize the execution of actions related to specific topics. For example, the execution unit can analyze social media posts and detect actions related to specific topics. In this way, the execution unit can prioritize the execution of relevant actions by analyzing the user's social media activity. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input social media data into a generating AI and prioritize the execution of relevant actions.

[0054] The tone analysis unit can learn the user's past voice tones and prioritize the analysis of specific tones. For example, the tone analysis unit can prioritize the analysis of tones that the user has frequently used in the past. For example, the tone analysis unit can analyze past audio data and detect specific tones. The tone analysis unit can also prioritize the analysis of tones used during specific time periods from the user's past voice tones. For example, the tone analysis unit can analyze past audio data and detect tones used during specific time periods. The tone analysis unit can also analyze the user's past voice tones and prioritize the analysis of tones used in specific emotional states. For example, the tone analysis unit can analyze past audio data and detect tones used in specific emotional states. In this way, the tone analysis unit can prioritize the analysis of specific tones by learning the user's past voice tones. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input past audio data into a generating AI and analyze specific tones.

[0055] The tone analysis unit can analyze the context of speech and more accurately analyze the intent of the tone. For example, the tone analysis unit can analyze the context before and after the user's utterance and accurately analyze the intent of the tone. For example, the tone analysis unit analyzes the audio data and identifies the context. The tone analysis unit can also analyze keywords used in the user's utterance and accurately analyze the intent of the tone. For example, the tone analysis unit analyzes the audio data and detects specific keywords. The tone analysis unit can also analyze the tone and emotion of the user's utterance and accurately analyze the intent of the tone. For example, the tone analysis unit analyzes the audio data and estimates the user's emotion. As a result, the tone analysis unit can more accurately analyze the intent of the tone by analyzing the context of speech. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input audio data into a generating AI and analyze the context.

[0056] The tone analysis unit can prioritize the analysis of tones in specific locations by taking into account the user's geographical location information. For example, if the user is at home, the tone analysis unit will prioritize the analysis of tones within the home. For example, the tone analysis unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the tone analysis unit can also prioritize the analysis of work-related tones. For example, the tone analysis unit will acquire geographical location information and detect that the user is at the office. If the user is out, the tone analysis unit can also prioritize the analysis of urgent tones. For example, the tone analysis unit will acquire geographical location information and detect that the user is out. In this way, the tone analysis unit can prioritize the analysis of tones in specific locations by taking into account the user's geographical location information. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input geographical location information into a generating AI and prioritize the analysis of tones in specific locations.

[0057] The tone analysis unit can analyze a user's social media activity and prioritize the analysis of relevant tones. For example, the tone analysis unit can prioritize the analysis of tones that the user frequently uses on social media. For example, the tone analysis unit can analyze the content of social media posts and detect specific tones. The tone analysis unit can also prioritize the analysis of tones related to specific events from the user's social media activity. For example, the tone analysis unit can analyze the content of social media posts and detect tones related to specific events. The tone analysis unit can also analyze a user's social media activity and prioritize the analysis of tones related to specific topics. For example, the tone analysis unit can analyze the content of social media posts and detect tones related to specific topics. In this way, the tone analysis unit can prioritize the analysis of relevant tones by analyzing the user's social media activity. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input social media data into a generating AI and prioritize the analysis of relevant tones.

[0058] The emergency response unit can refer to the user's past emergency history and prioritize responding to specific emergencies. For example, the emergency response unit prioritizes responses based on emergencies the user has experienced in the past. For example, the emergency response unit analyzes past emergency data to detect specific emergencies. The emergency response unit can also prioritize responding to emergencies that occur during specific time periods based on the user's past emergency history. For example, the emergency response unit analyzes past emergency data to detect emergencies that occur during specific time periods. The emergency response unit can also analyze the user's past emergency history and prioritize responding to emergencies that occur during specific emotional states. For example, the emergency response unit analyzes past emergency data to detect emergencies that occur during specific emotional states. In this way, the emergency response unit can prioritize responding to specific emergencies by referring to the user's past emergency history. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or without AI. For example, the emergency response unit can input past emergency data into a generating AI to detect specific emergencies.

[0059] The emergency response unit can analyze the context of speech to respond more accurately to the intent of an emergency. For example, the emergency response unit can analyze the context before and after a user's utterance to respond accurately to the intent of an emergency. For example, the emergency response unit can analyze speech data to identify the context. The emergency response unit can also analyze keywords used in a user's utterance to respond accurately to the intent of an emergency. For example, the emergency response unit can analyze speech data to detect specific keywords. The emergency response unit can also analyze the tone and emotion of a user's utterance to respond accurately to the intent of an emergency. For example, the emergency response unit can analyze speech data to estimate the user's emotion. This allows the emergency response unit to respond more accurately to the intent of an emergency by analyzing the context of speech. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or without AI. For example, the emergency response unit can input speech data into a generating AI to analyze the context.

[0060] The emergency response unit can prioritize responding to emergencies in specific locations by considering the user's geographical location. For example, if the user is at home, the emergency response unit will prioritize responding to emergencies within the home. For example, the emergency response unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the emergency response unit can also prioritize responding to work-related emergencies. For example, the emergency response unit will acquire geographical location information and detect that the user is at the office. If the user is out, the emergency response unit can also prioritize responding to urgent emergencies. For example, the emergency response unit will acquire geographical location information and detect that the user is out. In this way, the emergency response unit can prioritize responding to emergencies in specific locations by considering the user's geographical location. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or not using AI. For example, the emergency response unit can input geographical location information into a generating AI and prioritize responding to emergencies in specific locations.

[0061] The emergency response unit can analyze users' social media activity and prioritize responses to relevant emergencies. For example, the emergency response unit can prioritize responses to emergencies related to phrases that users frequently use on social media. For example, the emergency response unit can analyze social media posts and detect specific phrases. The emergency response unit can also prioritize responses to emergencies related to specific events based on users' social media activity. For example, the emergency response unit can analyze social media posts and detect emergencies related to specific events. The emergency response unit can also analyze users' social media activity and prioritize responses to emergencies related to specific topics. For example, the emergency response unit can analyze social media posts and detect emergencies related to specific topics. In this way, the emergency response unit can prioritize responses to relevant emergencies by analyzing users' social media activity. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or not using AI. For example, the emergency response unit can input social media data into a generating AI and prioritize responses to relevant emergencies.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The voice assistant system can also include a health monitoring unit that monitors the user's health status. The health monitoring unit, for example, measures the user's heart rate and blood pressure and notifies the voice assistant if an abnormality is detected. For instance, if the user's heart rate suddenly increases, the health monitoring unit notifies the voice assistant and encourages the user to rest. The health monitoring unit can also analyze the user's sleep patterns and suggest appropriate sleep durations. For example, if the user is not getting enough sleep, the voice assistant suggests going to bed earlier. Furthermore, the health monitoring unit can record the user's diet and evaluate nutritional balance. For example, if the user is consistently eating an unbalanced diet, the voice assistant suggests a balanced diet. In this way, the voice assistant system can support the user's health management by monitoring their health status and providing appropriate advice.

[0064] The voice assistant system can also include a schedule management unit to manage the user's schedule. This unit can, for example, synchronize the user's calendar and automatically update appointments. For instance, it can add new appointments based on the user's voice commands. If the user says, "Set up a meeting for 3pm tomorrow," the schedule management unit will detect the command and add the meeting to the calendar. The schedule management unit can also set reminders based on the user's schedule. For example, if the user says, "Remind me so I don't forget tomorrow's meeting," the schedule management unit will set a reminder. Furthermore, the schedule management unit can suggest optimal time management based on the user's schedule. For example, if the user says, "Optimize my schedule for this week," the schedule management unit will analyze the user's schedule and suggest an efficient schedule. This allows the schedule management unit to efficiently manage the user's schedule and support effective time management.

