system

Abstract

The system according to this embodiment aims to enable users to autonomously handle incoming and outgoing phone calls. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, an audio output unit, an audio input unit, and a notification unit. The reception unit receives instructions from the user. The generation unit generates call content based on the instructions received by the reception unit. The audio output unit synthesizes the call content generated by the generation unit and outputs it. The audio input unit takes the speech of the other party in the call as audio input and converts it into text. The notification unit summarizes the call content into a summary document and notifies the user.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult to handle incoming and outgoing calls due to time constraints and disabilities.

[0005] The system according to the embodiment aims to enable a user to autonomously handle incoming and outgoing calls.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a generation unit, an audio output unit, an audio input unit, and a notification unit. The reception unit receives instructions from the user. The generation unit generates call content based on the instructions received by the reception unit. The audio output unit synthesizes the call content generated by the generation unit and outputs it. The audio input unit takes the other party's speech as audio input and converts it into text. The notification unit summarizes the call content into a summary document and notifies the user. [Effects of the Invention]

[0007] The system according to this embodiment allows the user to autonomously handle incoming and outgoing phone calls. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is a system that autonomously handles incoming and outgoing phone calls using generative AI. In this system, the user inputs instructions through a smartphone application, and the generative AI makes a call and conducts the conversation based on those instructions. The content of the conversation is summarized by the generative AI and notified to the user's smartphone. The generative AI also handles incoming calls and summarizes the content of the conversation in a text document, notifying the user. This mechanism makes it possible for people who do not have time to make phone calls or who cannot use the phone due to a disability to handle phone calls. For example, the user inputs an instruction such as "I would like to make a reservation at a restaurant" through a smartphone application. This instruction is sent to the generative AI. Next, the generative AI makes a call based on the input instruction. The generative AI generates the content of the conversation as text and outputs it as voice to the other party through speech synthesis. For example, the generative AI outputs as voice the content "Please make a reservation for 3 PM on August 20th." The other party's statements are converted into text through voice input and input to the generative AI. The generating AI generates an appropriate response based on what the caller says and outputs it back to the caller through speech synthesis. For example, if the caller asks, "How many people are in your party?", the generating AI will respond, "Two adults." When the call ends, the generating AI summarizes the call content in a summary and notifies the user's smartphone. For example, the notification might say, "Your restaurant reservation is complete. Electronic payment is available." The generating AI also handles incoming calls. It answers incoming calls and summarizes the call content in a summary, notifying the user. For example, it might say, "You have a call from the bank regarding a credit card campaign." This system makes it possible for people who don't have time to make calls or who cannot use the phone due to disabilities to receive phone calls. It also helps deter spam and fraudulent calls and reduces the labor costs and time spent on answering calls. As a result, the AI ​​agent system can autonomously handle both incoming and outgoing calls.

[0029] The AI ​​agent system according to this embodiment comprises a reception unit, a generation unit, an audio output unit, an audio input unit, and a notification unit. The reception unit receives instructions from the user. Instructions from the user include, but are not limited to, voice instructions, text instructions, and gesture instructions. For example, the reception unit receives voice instructions with a microphone and converts them into text data using speech recognition technology. The reception unit can also directly receive text instructions. Furthermore, the reception unit can detect gesture instructions with a camera and analyze the content of the instructions using gesture recognition technology. The generation unit generates call content based on the instructions received by the reception unit using a generation AI. For example, the generation unit generates call content as text using a text generation AI (e.g., LLM). The generation unit can also generate an appropriate response based on what the other party says using a generation AI. For example, the generation AI generates call content such as "Please make a reservation for 3 PM on August 20th" based on the user's instructions. The audio output unit synthesizes the call content generated by the generation unit and outputs it. The audio output unit outputs the generated call content as audio, for example, using TTS (Text-to-Speech) technology. The audio output unit can also output the generated call content as natural-sounding audio using a speech synthesis engine. For example, the audio output unit inputs the generated call content into a speech synthesis engine and outputs it as audio data. The audio input unit takes the other party's speech as audio input and converts it into text. The audio input unit converts the other party's speech into text data using, for example, ASR (Automatic Speech Recognition) technology. The audio input unit can also recognize the other party's speech with high accuracy using a speech recognition engine. For example, the audio input unit receives the other party's speech via a microphone, inputs it into a speech recognition engine, and outputs it as text data. The notification unit summarizes the call content into a summary document and notifies the user. The notification unit summarizes the call content using, for example, a summarization algorithm and extracts highly important information. The notification unit can also concisely summarize the call content using a generation AI. For example, the notification unit inputs the call content into a generation AI and outputs a summarized text.As a result, the AI ​​agent system according to the embodiment can generate call content based on user instructions, synthesize and output it as speech, and convert the other party's statements into text for notification.

[0030] The reception desk receives instructions from users. These instructions may include, but are not limited to, voice, text, and gesture instructions. For example, the reception desk receives voice instructions via a microphone and converts them into text data using speech recognition technology. Specifically, a deep learning-based speech recognition model is used. This model has been trained on a large amount of voice data and can convert voice to text with high accuracy. For example, if a user gives the instruction "Cancel tomorrow's meeting," the reception desk receives this voice via a microphone and converts it into text data "Cancel tomorrow's meeting" using the speech recognition model. The reception desk can also directly receive text instructions. If a user enters text using a keyboard or touchscreen, the reception desk receives the text directly and passes it on to the next process. Furthermore, the reception desk can detect gesture instructions with a camera and analyze the content of the instructions using gesture recognition technology. The gesture recognition technology used combines computer vision and machine learning. For example, if a user waves their hand, the camera captures the motion, and the gesture recognition model analyzes the motion to recognize the instruction "wave hand." This allows the reception desk to support a variety of input methods, such as voice, text, and gestures, enabling it to flexibly receive user instructions.

[0031] The generation unit uses a generation AI to generate call content based on instructions received by the reception unit. For example, the generation unit uses a text generation AI (e.g., LLM) to generate the call content as text. Specifically, the generation AI analyzes the user's instructions and utilizes natural language processing techniques to generate appropriate call content. For example, if a user instructs, "Please make a reservation for 3 PM on August 20th," the generation AI analyzes this instruction and generates call content including reservation details. The generation unit can also use the generation AI to generate appropriate responses based on what the other party says. For example, if the other party asks, "Are you free that day?", the generation AI analyzes the question and generates an appropriate response such as, "Yes, 3 PM on August 20th is available." The generation AI has learned from a large amount of conversational data beforehand, enabling it to generate natural responses appropriate to the context. Furthermore, the generation unit can perform grammar checks and style adjustments to output the generated call content in an appropriate format. This allows the generation unit to generate high-quality call content based on user instructions, improving the overall communication capabilities of the system.

[0032] The audio output unit synthesizes and outputs the call content generated by the generation unit. For example, the audio output unit outputs the call content generated using TTS (Text-to-Speech) technology as audio. Specifically, TTS technology uses a speech synthesis engine to convert text data into audio data. This engine can reproduce natural pronunciation and intonation based on pre-recorded audio data. For example, if the generation unit generates the call content "Please make a reservation for 3 PM on August 20th," the audio output unit inputs this text data into the TTS engine and outputs it as natural speech. The audio output unit can also output the generated call content as natural speech using the speech synthesis engine. The speech synthesis engine can select different voice qualities and speaking styles according to the user's preferences. For example, it can provide various voice styles such as male or female voices, calm speaking styles, and energetic speaking styles. This allows the audio output unit to provide the generated call content as natural speech that is easy for the user to understand. Furthermore, the audio output unit also has a function to adjust the speed and volume of the audio, allowing for customization according to user needs. This allows the audio output unit to provide users with high-quality audio output, improving the overall user experience of the system.

