system

Abstract

The system according to this embodiment aims to allow users to make phone calls without being restricted by time or location, and without stress. [Solution] The system according to the embodiment comprises a reception unit, a prediction unit, a generation unit, a calling unit, and a response unit. The reception unit receives instructions from the user. The prediction unit predicts the content of the conversation based on the instructions received by the reception unit. The generation unit generates the user's voice based on the conversation content predicted by the prediction unit. The calling unit makes a phone call using the voice generated by the generation unit. The response unit continues the conversation on the phone call made by the calling unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there are problems such as restrictions on time and location, lack of specific communication capabilities, and privacy issues in telephone communication, leaving room for improvement.

[0005] The system according to the embodiment aims to enable a user to make a phone call without being restricted by time and location and without stress.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a prediction unit, a generation unit, a calling unit, and a response unit. The reception unit receives instructions from the user. The prediction unit predicts the content of the conversation based on the instructions received by the reception unit. The generation unit generates the user's voice based on the conversation content predicted by the prediction unit. The calling unit makes a phone call using the voice generated by the generation unit. The response unit continues the conversation on the phone call made by the calling unit. [Effects of the Invention]

[0007] The system according to this embodiment allows users to make phone calls without being restricted by time or location, and without stress. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The telephone communication system according to an embodiment of the present invention is a system that fundamentally overturns the current state of telephone communication by utilizing generative AI, ultimately enabling AI to handle all human phone calls. This telephone communication system targets people who have difficulty making phone calls due to time or location constraints, or who lack confidence in certain communication skills. Ultimately, it targets all people who make phone calls. Telephone communication presents various problems such as time constraints (e.g., during work), location constraints (e.g., on trains or in libraries), lack of confidence in certain communication skills (e.g., telephone phobia, difficulty with foreign languages, deaf people, etc.), and privacy (e.g., confidential calls that must not be overheard by others). Users simply give instructions to the AI, and the AI ​​makes the call on their behalf. The AI ​​predicts what the user wants to convey over the phone using machine learning, understands the user's needs, and generates natural conversational audio using the user's voice. This allows users to overcome time and location constraints, reduce stress, and enable professional communication. The ultimate goal of this telephone communication system is to enable AI to handle all human phone calls, transforming them into more efficient and higher-quality communication. For example, the user tells the AI ​​"who they want to call" and "what they want to talk about." While voice communication is recommended, text is also an option in environments such as on a train. The AI ​​analyzes the information provided by the user, predicts the conversation, and generates text. This text is reviewed by the user until the prediction accuracy reaches 100%, and any necessary revisions are made before it is approved for use in the conversation. If the prediction accuracy remains at 100%, this step is skipped. Next, the AI ​​generates the user's voice, speaks with the same voice quality and tone as the user, and makes the call on the user's behalf. The AI ​​appropriately continues the conversation based on each other's responses, utilizing pre-learned information and the user's own voice characteristics to achieve a natural conversation. This service can be used in various ways, such as making restaurant reservations, inquiries, and business negotiations. The AI ​​can confirm reservations and make inquiries on behalf of the user, and make calls on behalf of the user when they are busy or lack confidence. Furthermore, it aims to enhance and improve user communication by utilizing the highest quality voice generation AI.By accumulating training data, more accurate predictions and responses become possible. This allows telephone communication systems to automatically handle user calls, providing efficient and high-quality communication.