[0065] The voice assistant system can also be equipped with a learning support unit to further assist the user's learning. This unit can, for example, monitor the user's learning progress and suggest an appropriate learning plan. For instance, if the user says, "I want to start studying for the next exam," the unit can create a learning plan. The unit can also provide quizzes and practice problems based on the user's learning content. For example, if the user says, "Give me a math problem," the unit will provide an appropriate problem. Furthermore, the unit can suggest learning materials tailored to the user's learning style. For example, if the user says, "I want to learn through videos," the unit will suggest video materials. This allows the learning support unit to effectively support the user's learning and improve learning outcomes.

[0066] The voice assistant system can also be equipped with a hobby support unit to further assist the user's hobbies. This unit can, for example, provide information related to the user's hobbies. For instance, if the user says, "Tell me some gardening tips," the hobby support unit will provide information about gardening. The hobby support unit can also notify the user of events related to their hobbies. For example, if the user says, "When is the next gardening event?", the hobby support unit will provide event information. Furthermore, the hobby support unit can introduce the user to communities related to their hobbies. For example, if the user says, "I want to find gardening friends," the hobby support unit will introduce relevant communities. In this way, the hobby support unit can support the user's hobbies and enrich their hobby activities.

[0067] The voice assistant system can also include a travel support unit to assist the user's travels. This unit can, for example, create travel plans and suggest optimal travel itineraries. For instance, if a user says, "I want to plan a trip for my next vacation," the travel support unit will create a travel plan. The travel support unit can also provide information about the user's travel destination. For example, if a user says, "Tell me about tourist attractions in Paris," the travel support unit will provide information about tourist attractions. Furthermore, the travel support unit can provide support during the user's trip. For example, if a user says, "Tell me the time of the next train," the travel support unit will provide a train timetable. In this way, the travel support unit can support the user's travels and provide a comfortable travel experience.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The monitoring unit continuously monitors the audio. For example, the monitoring unit monitors the audio in real time and constantly captures the user's speech. The monitoring unit can also perform periodic sampling and collect audio data. For example, the monitoring unit samples audio data every second and sends it to the analysis unit. Step 2: The analysis unit analyzes the audio monitored by the monitoring unit. The analysis unit converts the audio data into text data, for example, using speech recognition technology. The analysis unit can also analyze the content of the audio data using natural language processing technology. For example, the analysis unit converts the audio data into text data and then analyzes that text data to extract instructions. Step 3: The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. The detection unit detects instructions, for example, by detecting specific keywords. The detection unit can also perform contextual analysis to understand the intent of the instructions. For example, the detection unit detects the instruction "set a timer for 3 minutes" and starts the timer. Step 4: The execution unit performs an action based on the instructions detected by the detection unit. The execution unit can, for example, operate a home appliance. The execution unit can also provide information. For example, the execution unit can start a timer and sound an alarm after 3 minutes.

[0070] (Example of form 2) The voice assistant system according to an embodiment of the present invention is a system that eliminates the need to call out to the voice assistant and automatically detects when the voice assistant is being spoken to based on the content of the conversation. The voice assistant system allows the user to give instructions to the voice assistant without using a specific calling phrase. For example, if the user simply says, "Set a timer for 3 minutes," the voice assistant will automatically respond and start the timer. This mechanism eliminates the need for the user to call out to the voice assistant in anger and allows for a quick response in emergencies. First, the voice assistant constantly monitors the audio and analyzes the content of the conversation. Next, it determines from the analyzed content whether an instruction for the voice assistant is included. For example, if the user says, "Set a timer for 3 minutes," the voice assistant detects this instruction and starts the timer. In this case, there is no need to use a specific calling phrase. This mechanism allows the user to give instructions to the voice assistant in a natural conversation, making it easy to operate. It also improves user convenience by allowing for a quick response in emergencies. For example, even if your hands are busy while cooking, you can start the timer simply by saying, "Set a timer for 3 minutes." Furthermore, this mechanism includes technology for the voice assistant to accurately understand the user's intentions and take appropriate action. For example, a voice assistant can analyze the tone and context of the user's voice to determine the urgency of the instruction. This allows the voice assistant to respond quickly and provide appropriate assistance when the user says "help" in an emergency. Thus, the present invention eliminates the need to call out to the voice assistant and provides a mechanism that automatically detects when the voice assistant is being spoken to based on the content of the conversation. This allows the user to give instructions to the voice assistant in a natural conversation, making it easy to operate and enabling a quick response in emergencies. As a result, the voice assistant system can quickly and accurately detect the user's instructions and take appropriate action.

[0071] The voice assistant system according to this embodiment comprises a monitoring unit, an analysis unit, a detection unit, and an execution unit. The monitoring unit continuously monitors voice. For example, the monitoring unit monitors voice in real time and constantly captures the user's speech. The monitoring unit can also perform periodic sampling and collect voice data. For example, the monitoring unit samples voice data every second and transmits it to the analysis unit. The analysis unit analyzes the voice monitored by the monitoring unit. For example, the analysis unit converts the voice data into text data using speech recognition technology. The analysis unit can also analyze the content of the voice data using natural language processing technology. For example, the analysis unit converts the voice data into text data and analyzes the text data to extract instructions. The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. For example, the detection unit detects instructions by detecting specific keywords. The detection unit can also perform contextual analysis to understand the intent of the instructions. For example, the detection unit detects the instruction "set a timer for 3 minutes" and starts the timer. The execution unit performs actions based on instructions detected by the detection unit. For example, the execution unit can operate home appliances. The execution unit can also provide information. For example, the execution unit can start a timer and sound an alarm after 3 minutes. This eliminates the need to call out to the voice assistant system according to the embodiment, and allows the voice assistant to automatically detect from the content of the conversation that it is being spoken to. Some or all of the above-described processes in the monitoring unit, analysis unit, detection unit, and execution unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input voice data into the AI ​​and monitor the voice in real time. The analysis unit can input voice data into the AI ​​and perform speech recognition and natural language processing. The detection unit can input the analyzed text data into the AI ​​and detect instructions. The execution unit can input the detected instructions into the AI ​​and perform actions.

[0072] The monitoring unit continuously monitors audio. For example, it monitors audio in real time and constantly captures user speech. Specifically, the monitoring unit uses high-sensitivity microphones to collect ambient sound and noise cancellation technology to remove environmental noise. This allows for clear capture of user speech. The monitoring unit can also collect audio data by performing periodic sampling. For example, the monitoring unit samples audio data every second and sends it to the analysis unit. The sampled audio data is efficiently transmitted using compression technology, minimizing the amount of data. Furthermore, the monitoring unit can optimize the audio signal using adaptive filtering technology to maintain the quality of the audio data. This allows the monitoring unit to consistently collect and provide high-quality audio data to the analysis unit. The monitoring unit can also monitor audio data in real time using AI. For example, the monitoring unit can input audio data into AI to detect specific speech patterns and keywords. This allows for rapid capture of user speech and transmission to the analysis unit. The monitoring unit can also implement sound source localization technology using multiple microphones to pinpoint the user's location. This allows for prioritizing monitoring of a specific user's messages, even when multiple users are speaking simultaneously.

[0073] The analysis unit analyzes the audio monitored by the monitoring unit. For example, the analysis unit converts audio data into text data using speech recognition technology. Specifically, the analysis unit uses a deep learning-based speech recognition model to achieve highly accurate speech recognition. The speech recognition model is pre-trained using a large amount of audio data and can handle various accents and speaking styles. The analysis unit can also analyze the content of the audio data using natural language processing technology. For example, the analysis unit converts audio data into text data and then analyzes that text data to extract instructions. Natural language processing techniques include tokenization, part-of-speech tagging, and dependency analysis, which are combined to understand the meaning of the audio data. The analysis unit can also analyze audio data using AI. For example, the analysis unit can input audio data into AI for speech recognition and natural language processing. The AI ​​can understand the context of the audio data and accurately grasp the user's intent. Furthermore, based on the analysis results of the audio data, the analysis unit can infer the intent of the user's statements and generate appropriate responses. This allows the analysis unit to quickly and accurately analyze user statements and improve the overall system response performance.