[0033] The voice input unit takes the other party's speech as voice input and converts it into text. For example, the voice input unit uses ASR (Automatic Speech Recognition) technology to convert the other party's speech into text data. Specifically, ASR technology uses a speech recognition engine to analyze the voice data, extract voice features, and convert them into text. This engine has learned from a large amount of voice data and can convert speech to text with high accuracy. For example, if the other party says, "Are you free that day?", the voice input unit receives this voice via the microphone and uses the speech recognition engine to convert it into text data: "Are you free that day?". Furthermore, the voice input unit can also recognize the other party's speech with high accuracy using the speech recognition engine. The speech recognition engine performs preprocessing such as noise reduction and speech normalization to improve the quality of the voice data. This allows the voice input unit to accurately convert the other party's speech into text data and pass it on to the next processing step. In addition, the voice input unit can support multiple languages ​​and dialects, achieving high-accuracy speech recognition even in different language environments. This allows the voice input unit to accurately recognize what the other party is saying, improving the overall communication capabilities of the system.

[0034] The notification unit summarizes the call content into a summary document and notifies the user. For example, the notification unit uses a summarization algorithm to summarize the call content and extract highly important information. Specifically, the summarization algorithm analyzes the text data of the call content, extracts important keywords and phrases, and generates a concise summary. For example, if the call content is "Please make a reservation for 3 PM on August 20th. I have no other plans that day, so it's fine," the notification unit will generate a summary such as "Make a reservation for 3 PM on August 20th." The notification unit can also use generative AI to concisely summarize the call content. Generative AI utilizes natural language processing technology to understand the context of the call content, extract important information, and generate a summary. For example, if the call content is "Please make a reservation for 3 PM on August 20th. I have no other plans that day, so it's fine," the generative AI will generate a summary such as "Make a reservation for 3 PM on August 20th." In this way, the notification unit can concisely notify the user of important information and help the user understand it. Furthermore, the notification unit provides various notification methods to inform users of summarized call content. For example, it can quickly deliver summarized call content to users using smartphone push notifications, email, SMS, etc. This allows the notification unit to quickly and reliably notify users of important information, improving the overall usability of the system.

[0035] The generation unit can generate conversation content as text using a generation AI. For example, the generation unit uses a text generation AI (e.g., LLM) to generate conversation content as text. For example, the generation unit's generation AI can generate conversation content such as "Please make a reservation for 3 PM on August 20th." The generation unit can also use the generation AI to generate appropriate responses based on what the other party says. For example, if the other party asks "How many people are in your party?", the generation unit will generate a response such as "Two adults." This improves the accuracy of the conversation content by generating it as text using the generation AI. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit inputs user instructions into the generation AI and outputs the generated conversation content.

[0036] The audio output unit can synthesize and output the generated call content. For example, the audio output unit can output the generated call content as audio using TTS (Text-to-Speech) technology. For example, the audio output unit can input the generated call content into a speech synthesis engine and output it as audio data. Furthermore, the audio output unit can synthesize and output the call content generated using a generation AI. For example, the audio output unit inputs the call content generated by the generation AI into a speech synthesis engine and outputs it as audio data. This allows the generated call content to be transmitted to the other party as audio by synthesizing and outputting it. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the audio output unit inputs the call content generated by the generation AI into a speech synthesis engine and outputs it as audio data.

[0037] The voice input unit can input the other party's speech and convert it into text. For example, the voice input unit uses ASR (Automatic Speech Recognition) technology to convert the other party's speech into text data. For example, the voice input unit receives the other party's speech via a microphone, inputs it into a speech recognition engine, and outputs it as text data. The voice input unit can also use a generative AI to input the other party's speech and convert it into text. For example, the generative AI inputs the other party's speech into a speech recognition engine and outputs it as text data. This allows the content of a call to be recorded as text by inputting the other party's speech and converting it into text. Some or all of the above processing in the voice input unit is performed using a generative AI. For example, the generative AI inputs the other party's speech into a speech recognition engine and outputs it as text data.

[0038] The notification unit can summarize the call content into a summary document and notify the user. For example, the notification unit can summarize the call content using a summarization algorithm and extract highly important information. For example, the notification unit can input the call content into a generation AI and output a summarized document. The notification unit can also use the generation AI to concisely summarize the call content. For example, the notification unit can have the generation AI summarize the call content, extract important information, and notify the user. This allows the user to easily grasp the call content by summarizing it into a summary document and notifying them of it. Some or all of the above processing in the notification unit is performed using the generation AI. For example, the notification unit can have the generation AI summarize the call content, extract important information, and notify the user.

[0039] The reception desk can analyze the user's past instruction history and select the optimal reception method. For example, the reception desk can automatically display instructions that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting reception methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest instructions to be used during specific time periods based on the user's past instruction history. In this way, the reception desk can select the optimal reception method by analyzing the user's past instruction history. Some or all of the above processes in the reception desk are performed using AI. For example, the reception desk uses AI to analyze the user's past instruction history and select the optimal reception method.

[0040] The reception unit can filter instructions based on the user's current situation and areas of interest when receiving them. For example, the reception unit prioritizes displaying relevant instructions based on the user's current situation. It can also filter and display relevant instructions based on the user's areas of interest. Furthermore, the reception unit can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows for the priority reception of highly relevant instructions by filtering based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit uses AI to analyze the user's current situation and areas of interest and filter and display relevant instructions.

[0041] The reception unit can prioritize receiving instructions that are highly relevant based on the user's geographical location. For example, if the user is in a specific location, the reception unit will prioritize receiving instructions related to that location. The reception unit can also filter and display relevant instructions based on the user's current location. Furthermore, the reception unit can suggest the most appropriate instructions, taking into account the user's geographical location. This allows for more appropriate instruction reception by prioritizing highly relevant instructions based on the user's geographical location. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit uses AI to analyze the user's geographical location and filter and display relevant instructions.

[0042] The reception unit can analyze the user's social media activity when receiving instructions and accept relevant instructions. For example, the reception unit can prioritize receiving relevant instructions based on the user's social media activity. The reception unit can also analyze the user's social media activity and suggest the most appropriate instructions. Furthermore, the reception unit can filter and display relevant instructions based on the user's social media activity. This allows for the priority acceptance of relevant instructions by analyzing the user's social media activity. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit uses AI to analyze the user's social media activity and filter and display relevant instructions.

[0043] The generation unit can adjust the level of detail generated based on the importance of the call when generating call content. For example, in the case of an important call, the generation unit generates call content that includes detailed information. In the case of a normal call, the generation unit can also generate call content that includes concise information. Furthermore, in the case of an urgent call, the generation unit can generate call content that allows for a quick response. In this way, by adjusting the level of detail generated based on the importance of the call, important call content can be generated in detail. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit uses the generation AI to evaluate the importance of the call and generate detailed important call content.

[0044] The generation unit can apply different generation algorithms depending on the call category when generating call content. For example, in the case of a business call, the generation unit generates formal call content. It can also generate casual call content for private calls. Furthermore, in the case of an emergency call, the generation unit can generate call content that allows for a quick response. By applying different generation algorithms depending on the call category, more appropriate call content can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI identifies the call category and applies the appropriate generation algorithm.

[0045] The generation unit can determine the generation priority based on the call submission timing when generating call content. For example, the generation unit will generate urgent call content with the highest priority. The generation unit can also generate normal call content with normal priority. Furthermore, the generation unit can prioritize the generation of important call content. This allows for the priority generation of urgent call content by determining the generation priority based on the call submission timing. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit uses the generation AI to evaluate the call submission timing and prioritize the generation of urgent call content.

[0046] The generation unit can adjust the generation order based on the relevance of the calls when generating call content. For example, the generation unit can prioritize generating highly relevant call content. It can also postpone generating less relevant call content. Furthermore, the generation unit can determine the optimal generation order based on the relevance of the call content. This allows for the priority generation of highly relevant call content by adjusting the generation order based on the relevance of the calls. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit uses the generation AI to evaluate the relevance of the call content and prioritize the generation of highly relevant call content.