[0074] The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. For example, the detection unit detects instructions by detecting specific keywords. Specifically, the detection unit matches the analyzed text data with a pre-set keyword list and detects matching keywords. The detection unit can also perform contextual analysis to understand the intent of the instructions. For example, the detection unit detects the instruction "set a timer for 3 minutes" and starts the timer. Contextual analysis includes techniques that use natural language processing to understand the meaning of text data and accurately grasp the user's intent. The detection unit can also analyze the analyzed text data using AI to detect instructions. For example, the detection unit can input the analyzed text data into the AI ​​to understand the intent of the instructions. The AI ​​can infer the user's intent based on past data and the user's speech history and detect appropriate instructions. Furthermore, if multiple instructions are detected simultaneously, the detection unit can set priorities and execute the most important instruction first. This allows the detection unit to accurately and quickly detect instructions from user speech and improve the overall response performance of the system.

[0075] The execution unit performs actions based on instructions detected by the detection unit. For example, the execution unit can operate home appliances. Specifically, it can work with smart home devices to turn lights on and off, adjust air conditioner temperatures, change TV channels, and so on. The execution unit can also provide information. For example, it can start a timer and sound an alarm after 3 minutes. Furthermore, based on user instructions, the execution unit can provide information such as weather forecasts, news broadcasts, and calendar schedule checks. The execution unit can also analyze detected instructions using AI and perform the optimal action. For example, the execution unit can input detected instructions into the AI ​​and perform the action. The AI ​​can recommend and perform the optimal action based on past data and user preferences. Furthermore, the execution unit can perform multiple actions simultaneously. For example, if a user instructs, "Turn off the lights and turn on the air conditioner," the execution unit can simultaneously turn off the lights and turn on the air conditioner. This allows the execution unit to perform actions quickly and accurately based on user instructions, improving the overall convenience of the system.

[0076] The tone analysis unit can analyze the tone and context of the user's voice. For example, the tone analysis unit can analyze the pitch and volume of the voice. For instance, the tone analysis unit can analyze the tone of the user's voice and detect changes in emotion. The tone analysis unit can also analyze the content of preceding and succeeding statements in order to analyze context. For example, the tone analysis unit can analyze the context before and after the user's statement to understand the intent of the statement. Furthermore, the tone analysis unit can also analyze related topics. For example, the tone analysis unit can analyze keywords used in the user's statement and identify related topics. As a result, by analyzing the tone and context of the user's voice, the tone analysis unit can enable the voice assistant to understand the user's intent more accurately. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input voice data into AI to analyze the pitch and volume of the voice.

[0077] The emergency response unit can respond quickly in emergencies. For example, the emergency response unit can detect emergencies by detecting specific keywords. For example, the emergency response unit can detect the keyword "help" and respond quickly. The emergency response unit can also analyze the tone of voice to determine the degree of urgency. For example, if the tone of the user's voice is raised, the emergency response unit will determine it is an emergency and respond quickly. Furthermore, the emergency response unit can analyze the context to understand the intent of the emergency. For example, the emergency response unit can analyze the context before and after the user's statement to identify the intent of the emergency. As a result, the emergency response unit can ensure the user's safety by responding quickly in emergencies. Some or all of the above processes in the emergency response unit may be performed using AI, for example, or not. For example, the emergency response unit can input voice data into AI to detect emergencies.

[0078] The analysis unit can analyze the tone and context of the user's voice to determine the urgency of the instructions. For example, the analysis unit can analyze the tone of voice to determine the urgency. For instance, if the user's voice tone is high, the analysis unit will determine that the urgency is high. The analysis unit can also analyze the context to determine the urgency. For example, the analysis unit can analyze the context before and after the user's statement to determine the urgency. Furthermore, the analysis unit can detect specific keywords to determine the urgency. For example, if the analysis unit detects the keyword "help," it will determine that the urgency is high. In this way, the analysis unit can determine the urgency of the instructions by analyzing the tone and context of the user's voice and take appropriate action. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input voice data into AI to analyze the tone and context of the voice.

[0079] The execution unit can respond quickly and provide appropriate assistance when a user says "help." For example, the execution unit can detect the keyword "help" and respond quickly. For example, the execution unit can detect the instruction "help" and notify emergency contacts. The execution unit can also provide instructions for first aid. For example, the execution unit can guide the user through first aid procedures. Furthermore, the execution unit can execute emergency response procedures. For example, the execution unit can provide appropriate assistance by following emergency response procedures. In this way, the execution unit can respond quickly and provide appropriate assistance when a user says "help," enabling emergency response. Some or all of the above processing in the execution unit may be performed using AI, for example, or not using AI. For example, the execution unit can input voice data into AI, detect the instruction "help," and provide appropriate assistance.

[0080] The monitoring unit can estimate the user's emotions and adjust the accuracy of voice monitoring based on the estimated emotions. For example, if the user is stressed, the monitoring unit can increase the accuracy of voice monitoring to reduce false positives. For example, the monitoring unit analyzes the voice data and estimates the user's emotions. If the user is relaxed, the monitoring unit can also return the accuracy of voice monitoring to normal and prioritize natural conversation. For example, the monitoring unit analyzes the voice data and estimates the user's emotions. If the user is in a hurry, the monitoring unit can also maximize the accuracy of voice monitoring to enable a quick response. For example, the monitoring unit analyzes the voice data and estimates the user's emotions. This allows the monitoring unit to reduce false positives by adjusting the accuracy of voice monitoring based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input voice data into a generating AI and have the AI ​​perform an estimation of the user's emotions.

[0081] The monitoring unit can learn the user's past voice patterns and prioritize monitoring specific voice patterns. For example, the monitoring unit can learn phrases that the user frequently uses and prioritize monitoring when those phrases are uttered. For example, the monitoring unit can analyze past voice data and learn specific phrases. The monitoring unit can also learn phrases used during specific time periods from the user's past voice patterns and prioritize monitoring during those time periods. For example, the monitoring unit can analyze past voice data and learn phrases used during specific time periods. The monitoring unit can also analyze the user's past voice patterns and prioritize monitoring phrases used in specific emotional states. For example, the monitoring unit can analyze past voice data and learn phrases used in specific emotional states. In this way, the monitoring unit can prioritize monitoring specific voice patterns by learning the user's past voice patterns. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past voice data into a generating AI and have it learn specific voice patterns.

[0082] The monitoring unit can filter ambient noise and monitor only the user's voice. For example, the monitoring unit can remove background noise and extract and monitor only the user's voice. For example, the monitoring unit can remove background noise using noise cancellation technology. The monitoring unit can also filter specific frequency bands from ambient noise and prioritize monitoring of the user's voice. For example, the monitoring unit filters specific frequency bands and extracts the user's voice. The monitoring unit can also analyze fluctuations in ambient noise in real time and effectively extract and monitor the user's voice. For example, the monitoring unit analyzes fluctuations in ambient noise and extracts the user's voice. As a result, the monitoring unit can monitor only the user's voice by filtering ambient noise. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input ambient noise data into a generating AI and extract the user's voice.