[0047] The audio output unit can adjust the level of detail in the audio output based on the importance of the call content. For example, in the case of important call content, the audio output unit will output audio containing detailed information. In the case of normal call content, the audio output unit can also output audio containing concise information. Furthermore, in the case of urgent call content, the audio output unit can output audio that allows for a quick response. In this way, by adjusting the level of detail in the audio output unit based on the importance of the call content, important call content can be output in detail. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the generation AI evaluates the importance of the call content and outputs important call content in detail.

[0048] The voice output unit can apply different speech synthesis algorithms depending on the call category when outputting voice. For example, the voice output unit can output formal voice for business calls. It can also output casual voice for private calls. Furthermore, in the case of emergency calls, it can output voice that can respond quickly. By applying different speech synthesis algorithms depending on the call category, more appropriate voice output becomes possible. Some or all of the above processing in the voice output unit is performed using a generation AI. For example, the generation AI identifies the call category and applies the appropriate speech synthesis algorithm.

[0049] The audio output unit can determine the priority of audio output based on the timing of call submission. For example, the audio output unit will prioritize audio output for urgent call content. It can also output audio for normal call content with normal priority. Furthermore, it can prioritize audio output for important call content. This allows for priority output of urgent call content based on the timing of call submission. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the generation AI evaluates the timing of call submission and prioritizes audio output of urgent call content.

[0050] The audio output unit can adjust the order of audio output based on the relevance of the conversation. For example, the audio output unit prioritizes outputting highly relevant conversation content. It can also postpone outputting less relevant conversation content. Furthermore, the audio output unit can determine the optimal audio output order based on the relevance of the conversation content. This allows for priority output of highly relevant conversation content by adjusting the order of audio output based on the relevance of the conversation. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the generation AI evaluates the relevance of the conversation content and prioritizes outputting highly relevant conversation content.

[0051] The voice input unit can adjust the level of detail in the input based on the importance of what the other party says during voice input. For example, if the statement is important, the voice input unit will input voice information that includes detailed information. In addition, if the statement is normal, the voice input unit can input voice information that includes concise information. Furthermore, in the case of an urgent statement, the voice input unit can input voice information that allows for a quick response. In this way, by adjusting the level of detail in the input based on the importance of what the other party says, important statements can be input in detail. Some or all of the above processing in the voice input unit is performed using a generation AI. For example, the generation AI evaluates the importance of what the other party says and inputs important statements in detail.

[0052] The voice input unit can apply different speech recognition algorithms depending on the call category during voice input. For example, in the case of a business call, the voice input unit can apply a formal speech recognition algorithm. In the case of a private call, it can also apply a casual speech recognition algorithm. Furthermore, in the case of an emergency call, the voice input unit can apply a speech recognition algorithm that allows for a quick response. By applying different speech recognition algorithms depending on the call category, more appropriate voice input becomes possible. Some or all of the above processing in the voice input unit is performed using a generative AI. For example, the generative AI identifies the call category and applies the appropriate speech recognition algorithm.

[0053] The voice input unit can determine the priority of voice input based on the timing of call submission. For example, the voice input unit will prioritize voice input for urgent call content. It can also prioritize voice input for regular call content. Furthermore, it can prioritize voice input for important call content. This allows for priority voice input of urgent call content based on the timing of call submission. Some or all of the above processing in the voice input unit is performed using a generation AI. For example, the generation AI evaluates the timing of call submission and prioritizes voice input of urgent call content.

[0054] The voice input unit can adjust the order of voice input based on the relevance of the conversation. For example, the voice input unit prioritizes inputting highly relevant conversation content. It can also postpone inputting less relevant conversation content. Furthermore, the voice input unit can determine the optimal order of voice input based on the relevance of the conversation content. This allows for priority input of highly relevant conversation content by adjusting the order of voice input based on the relevance of the conversation. Some or all of the above processing in the voice input unit is performed using a generation AI. For example, the generation AI evaluates the relevance of the conversation content and prioritizes inputting highly relevant conversation content.

[0055] The notification unit can adjust the level of detail in notifications based on the importance of the call content. For example, if the call content is important, the notification unit will send a notification with detailed information. For ordinary call content, the notification unit can also send a notification with concise information. Furthermore, for urgent call content, the notification unit can send a notification that allows for a quick response. This allows for detailed notifications of important call content by adjusting the level of detail based on the importance of the call content. Some or all of the above processing in the notification unit is performed using a generation AI. For example, the generation AI evaluates the importance of the call content and provides detailed notifications of important call content.

[0056] The notification unit can apply different notification algorithms depending on the call category when a notification is sent. For example, the notification unit can send a formal notification for business calls. It can also send a casual notification for private calls. Furthermore, in the case of emergency calls, the notification unit can send a notification that allows for a quick response. By applying different notification algorithms depending on the call category, more appropriate notifications can be made. Some or all of the above processing in the notification unit is performed using generative AI. For example, the generative AI identifies the call category and applies the appropriate notification algorithm.

[0057] The notification unit can determine the priority of notifications based on the timing of call submission. For example, the notification unit will give the highest priority to urgent call content. The notification unit can also give the normal priority to regular call content. Furthermore, the notification unit can give priority to important call content. This allows for priority notification of urgent call content by determining the priority of notifications based on the timing of call submission. Some or all of the above processing in the notification unit is performed using a generation AI. For example, the generation AI evaluates the timing of call submission and prioritizes notifications for urgent call content.

[0058] The notification unit can adjust the order of notifications based on the relevance of the calls. For example, the notification unit will prioritize notifications for highly relevant call content. It can also postpone notifications for less relevant call content. Furthermore, the notification unit can determine the optimal notification order based on the relevance of the call content. This allows for priority notification of highly relevant call content by adjusting the order of notifications based on the relevance of the calls. Some or all of the above processing in the notification unit is performed using a generative AI. For example, the notification unit uses a generative AI to evaluate the relevance of the call content and prioritize notifications for highly relevant call content.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The reception system can learn the user's past behavior patterns and suggest the optimal method for receiving instructions. For example, if a user has frequently entered instructions during a specific time period in the past, the reception system will automatically display the instruction input screen at that time. Furthermore, if a user tends to enter specific instructions on certain days of the week, the system can suggest relevant instructions for those days. In addition, it can automatically display similar instructions as suggestions based on the user's past instruction history. This allows for more efficient instruction reception by learning the user's past behavior patterns.

[0061] The audio output unit can adjust the emphasis of the audio based on the importance of the call content. For example, in the case of an important call, the audio output unit will emphasize the important information. In the case of a normal call, the audio output unit can also output with a uniform tone throughout. Furthermore, in the case of an urgent call, the audio output unit can adjust the emphasis to allow for a quick response. In this way, by adjusting the emphasis of the audio based on the importance of the call content, important information can be effectively conveyed.

[0062] The notification system can adjust the timing of notifications based on the user's current activity. For example, if the user is in a meeting, the notification system will delay notifications until the meeting is over. Similarly, if the user is driving, the notification system can delay notifications until the driving is finished. Furthermore, if the user is relaxing, the notification system can send notifications immediately. This allows for more timely notifications by adjusting the timing based on the user's current activity.

[0063] The reception desk can analyze the user's past instruction history and select the optimal reception method. For example, the reception desk can automatically display instructions that the user has frequently entered in the past as suggestions. It can also prioritize suggesting reception methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest instructions to be used during specific time periods based on the user's past instruction history. This allows the system to select the optimal reception method by analyzing the user's past instruction history.

[0064] The reception unit can filter instructions based on the user's current situation and areas of interest when receiving them. For example, the reception unit can prioritize displaying instructions relevant to the user's current situation. It can also filter and display relevant instructions based on the user's areas of interest. Furthermore, the reception unit can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows the system to prioritize receiving highly relevant instructions by filtering based on the user's current situation and areas of interest.

[0065] The reception system can prioritize receiving instructions based on the user's geographical location. For example, if the user is in a specific location, the reception system will prioritize instructions related to that location. The reception system can also filter and display relevant instructions based on the user's current location. Furthermore, the reception system can suggest the most appropriate instructions, taking into account the user's geographical location. This allows for more appropriate instruction reception by prioritizing instructions based on the user's geographical location.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The reception desk receives instructions from the user. User instructions include voice instructions, text instructions, and gesture instructions. The reception desk receives voice instructions via a microphone and converts them into text data using speech recognition technology. It can also directly receive text instructions, and can detect gesture instructions with a camera and analyze their content using gesture recognition technology. Step 2: The generation unit uses a generation AI to generate call content based on the instructions received by the reception unit. The generation unit can also use a text generation AI (e.g., LLM) to generate call content as text and generate appropriate responses based on what the other party says. Step 3: The audio output unit synthesizes the call content generated by the generation unit and outputs it as speech. The audio output unit can output the call content generated using TTS (Text-to-Speech) technology as speech, or it can output it as natural-sounding speech using a speech synthesis engine. Step 4: The voice input unit takes the other party's speech as voice input and converts it into text. The voice input unit can also use ASR (Automatic Speech Recognition) technology to convert the other party's speech into text data and recognize it with high accuracy using a speech recognition engine. Step 5: The notification unit summarizes the call content into a summary document and notifies the user. The notification unit uses a summarization algorithm to summarize the call content and extract the most important information. It can also use generative AI to concisely summarize the call content.

[0068] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system that autonomously handles incoming and outgoing phone calls using generative AI. In this system, the user inputs instructions through a smartphone application, and the generative AI makes a call and conducts the conversation based on those instructions. The content of the conversation is summarized by the generative AI and notified to the user's smartphone. The generative AI also handles incoming calls and summarizes the content of the conversation in a text document, notifying the user. This mechanism makes it possible for people who do not have time to make phone calls or who cannot use the phone due to a disability to handle phone calls. For example, the user inputs an instruction such as "I would like to make a reservation at a restaurant" through a smartphone application. This instruction is sent to the generative AI. Next, the generative AI makes a call based on the input instruction. The generative AI generates the content of the conversation as text and outputs it as voice to the other party through speech synthesis. For example, the generative AI outputs as voice the content "Please make a reservation for 3 PM on August 20th." The other party's statements are converted into text through voice input and input to the generative AI. The generating AI generates an appropriate response based on what the caller says and outputs it back to the caller through speech synthesis. For example, if the caller asks, "How many people are in your party?", the generating AI will respond, "Two adults." When the call ends, the generating AI summarizes the call content in a summary and notifies the user's smartphone. For example, the notification might say, "Your restaurant reservation is complete. Electronic payment is available." The generating AI also handles incoming calls. It answers incoming calls and summarizes the call content in a summary, notifying the user. For example, it might say, "You have a call from the bank regarding a credit card campaign." This system makes it possible for people who don't have time to make calls or who cannot use the phone due to disabilities to receive phone calls. It also helps deter spam and fraudulent calls and reduces the labor costs and time spent on answering calls. As a result, the AI ​​agent system can autonomously handle both incoming and outgoing calls.

[0069] The AI ​​agent system according to this embodiment comprises a reception unit, a generation unit, an audio output unit, an audio input unit, and a notification unit. The reception unit receives instructions from the user. Instructions from the user include, but are not limited to, voice instructions, text instructions, and gesture instructions. For example, the reception unit receives voice instructions with a microphone and converts them into text data using speech recognition technology. The reception unit can also directly receive text instructions. Furthermore, the reception unit can detect gesture instructions with a camera and analyze the content of the instructions using gesture recognition technology. The generation unit generates call content based on the instructions received by the reception unit using a generation AI. For example, the generation unit generates call content as text using a text generation AI (e.g., LLM). The generation unit can also generate an appropriate response based on what the other party says using a generation AI. For example, the generation AI generates call content such as "Please make a reservation for 3 PM on August 20th" based on the user's instructions. The audio output unit synthesizes the call content generated by the generation unit and outputs it. The audio output unit outputs the generated call content as audio, for example, using TTS (Text-to-Speech) technology. The audio output unit can also output the generated call content as natural-sounding audio using a speech synthesis engine. For example, the audio output unit inputs the generated call content into a speech synthesis engine and outputs it as audio data. The audio input unit takes the other party's speech as audio input and converts it into text. The audio input unit converts the other party's speech into text data using, for example, ASR (Automatic Speech Recognition) technology. The audio input unit can also recognize the other party's speech with high accuracy using a speech recognition engine. For example, the audio input unit receives the other party's speech via a microphone, inputs it into a speech recognition engine, and outputs it as text data. The notification unit summarizes the call content into a summary document and notifies the user. The notification unit summarizes the call content using, for example, a summarization algorithm and extracts highly important information. The notification unit can also concisely summarize the call content using a generation AI. For example, the notification unit inputs the call content into a generation AI and outputs a summarized text.As a result, the AI ​​agent system according to the embodiment can generate call content based on user instructions, synthesize and output it as speech, and convert the other party's statements into text for notification.

[0070] The reception desk receives instructions from users. These instructions may include, but are not limited to, voice, text, and gesture instructions. For example, the reception desk receives voice instructions via a microphone and converts them into text data using speech recognition technology. Specifically, a deep learning-based speech recognition model is used. This model has been trained on a large amount of voice data and can convert voice to text with high accuracy. For example, if a user gives the instruction "Cancel tomorrow's meeting," the reception desk receives this voice via a microphone and converts it into text data "Cancel tomorrow's meeting" using the speech recognition model. The reception desk can also directly receive text instructions. If a user enters text using a keyboard or touchscreen, the reception desk receives the text directly and passes it on to the next process. Furthermore, the reception desk can detect gesture instructions with a camera and analyze the content of the instructions using gesture recognition technology. The gesture recognition technology used combines computer vision and machine learning. For example, if a user waves their hand, the camera captures the motion, and the gesture recognition model analyzes the motion to recognize the instruction "wave hand." This allows the reception desk to support a variety of input methods, such as voice, text, and gestures, enabling it to flexibly receive user instructions.

[0071] The generation unit uses a generation AI to generate call content based on instructions received by the reception unit. For example, the generation unit uses a text generation AI (e.g., LLM) to generate the call content as text. Specifically, the generation AI analyzes the user's instructions and utilizes natural language processing techniques to generate appropriate call content. For example, if a user instructs, "Please make a reservation for 3 PM on August 20th," the generation AI analyzes this instruction and generates call content including reservation details. The generation unit can also use the generation AI to generate appropriate responses based on what the other party says. For example, if the other party asks, "Are you free that day?", the generation AI analyzes the question and generates an appropriate response such as, "Yes, 3 PM on August 20th is available." The generation AI has learned from a large amount of conversational data beforehand, enabling it to generate natural responses appropriate to the context. Furthermore, the generation unit can perform grammar checks and style adjustments to output the generated call content in an appropriate format. This allows the generation unit to generate high-quality call content based on user instructions, improving the overall communication capabilities of the system.

[0072] The audio output unit synthesizes and outputs the call content generated by the generation unit. For example, the audio output unit outputs the call content generated using TTS (Text-to-Speech) technology as audio. Specifically, TTS technology uses a speech synthesis engine to convert text data into audio data. This engine can reproduce natural pronunciation and intonation based on pre-recorded audio data. For example, if the generation unit generates the call content "Please make a reservation for 3 PM on August 20th," the audio output unit inputs this text data into the TTS engine and outputs it as natural speech. The audio output unit can also output the generated call content as natural speech using the speech synthesis engine. The speech synthesis engine can select different voice qualities and speaking styles according to the user's preferences. For example, it can provide various voice styles such as male or female voices, calm speaking styles, and energetic speaking styles. This allows the audio output unit to provide the generated call content as natural speech that is easy for the user to understand. Furthermore, the audio output unit also has a function to adjust the speed and volume of the audio, allowing for customization according to user needs. This allows the audio output unit to provide users with high-quality audio output, improving the overall user experience of the system.