[0083] The monitoring unit can estimate the user's emotions and determine the priority of the audio to monitor based on the estimated user emotions. For example, if the user is tense, the monitoring unit will prioritize monitoring important instructions. For example, the monitoring unit will analyze the audio data and estimate the user's emotions. If the user is relaxed, the monitoring unit can also prioritize monitoring normal conversations. For example, the monitoring unit will analyze the audio data and estimate the user's emotions. If the user is in a hurry, the monitoring unit can also prioritize monitoring urgent instructions. For example, the monitoring unit will analyze the audio data and estimate the user's emotions. This allows the monitoring unit to prioritize monitoring important instructions by determining the priority of the audio to monitor based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input voice data into a generating AI and have the AI ​​perform an estimation of the user's emotions.

[0084] The monitoring unit can prioritize monitoring audio at specific locations by taking into account the user's geographical location information. For example, if the user is at home, the monitoring unit can prioritize monitoring instructions within the home. For example, the monitoring unit can acquire geographical location information and detect that the user is at home. If the user is at the office, the monitoring unit can also prioritize monitoring work-related instructions. For example, the monitoring unit can acquire geographical location information and detect that the user is at the office. If the user is out, the monitoring unit can also prioritize monitoring urgent instructions. For example, the monitoring unit can acquire geographical location information and detect that the user is out. This allows the monitoring unit to prioritize monitoring audio at specific locations by taking into account the user's geographical location information. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input geographical location information into a generating AI and prioritize monitoring audio at specific locations.

[0085] The monitoring unit can analyze a user's social media activity and prioritize monitoring relevant audio. For example, the monitoring unit can prioritize monitoring phrases that a user frequently uses on social media. For example, the monitoring unit can analyze social media posts and detect specific phrases. The monitoring unit can also prioritize monitoring audio related to specific events from a user's social media activity. For example, the monitoring unit can analyze social media posts and detect audio related to specific events. The monitoring unit can also analyze a user's social media activity and prioritize monitoring audio related to specific topics. For example, the monitoring unit can analyze social media posts and detect audio related to specific topics. In this way, the monitoring unit can prioritize monitoring relevant audio by analyzing a user's social media activity. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input social media data into a generating AI and prioritize monitoring relevant audio.

[0086] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit can increase the accuracy of the analysis and reduce misanalysis. For example, the analysis unit analyzes audio data and estimates the user's emotions. If the user is relaxed, the analysis unit can also return the accuracy of the analysis to normal and prioritize natural conversation. For example, the analysis unit analyzes audio data and estimates the user's emotions. If the user is in a hurry, the analysis unit can also maximize the accuracy of the analysis to enable a quick response. For example, the analysis unit analyzes audio data and estimates the user's emotions. This allows the analysis unit to reduce misanalysis by adjusting the accuracy of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI perform an estimation of the user's emotions.

[0087] The analysis unit can remove background noise from the audio and analyze clear audio data. For example, the analysis unit can remove background noise and extract and analyze only the user's voice. For example, the analysis unit can remove background noise using noise cancellation technology. The analysis unit can also filter specific frequency bands from ambient noise and prioritize the analysis of the user's voice. For example, the analysis unit filters specific frequency bands and extracts the user's voice. The analysis unit can also analyze fluctuations in ambient noise in real time and effectively extract and analyze the user's voice. For example, the analysis unit analyzes fluctuations in ambient noise and extracts the user's voice. As a result, the analysis unit can analyze clear audio data by removing background noise from the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input ambient sound data into a generating AI and extract the user's voice.

[0088] The analysis unit can refer to the user's past utterance history to more accurately analyze the intent of a utterance. For example, the analysis unit can analyze the intent of a utterance based on phrases the user has used in the past. For example, the analysis unit can analyze past utterance data and detect specific phrases. The analysis unit can also analyze the intent in a specific context from the user's past utterance history. For example, the analysis unit can analyze past utterance data and identify the intent in a specific context. The analysis unit can also analyze the intent in a specific emotional state by analyzing the user's past utterance history. For example, the analysis unit can analyze past utterance data and identify the intent in a specific emotional state. As a result, the analysis unit can more accurately analyze the intent of a utterance by referring to the user's past utterance history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past utterance data into a generating AI and analyze the intent of the utterance.

[0089] The analysis unit can estimate the user's emotions and determine the priority of the audio to be analyzed based on the estimated user emotions. For example, if the user is tense, the analysis unit will prioritize analyzing important instructions. For example, the analysis unit will analyze the audio data and estimate the user's emotions. If the user is relaxed, the analysis unit can also prioritize analyzing normal conversation. For example, the analysis unit will analyze the audio data and estimate the user's emotions. If the user is in a hurry, the analysis unit can also prioritize analyzing urgent instructions. For example, the analysis unit will analyze the audio data and estimate the user's emotions. This allows the analysis unit to prioritize analyzing important instructions by determining the priority of the audio to be analyzed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI perform an estimation of the user's emotions.

[0090] The analysis unit can prioritize the analysis of voices from specific locations by taking into account the user's geographical location information. For example, if the user is at home, the analysis unit will prioritize the analysis of instructions within the home. For example, the analysis unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the analysis unit can also prioritize the analysis of work-related instructions. For example, the analysis unit will acquire geographical location information and detect that the user is at the office. If the user is out, the analysis unit can also prioritize the analysis of urgent instructions. For example, the analysis unit will acquire geographical location information and detect that the user is out. This allows the analysis unit to prioritize the analysis of voices from specific locations by taking into account the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical location information into a generating AI and prioritize the analysis of voices from specific locations.

[0091] The analysis unit can analyze a user's social media activity and prioritize the analysis of relevant audio. For example, the analysis unit can prioritize the analysis of phrases that the user frequently uses on social media. For example, the analysis unit can analyze the content of social media posts and detect specific phrases. The analysis unit can also prioritize the analysis of audio related to specific events from the user's social media activity. For example, the analysis unit can analyze the content of social media posts and detect audio related to specific events. The analysis unit can also analyze a user's social media activity and prioritize the analysis of audio related to specific topics. For example, the analysis unit can analyze the content of social media posts and detect audio related to specific topics. In this way, the analysis unit can prioritize the analysis of relevant audio by analyzing the user's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input social media data into a generating AI and prioritize the analysis of relevant audio.

[0092] The detection unit can estimate the user's emotions and adjust the accuracy of instruction detection based on the estimated user emotions. For example, if the user is stressed, the detection unit can increase the accuracy of instruction detection and reduce false positives. For example, the detection unit can analyze voice data and estimate the user's emotions. If the user is relaxed, the detection unit can also return the accuracy of instruction detection to normal and prioritize natural conversation. For example, the detection unit can analyze voice data and estimate the user's emotions. If the user is in a hurry, the detection unit can maximize the accuracy of instruction detection to enable a quick response. For example, the detection unit can analyze voice data and estimate the user's emotions. This allows the detection unit to reduce false positives by adjusting the accuracy of instruction detection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input audio data into a generating AI, which can then perform the estimation of the user's emotions.

[0093] The detection unit can refer to the user's past instruction history and prioritize the detection of specific instructions. For example, the detection unit can prioritize the detection of instructions that the user has frequently used in the past. For example, the detection unit can analyze past instruction data and detect specific instructions. The detection unit can also prioritize the detection of instructions used during specific time periods from the user's past instruction history. For example, the detection unit can analyze past instruction data and detect instructions used during specific time periods. The detection unit can also analyze the user's past instruction history and prioritize the detection of instructions used in specific emotional states. For example, the detection unit can analyze past instruction data and detect instructions used in specific emotional states. In this way, the detection unit can prioritize the detection of specific instructions by referring to the user's past instruction history. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input past instruction data into a generating AI and detect specific instructions.