[0073] The voice input unit takes the other party's speech as voice input and converts it into text. For example, the voice input unit uses ASR (Automatic Speech Recognition) technology to convert the other party's speech into text data. Specifically, ASR technology uses a speech recognition engine to analyze the voice data, extract voice features, and convert them into text. This engine has learned from a large amount of voice data and can convert speech to text with high accuracy. For example, if the other party says, "Are you free that day?", the voice input unit receives this voice via the microphone and uses the speech recognition engine to convert it into text data: "Are you free that day?". Furthermore, the voice input unit can also recognize the other party's speech with high accuracy using the speech recognition engine. The speech recognition engine performs preprocessing such as noise reduction and speech normalization to improve the quality of the voice data. This allows the voice input unit to accurately convert the other party's speech into text data and pass it on to the next processing step. In addition, the voice input unit can support multiple languages ​​and dialects, achieving high-accuracy speech recognition even in different language environments. This allows the voice input unit to accurately recognize what the other party is saying, improving the overall communication capabilities of the system.

[0074] The notification unit summarizes the call content into a summary document and notifies the user. For example, the notification unit uses a summarization algorithm to summarize the call content and extract highly important information. Specifically, the summarization algorithm analyzes the text data of the call content, extracts important keywords and phrases, and generates a concise summary. For example, if the call content is "Please make a reservation for 3 PM on August 20th. I have no other plans that day, so it's fine," the notification unit will generate a summary such as "Make a reservation for 3 PM on August 20th." The notification unit can also use generative AI to concisely summarize the call content. Generative AI utilizes natural language processing technology to understand the context of the call content, extract important information, and generate a summary. For example, if the call content is "Please make a reservation for 3 PM on August 20th. I have no other plans that day, so it's fine," the generative AI will generate a summary such as "Make a reservation for 3 PM on August 20th." In this way, the notification unit can concisely notify the user of important information and help the user understand it. Furthermore, the notification unit provides various notification methods to inform users of summarized call content. For example, it can quickly deliver summarized call content to users using smartphone push notifications, email, SMS, etc. This allows the notification unit to quickly and reliably notify users of important information, improving the overall usability of the system.

[0075] The generation unit can generate conversation content as text using a generation AI. For example, the generation unit uses a text generation AI (e.g., LLM) to generate conversation content as text. For example, the generation unit's generation AI can generate conversation content such as "Please make a reservation for 3 PM on August 20th." The generation unit can also use the generation AI to generate appropriate responses based on what the other party says. For example, if the other party asks "How many people are in your party?", the generation unit will generate a response such as "Two adults." This improves the accuracy of the conversation content by generating it as text using the generation AI. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit inputs user instructions into the generation AI and outputs the generated conversation content.

[0076] The audio output unit can synthesize and output the generated call content. For example, the audio output unit can output the generated call content as audio using TTS (Text-to-Speech) technology. For example, the audio output unit can input the generated call content into a speech synthesis engine and output it as audio data. Furthermore, the audio output unit can synthesize and output the call content generated using a generation AI. For example, the audio output unit inputs the call content generated by the generation AI into a speech synthesis engine and outputs it as audio data. This allows the generated call content to be transmitted to the other party as audio by synthesizing and outputting it. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the audio output unit inputs the call content generated by the generation AI into a speech synthesis engine and outputs it as audio data.

[0077] The voice input unit can input the other party's speech and convert it into text. For example, the voice input unit uses ASR (Automatic Speech Recognition) technology to convert the other party's speech into text data. For example, the voice input unit receives the other party's speech via a microphone, inputs it into a speech recognition engine, and outputs it as text data. The voice input unit can also use a generative AI to input the other party's speech and convert it into text. For example, the generative AI inputs the other party's speech into a speech recognition engine and outputs it as text data. This allows the content of a call to be recorded as text by inputting the other party's speech and converting it into text. Some or all of the above processing in the voice input unit is performed using a generative AI. For example, the generative AI inputs the other party's speech into a speech recognition engine and outputs it as text data.

[0078] The notification unit can summarize the call content into a summary document and notify the user. For example, the notification unit can summarize the call content using a summarization algorithm and extract highly important information. For example, the notification unit can input the call content into a generation AI and output a summarized document. The notification unit can also use the generation AI to concisely summarize the call content. For example, the notification unit can have the generation AI summarize the call content, extract important information, and notify the user. This allows the user to easily grasp the call content by summarizing it into a summary document and notifying them of it. Some or all of the above processing in the notification unit is performed using the generation AI. For example, the notification unit can have the generation AI summarize the call content, extract important information, and notify the user.

[0079] The reception unit can estimate the user's emotions and adjust the instruction reception method based on the estimated emotions. For example, if the user is stressed, the reception unit can provide a simple interface and minimize the input steps. If the user is relaxed, the reception unit can also provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input to allow for quick instruction input. This allows for more appropriate instruction reception by adjusting the instruction reception method according to 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 processing in the reception unit is performed using generative AI. For example, the reception unit uses generative AI to estimate the user's emotions and adjust the instruction reception method based on the estimated emotions.

[0080] The reception desk can analyze the user's past instruction history and select the optimal reception method. For example, the reception desk can automatically display instructions that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting reception methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest instructions to be used during specific time periods based on the user's past instruction history. In this way, the reception desk can select the optimal reception method by analyzing the user's past instruction history. Some or all of the above processes in the reception desk are performed using AI. For example, the reception desk uses AI to analyze the user's past instruction history and select the optimal reception method.

[0081] The reception unit can filter instructions based on the user's current situation and areas of interest when receiving them. For example, the reception unit prioritizes displaying relevant instructions based on the user's current situation. It can also filter and display relevant instructions based on the user's areas of interest. Furthermore, the reception unit can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows for the priority reception of highly relevant instructions by filtering based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit uses AI to analyze the user's current situation and areas of interest and filter and display relevant instructions.

[0082] The reception desk can estimate the user's emotions and determine the priority of instructions to receive based on the estimated emotions. For example, if the user is stressed, the reception desk will prioritize important instructions. If the user is relaxed, the reception desk may also prioritize detailed instructions. Furthermore, if the user is in a hurry, the reception desk may prioritize instructions that require quick processing. This allows for the prioritization of important instructions by determining the priority of instructions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 reception desk is performed using generative AI. For example, the reception desk uses generative AI to estimate the user's emotions and determines the priority of instructions based on the estimated emotions.

[0083] The reception unit can prioritize receiving instructions that are highly relevant based on the user's geographical location. For example, if the user is in a specific location, the reception unit will prioritize receiving instructions related to that location. The reception unit can also filter and display relevant instructions based on the user's current location. Furthermore, the reception unit can suggest the most appropriate instructions, taking into account the user's geographical location. This allows for more appropriate instruction reception by prioritizing highly relevant instructions based on the user's geographical location. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit uses AI to analyze the user's geographical location and filter and display relevant instructions.

[0084] The reception unit can analyze the user's social media activity when receiving instructions and accept relevant instructions. For example, the reception unit can prioritize receiving relevant instructions based on the user's social media activity. The reception unit can also analyze the user's social media activity and suggest the most appropriate instructions. Furthermore, the reception unit can filter and display relevant instructions based on the user's social media activity. This allows for the priority acceptance of relevant instructions by analyzing the user's social media activity. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit uses AI to analyze the user's social media activity and filter and display relevant instructions.

[0085] The generation unit can estimate the user's emotions and adjust the method of generating the call content based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate call content that proceeds at a relaxed pace. If the user is in a hurry, the generation unit can also generate call content that emphasizes the shortest route. Furthermore, if the user is excited, the generation unit can generate call content with visually stimulating effects. In this way, by adjusting the method of generating the call content according to the user's emotions, more appropriate call content can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 generation unit is performed using the generation AI. For example, the generation unit uses the generation AI to estimate the user's emotions and adjusts the method of generating the call content based on the estimated emotions.

[0086] The generation unit can adjust the level of detail generated based on the importance of the call when generating call content. For example, in the case of an important call, the generation unit generates call content that includes detailed information. In the case of a normal call, the generation unit can also generate call content that includes concise information. Furthermore, in the case of an urgent call, the generation unit can generate call content that allows for a quick response. In this way, by adjusting the level of detail generated based on the importance of the call, important call content can be generated in detail. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit uses the generation AI to evaluate the importance of the call and generate detailed important call content.

[0087] The generation unit can apply different generation algorithms depending on the call category when generating call content. For example, in the case of a business call, the generation unit generates formal call content. It can also generate casual call content for private calls. Furthermore, in the case of an emergency call, the generation unit can generate call content that allows for a quick response. By applying different generation algorithms depending on the call category, more appropriate call content can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI identifies the call category and applies the appropriate generation algorithm.

[0088] The generation unit can estimate the user's emotions and adjust the length of the call content based on the estimated emotions. For example, if the user is in a hurry, the generation unit can generate a short, concise call. If the user is relaxed, the generation unit can also generate a longer call with detailed explanations. Furthermore, if the user is excited, the generation unit can generate a call with visually stimulating effects. This allows for the generation of more appropriate call content by adjusting the length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation 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 generation unit is performed using the generation AI. For example, the generation unit uses the generation AI to estimate the user's emotions and adjust the length of the call content based on the estimated emotions.

[0089] The generation unit can determine the generation priority based on the call submission timing when generating call content. For example, the generation unit will generate urgent call content with the highest priority. The generation unit can also generate normal call content with normal priority. Furthermore, the generation unit can prioritize the generation of important call content. This allows for the priority generation of urgent call content by determining the generation priority based on the call submission timing. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit uses the generation AI to evaluate the call submission timing and prioritize the generation of urgent call content.

[0090] The generation unit can adjust the generation order based on the relevance of the calls when generating call content. For example, the generation unit can prioritize generating highly relevant call content. It can also postpone generating less relevant call content. Furthermore, the generation unit can determine the optimal generation order based on the relevance of the call content. This allows for the priority generation of highly relevant call content by adjusting the generation order based on the relevance of the calls. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit uses the generation AI to evaluate the relevance of the call content and prioritize the generation of highly relevant call content.

[0091] The voice output unit can estimate the user's emotions and adjust the expression of the voice output based on the estimated emotions. For example, if the user is nervous, the voice output unit will output in a calm voice. It can also output in a cheerful voice if the user is relaxed. Furthermore, if the user is in a hurry, the voice output unit can output quickly and concisely. This allows for more appropriate voice output by adjusting the expression of the voice output according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voice output unit is performed using generative AI. For example, the voice output unit uses generative AI to estimate the user's emotions and adjusts the expression of the voice output based on the estimated emotions.

[0092] The audio output unit can adjust the level of detail in the audio output based on the importance of the call content. For example, in the case of important call content, the audio output unit will output audio containing detailed information. In the case of normal call content, the audio output unit can also output audio containing concise information. Furthermore, in the case of urgent call content, the audio output unit can output audio that allows for a quick response. In this way, by adjusting the level of detail in the audio output unit based on the importance of the call content, important call content can be output in detail. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the generation AI evaluates the importance of the call content and outputs important call content in detail.

[0093] The voice output unit can apply different speech synthesis algorithms depending on the call category when outputting voice. For example, the voice output unit can output formal voice for business calls. It can also output casual voice for private calls. Furthermore, in the case of emergency calls, it can output voice that can respond quickly. By applying different speech synthesis algorithms depending on the call category, more appropriate voice output becomes possible. Some or all of the above processing in the voice output unit is performed using a generation AI. For example, the generation AI identifies the call category and applies the appropriate speech synthesis algorithm.

[0094] The audio output unit can estimate the user's emotions and adjust the length of the audio output based on the estimated emotions. For example, if the user is in a hurry, the audio output unit will produce a short, concise audio output. If the user is relaxed, the audio output unit can produce a longer audio output that includes detailed explanations. Furthermore, if the user is excited, the audio output unit can produce an audio output with visually stimulating effects. By adjusting the length of the audio output according to the user's emotions, more appropriate audio output becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the audio output unit is performed using generative AI. For example, the audio output unit uses generative AI to estimate the user's emotions and adjust the length of the audio output based on the estimated emotions.

[0095] The audio output unit can determine the priority of audio output based on the timing of call submission. For example, the audio output unit will prioritize audio output for urgent call content. It can also output audio for normal call content with normal priority. Furthermore, it can prioritize audio output for important call content. This allows for priority output of urgent call content based on the timing of call submission. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the generation AI evaluates the timing of call submission and prioritizes audio output of urgent call content.

[0096] The audio output unit can adjust the order of audio output based on the relevance of the conversation. For example, the audio output unit prioritizes outputting highly relevant conversation content. It can also postpone outputting less relevant conversation content. Furthermore, the audio output unit can determine the optimal audio output order based on the relevance of the conversation content. This allows for priority output of highly relevant conversation content by adjusting the order of audio output based on the relevance of the conversation. Some or all of the above processing in the audio output unit is performed using a generation AI. For example, the generation AI evaluates the relevance of the conversation content and prioritizes outputting highly relevant conversation content.

[0097] The voice input unit can estimate the user's emotions and adjust the voice input method based on the estimated emotions. For example, if the user is nervous, the voice input unit can use a calm voice for voice input. If the user is relaxed, the voice input unit can use a cheerful voice for voice input. Furthermore, if the user is in a hurry, the voice input unit can use a quick and concise voice input. This allows for more appropriate voice input by adjusting the voice input method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voice input unit is performed using generative AI. For example, the voice input unit uses generative AI to estimate the user's emotions and adjust the voice input method based on the estimated emotions.

[0098] The voice input unit can adjust the level of detail in the input based on the importance of what the other party says during voice input. For example, if the statement is important, the voice input unit will input voice information that includes detailed information. In addition, if the statement is normal, the voice input unit can input voice information that includes concise information. Furthermore, in the case of an urgent statement, the voice input unit can input voice information that allows for a quick response. In this way, by adjusting the level of detail in the input based on the importance of what the other party says, important statements can be input in detail. Some or all of the above processing in the voice input unit is performed using a generation AI. For example, the generation AI evaluates the importance of what the other party says and inputs important statements in detail.

[0099] The voice input unit can apply different speech recognition algorithms depending on the call category during voice input. For example, in the case of a business call, the voice input unit can apply a formal speech recognition algorithm. In the case of a private call, it can also apply a casual speech recognition algorithm. Furthermore, in the case of an emergency call, the voice input unit can apply a speech recognition algorithm that allows for a quick response. By applying different speech recognition algorithms depending on the call category, more appropriate voice input becomes possible. Some or all of the above processing in the voice input unit is performed using a generative AI. For example, the generative AI identifies the call category and applies the appropriate speech recognition algorithm.

[0100] The voice input unit can estimate the user's emotions and determine the priority of voice input based on the estimated emotions. For example, if the user is in a hurry, the voice input unit will prioritize inputting important statements. It can also prioritize inputting detailed statements if the user is relaxed. Furthermore, if the user is excited, the voice input unit can add visually stimulating effects to the voice input. This allows for prioritizing important statements by determining the priority of voice input according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 voice input unit is performed using generative AI. For example, the voice input unit uses generative AI to estimate the user's emotions and determine the priority of voice input based on the estimated emotions.