[0094] The detection unit can analyze the context of the audio and more accurately detect the intent of the instruction. For example, the detection unit can analyze the context before and after the user's utterance to accurately detect the intent of the instruction. For example, the detection unit analyzes the audio data to identify the context. The detection unit can also analyze keywords used in the user's utterance to accurately detect the intent of the instruction. For example, the detection unit analyzes the audio data to detect specific keywords. The detection unit can also analyze the tone and emotion of the user's utterance to accurately detect the intent of the instruction. For example, the detection unit analyzes the audio data to estimate the user's emotion. As a result, the detection unit can more accurately detect the intent of the instruction by analyzing the context of the audio. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input audio data into a generating AI to analyze the context.

[0095] The detection unit can estimate the user's emotions and determine the priority of instructions to detect based on the estimated user emotions. For example, if the user is tense, the detection unit will prioritize detecting important instructions. For example, the detection unit will analyze voice data and estimate the user's emotions. The detection unit can also prioritize detecting normal instructions if the user is relaxed. For example, the detection unit will analyze voice data and estimate the user's emotions. The detection unit can also prioritize detecting urgent instructions if the user is in a hurry. For example, the detection unit will analyze voice data and estimate the user's emotions. In this way, the detection unit can prioritize detecting important instructions by determining the priority of instructions to detect based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input audio data into a generating AI, which can then perform the estimation of the user's emotions.

[0096] The detection unit can prioritize detecting instructions for specific locations by taking into account the user's geographical location information. For example, if the user is at home, the detection unit will prioritize detecting instructions within the home. For example, the detection unit will acquire geographical location information and detect that the user is at home. The detection unit can also prioritize detecting work-related instructions if the user is at the office. For example, the detection unit will acquire geographical location information and detect that the user is at the office. The detection unit can also prioritize detecting urgent instructions if the user is out. For example, the detection unit will acquire geographical location information and detect that the user is out. In this way, the detection unit can prioritize detecting instructions for specific locations by taking into account the user's geographical location information. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input geographical location information into a generating AI and prioritize detecting instructions for specific locations.

[0097] The detection unit can analyze a user's social media activity and prioritize the detection of relevant instructions. For example, the detection unit can prioritize the detection of phrases that the user frequently uses on social media. For example, the detection unit can analyze the content of social media posts and detect specific phrases. The detection unit can also prioritize the detection of instructions related to specific events from a user's social media activity. For example, the detection unit can analyze the content of social media posts and detect instructions related to specific events. The detection unit can also analyze a user's social media activity and prioritize the detection of instructions related to specific topics. For example, the detection unit can analyze the content of social media posts and detect instructions related to specific topics. In this way, the detection unit can prioritize the detection of relevant instructions by analyzing a user's social media activity. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input social media data into a generating AI and prioritize the detection of relevant instructions.

[0098] The execution unit can estimate the user's emotions and adjust how actions are performed based on the estimated emotions. For example, if the user is stressed, the execution unit can speed up the execution of actions to reduce errors. For example, the execution unit can analyze voice data to estimate the user's emotions. If the user is relaxed, the execution unit can also return to normal execution of actions and prioritize natural actions. For example, the execution unit can analyze voice data to estimate the user's emotions. If the user is in a hurry, the execution unit can maximize the execution of actions to enable a quick response. For example, the execution unit can analyze voice data to estimate the user's emotions. This allows the execution unit to reduce errors by adjusting how actions are performed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input voice data into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0099] The execution unit can refer to the user's past action history and prioritize the execution of specific actions. For example, the execution unit can prioritize actions that the user has frequently performed in the past. For example, the execution unit can analyze past action data and detect specific actions. The execution unit can also prioritize actions performed during specific time periods based on the user's past action history. For example, the execution unit can analyze past action data and detect actions performed during specific time periods. The execution unit can also analyze the user's past action history and prioritize actions performed during specific emotional states. For example, the execution unit can analyze past action data and detect actions performed during specific emotional states. In this way, the execution unit can prioritize the execution of specific actions by referring to the user's past action history. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input past action data into a generating AI and execute a specific action.

[0100] The execution unit can analyze the context of the speech and execute the intent of the action more accurately. For example, the execution unit can analyze the context before and after the user's utterance and execute the intent of the action accurately. For example, the execution unit can analyze the speech data and identify the surrounding context. The execution unit can also analyze keywords used in the user's utterance and execute the intent of the action accurately. For example, the execution unit can analyze the speech data and detect specific keywords. The execution unit can also analyze the tone and emotion of the user's utterance and execute the intent of the action accurately. For example, the execution unit can analyze the speech data and estimate the user's emotion. As a result, the execution unit can execute the intent of the action more accurately by analyzing the context of the speech. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input speech data into a generating AI and analyze the context.

[0101] The execution unit can estimate the user's emotions and determine the priority of actions to perform based on the estimated emotions. For example, if the user is tense, the execution unit may prioritize important actions. For example, the execution unit may analyze voice data and estimate the user's emotions. If the user is relaxed, the execution unit may also prioritize normal actions. For example, the execution unit may analyze voice data and estimate the user's emotions. If the user is in a hurry, the execution unit may also prioritize urgent actions. For example, the execution unit may analyze voice data and estimate the user's emotions. This allows the execution unit to prioritize important actions by determining the priority of actions to perform based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input voice data into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0102] The execution unit can prioritize actions performed in specific locations by considering the user's geographical location. For example, if the user is at home, the execution unit will prioritize actions performed within the home. For example, the execution unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the execution unit can also prioritize work-related actions. For example, the execution unit will acquire geographical location information and detect that the user is at the office. If the user is out, the execution unit can also prioritize urgent actions. For example, the execution unit will acquire geographical location information and detect that the user is out. This allows the execution unit to prioritize actions performed in specific locations by considering the user's geographical location. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input geographical location information into a generating AI and prioritize actions performed in specific locations.

[0103] The execution unit can analyze the user's social media activity and prioritize the execution of relevant actions. For example, the execution unit can prioritize actions related to phrases that the user frequently uses on social media. For example, the execution unit can analyze social media posts and detect specific phrases. The execution unit can also prioritize actions related to specific events from the user's social media activity. For example, the execution unit can analyze social media posts and detect actions related to specific events. The execution unit can also analyze the user's social media activity and prioritize the execution of actions related to specific topics. For example, the execution unit can analyze social media posts and detect actions related to specific topics. In this way, the execution unit can prioritize the execution of relevant actions by analyzing the user's social media activity. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input social media data into a generating AI and prioritize the execution of relevant actions.

[0104] The tone analysis unit can estimate the user's emotions and adjust the accuracy of the tone analysis based on the estimated emotions. For example, if the user is stressed, the tone analysis unit can increase the accuracy of the analysis and reduce misanalysis. For example, the tone analysis unit analyzes the audio data and estimates the user's emotions. If the user is relaxed, the tone analysis unit can also return the accuracy of the analysis to normal and prioritize natural conversation. For example, the tone analysis unit analyzes the audio data and estimates the user's emotions. If the user is in a hurry, the tone analysis unit can also maximize the accuracy of the analysis to enable a quick response. For example, the tone analysis unit analyzes the audio data and estimates the user's emotions. This allows the tone analysis unit to reduce misanalysis by adjusting the accuracy of the tone analysis based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input voice data into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0105] The tone analysis unit can learn the user's past voice tones and prioritize the analysis of specific tones. For example, the tone analysis unit can prioritize the analysis of tones that the user has frequently used in the past. For example, the tone analysis unit can analyze past audio data and detect specific tones. The tone analysis unit can also prioritize the analysis of tones used during specific time periods from the user's past voice tones. For example, the tone analysis unit can analyze past audio data and detect tones used during specific time periods. The tone analysis unit can also analyze the user's past voice tones and prioritize the analysis of tones used in specific emotional states. For example, the tone analysis unit can analyze past audio data and detect tones used in specific emotional states. In this way, the tone analysis unit can prioritize the analysis of specific tones by learning the user's past voice tones. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input past audio data into a generating AI and analyze specific tones.

[0106] The tone analysis unit can analyze the context of speech and more accurately analyze the intent of the tone. For example, the tone analysis unit can analyze the context before and after the user's utterance and accurately analyze the intent of the tone. For example, the tone analysis unit analyzes the audio data and identifies the context. The tone analysis unit can also analyze keywords used in the user's utterance and accurately analyze the intent of the tone. For example, the tone analysis unit analyzes the audio data and detects specific keywords. The tone analysis unit can also analyze the tone and emotion of the user's utterance and accurately analyze the intent of the tone. For example, the tone analysis unit analyzes the audio data and estimates the user's emotion. As a result, the tone analysis unit can more accurately analyze the intent of the tone by analyzing the context of speech. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input audio data into a generating AI and analyze the context.

[0107] The tone analysis unit can estimate the user's emotions and determine the priority of tones to analyze based on the estimated user emotions. For example, if the user is tense, the tone analysis unit will prioritize analyzing important tones. For example, the tone analysis unit will analyze the audio data and estimate the user's emotions. If the user is relaxed, the tone analysis unit can also prioritize analyzing normal tones. For example, the tone analysis unit will analyze the audio data and estimate the user's emotions. If the user is in a hurry, the tone analysis unit can also prioritize analyzing urgent tones. For example, the tone analysis unit will analyze the audio data and estimate the user's emotions. In this way, the tone analysis unit can prioritize analyzing important tones by determining the priority of tones to analyze based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input voice data into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0108] The tone analysis unit can prioritize the analysis of tones in specific locations by taking into account the user's geographical location information. For example, if the user is at home, the tone analysis unit will prioritize the analysis of tones within the home. For example, the tone analysis unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the tone analysis unit can also prioritize the analysis of work-related tones. For example, the tone analysis unit will acquire geographical location information and detect that the user is at the office. If the user is out, the tone analysis unit can also prioritize the analysis of urgent tones. For example, the tone analysis unit will acquire geographical location information and detect that the user is out. In this way, the tone analysis unit can prioritize the analysis of tones in specific locations by taking into account the user's geographical location information. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input geographical location information into a generating AI and prioritize the analysis of tones in specific locations.

[0109] The tone analysis unit can analyze a user's social media activity and prioritize the analysis of relevant tones. For example, the tone analysis unit can prioritize the analysis of tones that the user frequently uses on social media. For example, the tone analysis unit can analyze the content of social media posts and detect specific tones. The tone analysis unit can also prioritize the analysis of tones related to specific events from the user's social media activity. For example, the tone analysis unit can analyze the content of social media posts and detect tones related to specific events. The tone analysis unit can also analyze a user's social media activity and prioritize the analysis of tones related to specific topics. For example, the tone analysis unit can analyze the content of social media posts and detect tones related to specific topics. In this way, the tone analysis unit can prioritize the analysis of relevant tones by analyzing the user's social media activity. Some or all of the above processing in the tone analysis unit may be performed using AI, for example, or without AI. For example, the tone analysis unit can input social media data into a generating AI and prioritize the analysis of relevant tones.

[0110] The emergency response unit can estimate the user's emotions and adjust its emergency response method based on the estimated emotions. For example, if the user is stressed, the emergency response unit can respond quickly and reduce the likelihood of an incorrect response. For example, the emergency response unit can analyze voice data to estimate the user's emotions. If the user is relaxed, the emergency response unit can also use a normal response method and prioritize a natural response. For example, the emergency response unit can analyze voice data to estimate the user's emotions. If the user is in a hurry, the emergency response unit can use the most efficient response method to enable a quick response. For example, the emergency response unit can analyze voice data to estimate the user's emotions. This allows the emergency response unit to reduce the likelihood of an incorrect response by adjusting its emergency response method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or without AI. For example, the emergency response unit can input voice data into a generating AI and have the AI ​​perform an estimation of the user's emotions.

[0111] The emergency response unit can refer to the user's past emergency history and prioritize responding to specific emergencies. For example, the emergency response unit prioritizes responses based on emergencies the user has experienced in the past. For example, the emergency response unit analyzes past emergency data to detect specific emergencies. The emergency response unit can also prioritize responding to emergencies that occur during specific time periods based on the user's past emergency history. For example, the emergency response unit analyzes past emergency data to detect emergencies that occur during specific time periods. The emergency response unit can also analyze the user's past emergency history and prioritize responding to emergencies that occur during specific emotional states. For example, the emergency response unit analyzes past emergency data to detect emergencies that occur during specific emotional states. In this way, the emergency response unit can prioritize responding to specific emergencies by referring to the user's past emergency history. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or without AI. For example, the emergency response unit can input past emergency data into a generating AI to detect specific emergencies.

[0112] The emergency response unit can analyze the context of speech to respond more accurately to the intent of an emergency. For example, the emergency response unit can analyze the context before and after a user's utterance to respond accurately to the intent of an emergency. For example, the emergency response unit can analyze speech data to identify the context. The emergency response unit can also analyze keywords used in a user's utterance to respond accurately to the intent of an emergency. For example, the emergency response unit can analyze speech data to detect specific keywords. The emergency response unit can also analyze the tone and emotion of a user's utterance to respond accurately to the intent of an emergency. For example, the emergency response unit can analyze speech data to estimate the user's emotion. This allows the emergency response unit to respond more accurately to the intent of an emergency by analyzing the context of speech. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or without AI. For example, the emergency response unit can input speech data into a generating AI to analyze the context.

[0113] The emergency response unit can estimate the user's emotions and determine the priority of emergency responses based on the estimated emotions. For example, if the user is tense, the emergency response unit will prioritize important emergencies. For example, the emergency response unit will analyze voice data and estimate the user's emotions. If the user is relaxed, the emergency response unit can also prioritize ordinary emergencies. For example, the emergency response unit will analyze voice data and estimate the user's emotions. If the user is in a hurry, the emergency response unit can also prioritize urgent emergencies. For example, the emergency response unit will analyze voice data and estimate the user's emotions. This allows the emergency response unit to prioritize important emergencies by determining the priority of emergency responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or without AI. For example, the emergency response unit can input voice data into a generating AI and have the AI ​​perform an estimation of the user's emotions.

[0114] The emergency response unit can prioritize responding to emergencies in specific locations by considering the user's geographical location. For example, if the user is at home, the emergency response unit will prioritize responding to emergencies within the home. For example, the emergency response unit will acquire geographical location information and detect that the user is at home. If the user is at the office, the emergency response unit can also prioritize responding to work-related emergencies. For example, the emergency response unit will acquire geographical location information and detect that the user is at the office. If the user is out, the emergency response unit can also prioritize responding to urgent emergencies. For example, the emergency response unit will acquire geographical location information and detect that the user is out. In this way, the emergency response unit can prioritize responding to emergencies in specific locations by considering the user's geographical location. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or not using AI. For example, the emergency response unit can input geographical location information into a generating AI and prioritize responding to emergencies in specific locations.

[0115] The emergency response unit can analyze users' social media activity and prioritize responses to relevant emergencies. For example, the emergency response unit can prioritize responses to emergencies related to phrases that users frequently use on social media. For example, the emergency response unit can analyze social media posts and detect specific phrases. The emergency response unit can also prioritize responses to emergencies related to specific events based on users' social media activity. For example, the emergency response unit can analyze social media posts and detect emergencies related to specific events. The emergency response unit can also analyze users' social media activity and prioritize responses to emergencies related to specific topics. For example, the emergency response unit can analyze social media posts and detect emergencies related to specific topics. In this way, the emergency response unit can prioritize responses to relevant emergencies by analyzing users' social media activity. Some or all of the above processing in the emergency response unit may be performed using AI, for example, or not using AI. For example, the emergency response unit can input social media data into a generating AI and prioritize responses to relevant emergencies.