[0101] The voice input unit can determine the priority of voice input based on the timing of call submission. For example, the voice input unit will prioritize voice input for urgent call content. It can also prioritize voice input for regular call content. Furthermore, it can prioritize voice input for important call content. This allows for priority voice input of urgent call content based on the timing of call submission. Some or all of the above processing in the voice input unit is performed using a generation AI. For example, the generation AI evaluates the timing of call submission and prioritizes voice input of urgent call content.

[0102] The voice input unit can adjust the order of voice input based on the relevance of the conversation. For example, the voice input unit prioritizes inputting highly relevant conversation content. It can also postpone inputting less relevant conversation content. Furthermore, the voice input unit can determine the optimal order of voice input based on the relevance of the conversation content. This allows for priority input of highly relevant conversation content by adjusting the order of voice input based on the relevance of the conversation. Some or all of the above processing in the voice input unit is performed using a generation AI. For example, the generation AI evaluates the relevance of the conversation content and prioritizes inputting highly relevant conversation content.

[0103] The notification unit can estimate the user's emotions and adjust the way notifications are expressed based on those emotions. For example, if the user is tense, the notification unit will use calm language. If the user is relaxed, the notification unit can use cheerful language. Furthermore, if the user is in a hurry, the notification unit can use quick and concise language. By adjusting the way notifications are expressed according to the user's emotions, more appropriate notifications can be provided. Emotion estimation is achieved using an emotion estimation function, such as 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 notification unit is performed using generative AI. For example, the notification unit uses generative AI to estimate the user's emotions and adjusts the way notifications are expressed based on those emotions.

[0104] The notification unit can adjust the level of detail in notifications based on the importance of the call content. For example, if the call content is important, the notification unit will send a notification with detailed information. For ordinary call content, the notification unit can also send a notification with concise information. Furthermore, for urgent call content, the notification unit can send a notification that allows for a quick response. This allows for detailed notifications of important call content by adjusting the level of detail based on the importance of the call content. Some or all of the above processing in the notification unit is performed using a generation AI. For example, the generation AI evaluates the importance of the call content and provides detailed notifications of important call content.

[0105] The notification unit can apply different notification algorithms depending on the call category when a notification is sent. For example, the notification unit can send a formal notification for business calls. It can also send a casual notification for private calls. Furthermore, in the case of emergency calls, the notification unit can send a notification that allows for a quick response. By applying different notification algorithms depending on the call category, more appropriate notifications can be made. Some or all of the above processing in the notification unit is performed using generative AI. For example, the generative AI identifies the call category and applies the appropriate notification algorithm.

[0106] The notification unit can estimate the user's emotions and determine notification priorities based on those emotions. For example, if the user is in a hurry, the notification unit will prioritize important notifications. It can also prioritize detailed notifications if the user is relaxed. Furthermore, if the user is excited, the notification unit can deliver notifications with visually stimulating effects. This allows for prioritizing important notifications based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 notification unit is performed using generative AI. For example, the notification unit uses generative AI to estimate the user's emotions and determines notification priorities based on those emotions.

[0107] The notification unit can determine the priority of notifications based on the timing of call submission. For example, the notification unit will give the highest priority to urgent call content. The notification unit can also give the normal priority to regular call content. Furthermore, the notification unit can give priority to important call content. This allows for priority notification of urgent call content by determining the priority of notifications based on the timing of call submission. Some or all of the above processing in the notification unit is performed using a generation AI. For example, the generation AI evaluates the timing of call submission and prioritizes notifications for urgent call content.

[0108] The notification unit can adjust the order of notifications based on the relevance of the calls. For example, the notification unit will prioritize notifications for highly relevant call content. It can also postpone notifications for less relevant call content. Furthermore, the notification unit can determine the optimal notification order based on the relevance of the call content. This allows for priority notification of highly relevant call content by adjusting the order of notifications based on the relevance of the calls. Some or all of the above processing in the notification unit is performed using a generative AI. For example, the notification unit uses a generative AI to evaluate the relevance of the call content and prioritize notifications for highly relevant call content.

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

[0110] The reception system can learn the user's past behavior patterns and suggest the optimal method for receiving instructions. For example, if a user has frequently entered instructions during a specific time period in the past, the reception system will automatically display the instruction input screen at that time. Furthermore, if a user tends to enter specific instructions on certain days of the week, the system can suggest relevant instructions for those days. In addition, it can automatically display similar instructions as suggestions based on the user's past instruction history. This allows for more efficient instruction reception by learning the user's past behavior patterns.

[0111] The generation unit can estimate the user's emotions and adjust the tone of the call content based on the estimated emotions. For example, if the user is nervous, the generation unit can generate the call content in a calm tone. If the user is relaxed, the generation unit can generate the call content in a cheerful tone. Furthermore, if the user is in a hurry, the generation unit can generate the call content in a quick and concise tone. In this way, by adjusting the tone of the call content according to the user's emotions, more appropriate call content can be generated. Emotion estimation is achieved using an emotion engine or generative AI.

[0112] The audio output unit can adjust the emphasis of the audio based on the importance of the call content. For example, in the case of an important call, the audio output unit will emphasize the important information. In the case of a normal call, the audio output unit can also output with a uniform tone throughout. Furthermore, in the case of an urgent call, the audio output unit can adjust the emphasis to allow for a quick response. In this way, by adjusting the emphasis of the audio based on the importance of the call content, important information can be effectively conveyed.

[0113] The voice input unit can estimate the user's emotions and adjust the voice input feedback method based on the estimated emotions. For example, if the user is nervous, the voice input unit will provide calm feedback. If the user is relaxed, the voice input unit can provide cheerful feedback. Furthermore, if the user is in a hurry, the voice input unit can provide quick and concise feedback. By adjusting the voice input feedback method according to the user's emotions, more appropriate voice input becomes possible. Emotion estimation is achieved using an emotion engine or generative AI.

[0114] The notification system can adjust the timing of notifications based on the user's current activity. For example, if the user is in a meeting, the notification system will delay notifications until the meeting is over. Similarly, if the user is driving, the notification system can delay notifications until the driving is finished. Furthermore, if the user is relaxing, the notification system can send notifications immediately. This allows for more timely notifications by adjusting the timing based on the user's current activity.

[0115] The reception system can estimate the user's emotions and adjust how instructions are received based on those estimates. For example, if the user is stressed, it can provide a simple interface and minimize the input steps. If the user is relaxed, it can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, it can prioritize voice input to allow for quick instruction input. This allows for more appropriate instruction reception by adjusting the instruction reception method according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI.

[0116] The reception desk can analyze the user's past instruction history and select the optimal reception method. For example, the reception desk can automatically display instructions that the user has frequently entered in the past as suggestions. It can also prioritize suggesting reception methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest instructions to be used during specific time periods based on the user's past instruction history. This allows the system to select the optimal reception method by analyzing the user's past instruction history.

[0117] The reception unit can filter instructions based on the user's current situation and areas of interest when receiving them. For example, the reception unit can prioritize displaying instructions relevant to the user's current situation. It can also filter and display relevant instructions based on the user's areas of interest. Furthermore, the reception unit can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows the system to prioritize receiving highly relevant instructions by filtering based on the user's current situation and areas of interest.

[0118] The reception desk can estimate the user's emotions and determine the priority of instructions to process based on those emotions. For example, if the user is stressed, the reception desk will prioritize important instructions. If the user is relaxed, it may prioritize detailed instructions. Furthermore, if the user is in a hurry, it may prioritize instructions that require quick processing. This allows for the priority of important instructions by prioritizing them according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI.