[0116] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0117] The voice assistant system can also include a health monitoring unit that monitors the user's health status. The health monitoring unit, for example, measures the user's heart rate and blood pressure and notifies the voice assistant if an abnormality is detected. For instance, if the user's heart rate suddenly increases, the health monitoring unit notifies the voice assistant and encourages the user to rest. The health monitoring unit can also analyze the user's sleep patterns and suggest appropriate sleep durations. For example, if the user is not getting enough sleep, the voice assistant suggests going to bed earlier. Furthermore, the health monitoring unit can record the user's diet and evaluate nutritional balance. For example, if the user is consistently eating an unbalanced diet, the voice assistant suggests a balanced diet. In this way, the voice assistant system can support the user's health management by monitoring their health status and providing appropriate advice.

[0118] The voice assistant system may also include a music selection unit that estimates the user's emotions and selects music based on those emotions. For example, if the user is feeling stressed, the music selection unit might select relaxing music. For example, the music selection unit might analyze voice data to estimate the user's emotions. If the user is relaxed, the music selection unit might also select music to maintain that mood. For example, the music selection unit might analyze voice data to estimate the user's emotions. If the user is in a hurry, the music selection unit might also select energetic music. For example, the music selection unit might analyze voice data to estimate the user's emotions. In this way, the music selection unit can improve the user's mood by selecting appropriate music based on the user's emotions.

[0119] The voice assistant system can also include a schedule management unit to manage the user's schedule. This unit can, for example, synchronize the user's calendar and automatically update appointments. For instance, it can add new appointments based on the user's voice commands. If the user says, "Set up a meeting for 3pm tomorrow," the schedule management unit will detect the command and add the meeting to the calendar. The schedule management unit can also set reminders based on the user's schedule. For example, if the user says, "Remind me so I don't forget tomorrow's meeting," the schedule management unit will set a reminder. Furthermore, the schedule management unit can suggest optimal time management based on the user's schedule. For example, if the user says, "Optimize my schedule for this week," the schedule management unit will analyze the user's schedule and suggest an efficient schedule. This allows the schedule management unit to efficiently manage the user's schedule and support effective time management.

[0120] The voice assistant system may also include a notification management unit that estimates the user's emotions and prioritizes notifications based on those emotions. For example, if the user is stressed, the notification management unit will prioritize displaying only important notifications. For instance, it might analyze voice data to estimate the user's emotions. If the user is relaxed, the notification management unit can also display regular notifications. For example, it might analyze voice data to estimate the user's emotions. If the user is in a hurry, the notification management unit can also prioritize displaying urgent notifications. For example, it might analyze voice data to estimate the user's emotions. This allows the notification management unit to appropriately convey important information by prioritizing notifications based on the user's emotions.

[0121] The voice assistant system can also be equipped with a learning support unit to further assist the user's learning. This unit can, for example, monitor the user's learning progress and suggest an appropriate learning plan. For instance, if the user says, "I want to start studying for the next exam," the unit can create a learning plan. The unit can also provide quizzes and practice problems based on the user's learning content. For example, if the user says, "Give me a math problem," the unit will provide an appropriate problem. Furthermore, the unit can suggest learning materials tailored to the user's learning style. For example, if the user says, "I want to learn through videos," the unit will suggest video materials. This allows the learning support unit to effectively support the user's learning and improve learning outcomes.

[0122] The voice assistant system may also include an exercise suggestion unit that estimates the user's emotions and suggests exercises based on those emotions. For example, if the user is feeling stressed, the exercise suggestion unit may suggest relaxing exercises. For example, the exercise suggestion unit may analyze voice data to estimate the user's emotions. If the user is relaxed, the exercise suggestion unit may also suggest exercises to maintain that mood. For example, the exercise suggestion unit may analyze voice data to estimate the user's emotions. If the user is in a hurry, the exercise suggestion unit may also suggest short, effective exercises. For example, the exercise suggestion unit may analyze voice data to estimate the user's emotions. In this way, the exercise suggestion unit can support the user's health by suggesting appropriate exercises based on the user's emotions.

[0123] The voice assistant system can also be equipped with a hobby support unit to further assist the user's hobbies. This unit can, for example, provide information related to the user's hobbies. For instance, if the user says, "Tell me some gardening tips," the hobby support unit will provide information about gardening. The hobby support unit can also notify the user of events related to their hobbies. For example, if the user says, "When is the next gardening event?", the hobby support unit will provide event information. Furthermore, the hobby support unit can introduce the user to communities related to their hobbies. For example, if the user says, "I want to find gardening friends," the hobby support unit will introduce relevant communities. In this way, the hobby support unit can support the user's hobbies and enrich their hobby activities.

[0124] The voice assistant system may also include a relaxation suggestion unit that estimates the user's emotions and suggests relaxation methods based on those emotions. For example, if the user is feeling stressed, the relaxation suggestion unit might suggest relaxation methods. For instance, it might analyze voice data to estimate the user's emotions. If the user is relaxed, the relaxation suggestion unit might also suggest ways to maintain that mood. For example, it might analyze voice data to estimate the user's emotions. If the user is in a hurry, the relaxation suggestion unit might also suggest quick and effective relaxation methods. For example, it might analyze voice data to estimate the user's emotions. This allows the relaxation suggestion unit to reduce user stress by suggesting appropriate relaxation methods based on the user's emotions.

[0125] The voice assistant system can also include a travel support unit to assist the user's travels. This unit can, for example, create travel plans and suggest optimal travel itineraries. For instance, if a user says, "I want to plan a trip for my next vacation," the travel support unit will create a travel plan. The travel support unit can also provide information about the user's travel destination. For example, if a user says, "Tell me about tourist attractions in Paris," the travel support unit will provide information about tourist attractions. Furthermore, the travel support unit can provide support during the user's trip. For example, if a user says, "Tell me the time of the next train," the travel support unit will provide a train timetable. In this way, the travel support unit can support the user's travels and provide a comfortable travel experience.

[0126] The voice assistant system may also include a communication suggestion unit that estimates the user's emotions and proposes communication methods based on those emotions. For example, if the user is feeling stressed, the communication suggestion unit may suggest a relaxing communication method. For example, the communication suggestion unit may analyze voice data to estimate the user's emotions. If the user is relaxed, the communication suggestion unit may also suggest a communication method to maintain that mood. For example, the communication suggestion unit may analyze voice data to estimate the user's emotions. If the user is in a hurry, the communication suggestion unit may also suggest a quick communication method. For example, the communication suggestion unit may analyze voice data to estimate the user's emotions. In this way, the communication suggestion unit can support effective communication by suggesting appropriate communication methods based on the user's emotions.

[0127] The following briefly describes the processing flow for example form 2.

[0128] Step 1: The monitoring unit continuously monitors the audio. For example, the monitoring unit monitors the audio in real time and constantly captures the user's speech. The monitoring unit can also perform periodic sampling and collect audio data. For example, the monitoring unit samples audio data every second and sends it to the analysis unit. Step 2: The analysis unit analyzes the audio monitored by the monitoring unit. The analysis unit converts the audio data into text data, for example, using speech recognition technology. The analysis unit can also analyze the content of the audio data using natural language processing technology. For example, the analysis unit converts the audio data into text data and then analyzes that text data to extract instructions. Step 3: The detection unit detects instructions for the voice assistant from the content analyzed by the analysis unit. The detection unit detects instructions, for example, by detecting specific keywords. The detection unit can also perform contextual analysis to understand the intent of the instructions. For example, the detection unit detects the instruction "set a timer for 3 minutes" and starts the timer. Step 4: The execution unit performs an action based on the instructions detected by the detection unit. The execution unit can, for example, operate a home appliance. The execution unit can also provide information. For example, the execution unit can start a timer and sound an alarm after 3 minutes.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0131] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the monitoring unit, analysis unit, detection unit, execution unit, tone analysis unit, and emergency response unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the monitoring unit constantly monitors voice using the microphone 38B of the smart device 14. The analysis unit analyzes voice data using the identification processing unit 290 of the data processing unit 12. The detection unit detects instructions from the analyzed content, and the execution unit performs actions based on the detected instructions. The tone analysis unit analyzes the tone of the user's voice using the microphone 38B of the smart device 14, and the emergency response unit responds quickly in emergencies. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0133] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0134] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the monitoring unit, analysis unit, detection unit, execution unit, tone analysis unit, and emergency response unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the monitoring unit constantly monitors voice using the microphone 238 of the smart glasses 214. The analysis unit analyzes voice data using the identification processing unit 290 of the data processing unit 12. The detection unit detects instructions from the analyzed content, and the execution unit performs actions based on the detected instructions. The tone analysis unit analyzes the tone of the user's voice using the microphone 238 of the smart glasses 214, and the emergency response unit responds quickly in emergencies. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0149] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0150] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the monitoring unit, analysis unit, detection unit, execution unit, tone analysis unit, and emergency response unit, is implemented in at least one of the following: the headset terminal 314 and the data processing unit 12. For example, the monitoring unit constantly monitors voice using the microphone 238 of the headset terminal 314. The analysis unit analyzes voice data using the identification processing unit 290 of the data processing unit 12. The detection unit detects instructions from the analyzed content, and the execution unit performs actions based on the detected instructions. The tone analysis unit analyzes the tone of the user's voice using the microphone 238 of the headset terminal 314, and the emergency response unit responds quickly in emergencies. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0165] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0166] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0167] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0168] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0169] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0170] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0171] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0172] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0173] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0174] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0175] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0176] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0177] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0178] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0179] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0180] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] Each of the multiple elements described above, including the monitoring unit, analysis unit, detection unit, execution unit, tone analysis unit, and emergency response unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the monitoring unit constantly monitors voice using the microphone 238 of the robot 414. The analysis unit analyzes voice data using the identification processing unit 290 of the data processing unit 12. The detection unit detects instructions from the analyzed content, and the execution unit performs actions based on the detected instructions. The tone analysis unit analyzes the tone of the user's voice using the microphone 238 of the robot 414, and the emergency response unit responds quickly in emergencies. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0182] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0183] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0184] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0185] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0186] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0187] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0188] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0189] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0190] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0191] 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.

[0192] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0193] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0194] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0195] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0196] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0197] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0198] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0199] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0200] (Note 1) A monitoring unit that constantly monitors the audio, An analysis unit analyzes the audio monitored by the aforementioned monitoring unit, A detection unit detects instructions for the voice assistant from the content analyzed by the aforementioned analysis unit, The system includes an execution unit that performs an operation based on an instruction detected by the detection unit. A system characterized by the following features. (Note 2) It includes a tone analysis unit that analyzes the tone and context of the user's voice. The system described in Appendix 1, characterized by the features described herein. (Note 3) Equipped with an emergency response unit to respond quickly in emergencies. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, The system analyzes the user's tone of voice and context to determine the urgency of the instructions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The execution unit is, When a user says "help," we respond quickly and provide appropriate support. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned monitoring unit, It estimates the user's emotions and adjusts the accuracy of voice monitoring based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned monitoring unit, It learns the user's past voice patterns and prioritizes monitoring of specific voice patterns. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned monitoring unit, Filter out ambient noise and monitor only the user's voice. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned monitoring unit, It estimates the user's emotions and determines the priority of voices to monitor based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned monitoring unit, Prioritize monitoring of audio in specific locations, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned monitoring unit, Analyze users' social media activity and prioritize monitoring relevant audio. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, Remove background noise from audio and analyze the clear audio data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, Referencing the user's past statements allows for a more accurate analysis of their intent. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It estimates the user's emotions and determines the priority of the audio to analyze based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, By considering the user's geographical location, audio from specific locations is prioritized for analysis. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, Analyze users' social media activity and prioritize analyzing relevant audio. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit is It estimates the user's emotions and adjusts the accuracy of instruction detection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The detection unit is Referencing the user's past instruction history, the system prioritizes detecting specific instructions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The detection unit is Analyze the context of the audio to more accurately detect the intent behind the instructions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The detection unit is It estimates the user's emotions and determines the priority of the instructions to detect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The detection unit is The system prioritizes detecting instructions for specific locations, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The detection unit is Analyze users' social media activity and prioritize detecting relevant instructions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The execution unit is, It estimates the user's emotions and adjusts how actions are performed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The execution unit is, Referencing the user's past action history, prioritize certain actions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The execution unit is, By analyzing the context of the speech, the intent of the action is executed more accurately. The system described in Appendix 1, characterized by the features described herein. (Note 27) The execution unit is, It estimates the user's emotions and determines the priority of actions to perform based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The execution unit is, The system prioritizes actions performed in specific locations, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The execution unit is, Analyze users' social media activity and prioritize relevant actions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The tone analysis unit, It estimates the user's emotions and adjusts the accuracy of tone analysis based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The tone analysis unit, It learns the user's past voice tones and prioritizes analyzing specific tones. The system described in Appendix 2, characterized by the features described herein. (Note 32) The tone analysis unit, Analyze the context of the speech to more accurately interpret the intent behind the tone. The system described in Appendix 2, characterized by the features described herein. (Note 33) The tone analysis unit, It estimates the user's emotions and determines the tone priorities for analysis based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The tone analysis unit, By considering the user's geographical location, the system prioritizes analyzing the tone in specific locations. The system described in Appendix 2, characterized by the features described herein. (Note 35) The tone analysis unit, Analyze users' social media activity and prioritize analyzing relevant tones. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned emergency response unit, It estimates the user's emotions and adjusts emergency response methods based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned emergency response unit, Referencing the user's past emergency history, we prioritize responding to specific emergencies. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned emergency response unit, By analyzing the context of the audio, we can respond more accurately to the intent of an emergency. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned emergency response unit, It estimates the user's emotions and determines the priority of emergency responses based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned emergency response unit, By considering the user's geographical location, we prioritize responding to emergencies in specific locations. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned emergency response unit, We analyze users' social media activity and prioritize responses to relevant emergencies. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0201] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A monitoring unit that constantly monitors the audio, An analysis unit analyzes the audio monitored by the aforementioned monitoring unit, A detection unit detects instructions for the voice assistant from the content analyzed by the aforementioned analysis unit, The system includes an execution unit that performs an operation based on an instruction detected by the detection unit. A system characterized by the following features.

2. It includes a tone analysis unit that analyzes the tone and context of the user's voice. The system according to feature 1.

3. Equipped with an emergency response unit to respond quickly in emergencies. The system according to feature 1.

4. The aforementioned analysis unit, The system analyzes the user's tone of voice and context to determine the urgency of the instructions. The system according to feature 1.

5. The execution unit is, When a user asks for help, we respond quickly and provide appropriate support. The system according to feature 1.

6. The aforementioned monitoring unit, It estimates the user's emotions and adjusts the accuracy of voice monitoring based on the estimated user emotions. The system according to feature 1.

7. The aforementioned monitoring unit, It learns the user's past voice patterns and prioritizes monitoring of specific voice patterns. The system according to feature 1.

8. The aforementioned monitoring unit, Filter out ambient noise and monitor only the user's voice. The system according to feature 1.

9. The aforementioned monitoring unit, It estimates the user's emotions and determines the priority of voices to monitor based on the estimated user emotions. The system according to feature 1.

Images