[0119] The reception system can prioritize receiving instructions based on the user's geographical location. For example, if the user is in a specific location, the reception system will prioritize instructions related to that location. The reception system can also filter and display relevant instructions based on the user's current location. Furthermore, the reception system can suggest the most appropriate instructions, taking into account the user's geographical location. This allows for more appropriate instruction reception by prioritizing instructions based on the user's geographical location.

[0120] The following briefly describes the processing flow for example form 2.

[0121] Step 1: The reception desk receives instructions from the user. User instructions include voice instructions, text instructions, and gesture instructions. The reception desk receives voice instructions via a microphone and converts them into text data using speech recognition technology. It can also directly receive text instructions, and can detect gesture instructions with a camera and analyze their content using gesture recognition technology. Step 2: The generation unit uses a generation AI to generate call content based on the instructions received by the reception unit. The generation unit can also use a text generation AI (e.g., LLM) to generate call content as text and generate appropriate responses based on what the other party says. Step 3: The audio output unit synthesizes the call content generated by the generation unit and outputs it as speech. The audio output unit can output the call content generated using TTS (Text-to-Speech) technology as speech, or it can output it as natural-sounding speech using a speech synthesis engine. Step 4: The voice input unit takes the other party's speech as voice input and converts it into text. The voice input unit can also use ASR (Automatic Speech Recognition) technology to convert the other party's speech into text data and recognize it with high accuracy using a speech recognition engine. Step 5: The notification unit summarizes the call content into a summary document and notifies the user. The notification unit uses a summarization algorithm to summarize the call content and extract the most important information. It can also use generative AI to concisely summarize the call content.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating 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.

[0123] 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.

[0124] 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.

[0125] Each of the multiple elements described above, including the reception unit, generation unit, voice output unit, voice input unit, and notification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives user instructions using the microphone 38B or touch panel 38A of the smart device 14. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates call content using generation AI. The voice output unit outputs the generated call content as voice using the speaker 40B of the smart device 14. The voice input unit inputs the words of the person on the other end of the call using the microphone 38B of the smart device 14 and converts them into text data using the specific processing unit 290 of the data processing unit 12. The notification unit summarizes the call content using the specific processing unit 290 of the data processing unit 12 and notifies the display 40A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating 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.

[0139] 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.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is 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.

[0141] Each of the multiple elements described above, including the reception unit, generation unit, voice output unit, voice input unit, and notification unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives user instructions using the microphone 238 of the smart glasses 214. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates call content using generation AI. The voice output unit outputs the generated call content as voice using the speaker 240 of the smart glasses 214. The voice input unit inputs the words of the person being spoken to using the microphone 238 of the smart glasses 214 and converts them into text data using the specific processing unit 290 of the data processing unit 12. The notification unit summarizes the call content using the specific processing unit 290 of the data processing unit 12 and notifies the smart glasses 214's display. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.).

[0154] 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.

[0155] 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.

[0156] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0157] Each of the multiple elements described above, including the reception unit, generation unit, voice output unit, voice input unit, and notification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives user instructions using the microphone 238 of the headset terminal 314. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates call content using generation AI. The voice output unit outputs the generated call content as voice using the speaker 240 of the headset terminal 314. The voice input unit inputs the words of the person on the other end of the call using the microphone 238 of the headset terminal 314 and converts them into text data using the specific processing unit 290 of the data processing unit 12. The notification unit summarizes the call content using the specific processing unit 290 of the data processing unit 12 and notifies the display 343 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.).

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the 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.

[0172] 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.

[0173] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is 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.

[0174] Each of the multiple elements described above, including the reception unit, generation unit, voice output unit, voice input unit, and notification unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives user instructions using the microphone 238 of the robot 414. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates the content of the conversation using a generation AI. The voice output unit outputs the generated content of the conversation as voice using the speaker 240 of the robot 414. The voice input unit inputs the words of the person on the other end of the conversation using the microphone 238 of the robot 414 and converts them into text data using the specific processing unit 290 of the data processing unit 12. The notification unit summarizes the content of the conversation using the specific processing unit 290 of the data processing unit 12 and notifies the robot 414's display. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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."

[0181] 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.

[0182] 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.

[0183] 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.

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

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] (Note 1) A reception desk that receives instructions from users, A generation unit that generates call content based on instructions received by the reception unit, A voice output unit that synthesizes and outputs the call content generated by the generation unit, A voice input unit that takes the other party's speech as voice input and converts it into text, It includes a notification unit that summarizes the content of a call into a document and notifies the user. A system characterized by the following features. (Note 2) The generating unit is The AI ​​generates the content of the call as text. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned audio output unit is The generated call content is synthesized into speech and output. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned audio input unit is The other party's speech is entered into voice input and converted into text. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, The call content is summarized in a document and notified to the user. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is It estimates the user's emotions and adjusts how instructions are received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is Analyze the user's past instruction history and select the optimal reception method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When receiving instructions, filtering is performed based on the user's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is It estimates the user's emotions and determines the priority of instructions to accept based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving instructions, the system prioritizes accepting instructions that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving instructions, the system analyzes the user's social media activity and accepts relevant instructions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is The system estimates the user's emotions and adjusts how call content is generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is When generating call transcripts, adjust the level of detail based on the importance of the call. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating call content, different generation algorithms are applied depending on the call category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is It estimates the user's emotions and adjusts the length of the call based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating call content, the generation priority is determined based on when the call was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating call content, the generation order is adjusted based on the relevance of the call. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned audio output unit is It estimates the user's emotions and adjusts the way the voice output is expressed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned audio output unit is When outputting audio, the level of detail in the audio is adjusted based on the importance of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned audio output unit is When outputting audio, different speech synthesis algorithms are applied depending on the call category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned audio output unit is It estimates the user's emotions and adjusts the length of the audio output based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned audio output unit is When outputting audio, the priority of audio output is determined based on when the call was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned audio output unit is When outputting audio, adjust the order of audio output based on the relevance of the call. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned audio input unit is It estimates the user's emotions and adjusts the voice input method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned audio input unit is When using voice input, the level of detail is adjusted based on the importance of what the other party says. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned audio input unit is When using voice input, different speech recognition algorithms are applied depending on the call category. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned audio input unit is It estimates the user's emotions and determines the priority of voice input based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned audio input unit is When using voice input, the system prioritizes voice input based on when the call was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned audio input unit is When using voice input, the order of voice input is adjusted based on the relevance of the call. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, It estimates the user's emotions and adjusts the way notifications are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned notification unit, When a notification is sent, the level of detail in the notification will be adjusted based on the importance of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned notification unit, When sending notifications, different notification algorithms are applied depending on the call category. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned notification unit, It estimates the user's emotions and prioritizes notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned notification unit, When notifying, the notification priority is determined based on when the call was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned notification unit, When sending notifications, adjust the order of notifications based on the relevance of the call. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0194] 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 reception desk that receives instructions from users, A generation unit that generates call content based on instructions received by the reception unit, A voice output unit that synthesizes and outputs the call content generated by the generation unit, A voice input unit that takes the other party's speech as voice input and converts it into text, It includes a notification unit that summarizes the content of a call into a document and notifies the user. A system characterized by the following features.

2. The generating unit is The AI ​​generates the content of the call as text. The system according to feature 1.

3. The aforementioned audio output unit is The generated call content is synthesized into speech and output. The system according to feature 1.

4. The aforementioned audio input unit is The other party's speech is entered into voice input and converted into text. The system according to feature 1.

5. The aforementioned notification unit, The call content is summarized in a document and notified to the user. The system according to feature 1.

6. The aforementioned reception unit is It estimates the user's emotions and adjusts how instructions are received based on those estimated emotions. The system according to feature 1.

7. The aforementioned reception unit is Analyze the user's past instruction history and select the optimal reception method. The system according to feature 1.

8. The aforementioned reception unit is When receiving instructions, filtering is performed based on the user's current situation and areas of interest. The system according to feature 1.

Images