[0029] The telephone communication system according to the embodiment comprises a reception unit, a prediction unit, a generation unit, a transmission unit, and a response unit. The reception unit receives instructions from the user. Instructions from the user include, but are not limited to, voice instructions and text instructions. The reception unit receives voice instructions using, for example, speech recognition technology. The reception unit can also receive text instructions using text analysis technology. For example, if the user gives a voice instruction, "Make a phone call," the reception unit recognizes the voice and analyzes the content of the instruction. If the user enters text, "I want to make a reservation," the reception unit analyzes the text and understands the content of the instruction. The prediction unit predicts the content of the conversation based on the instructions received by the reception unit. Prediction of the conversation content takes into account, for example, past conversation history, contextual information, and the user's intent, but is not limited to these examples. The prediction unit predicts the content of the conversation using, for example, natural language processing technology. The prediction unit can also predict the content of the conversation using machine learning algorithms. For example, the prediction unit, based on past conversation history, understands the user's intent when they instruct "I want to make a reservation" and predicts appropriate conversation content. The generation unit generates the user's voice based on the conversation content predicted by the prediction unit. Voice generation may, but is not limited to, speech synthesis technology or voice quality adjustment methods. The generation unit may, for example, generate voice that mimics the user's voice quality and tone. The generation unit can also extract the characteristics of the user's voice and generate voice based on them. For example, the generation unit learns the characteristics of the user's voice and generates natural-sounding voice based on those characteristics. The calling unit makes a phone call using the voice generated by the generation unit. Making a phone call may, but is not limited to, the selection method of the phone number and the timing of the call. The calling unit may, for example, send the generated voice to the telephone system and make a call. The calling unit can also automatically select a phone number and make a call at the appropriate time. For example, when the user instructs "I want to make a reservation," the calling unit selects the phone number of an appropriate restaurant and makes a call using the generated voice. The response unit continues the conversation on the phone call initiated by the caller unit.The response to a conversation may, for example, take into account the timing of responses and how to manage the flow of the conversation, but is not limited to such examples. The response unit can, for example, continue the conversation in response to each other's responses. The response unit can also achieve natural conversation by utilizing previously learned information and the characteristics of the user's voice. For example, the response unit can generate a natural response based on the characteristics of the user's voice and continue the conversation. As a result, the telephone communication system according to the embodiment can predict the content of the conversation based on the user's instructions, generate speech, make a call, and continue the conversation.

[0030] The reception desk can accept instructions via voice or text. For example, the reception desk can accept voice instructions using speech recognition technology. For instance, if a user says "make a phone call," the reception desk will recognize the voice and analyze the instruction. The reception desk can also accept text instructions using text analysis technology. For example, if a user types "I want to make a reservation," the reception desk will analyze the text and understand the instruction. This allows the reception desk to accept instructions via voice or text.

[0031] The prediction unit can predict conversation content and generate text based on user instructions. For example, the prediction unit can predict conversation content using natural language processing techniques. For instance, based on past conversation history, if a user instructs "I want to make a reservation," the prediction unit understands the user's intent and predicts appropriate conversation content. The prediction unit can also predict conversation content using machine learning algorithms. For example, the prediction unit understands the user's intent and generates appropriate text. Thus, the prediction unit can predict conversation content and generate text based on user instructions.

[0032] The generation unit can generate speech that reproduces the user's voice quality and tone. For example, the generation unit can use speech synthesis technology to generate speech that reproduces the user's voice quality and tone. For instance, the generation unit can learn the characteristics of the user's voice and generate natural-sounding speech based on those characteristics. Alternatively, the generation unit can extract the characteristics of the user's voice and generate speech based on those characteristics. For example, the generation unit can generate natural-sounding speech based on the characteristics of the user's voice. In this way, the generation unit can generate speech that reproduces the user's voice quality and tone.

[0033] The calling unit can make phone calls using the generated voice. For example, the calling unit can send the generated voice to a telephone system and make a call. For instance, if the user instructs the calling unit to "make a reservation," it can select the appropriate restaurant's phone number and make the call using the generated voice. The calling unit can also automatically select a phone number and make a call at the appropriate time. For example, if the user instructs the calling unit to "make an inquiry," it can select the appropriate company's phone number and make the call using the generated voice. In this way, the calling unit can make phone calls using the generated voice.

[0034] The response unit can continue the conversation in response to each other's responses. For example, the response unit can continue the conversation in response to each other's responses. For example, the response unit can generate natural responses based on the characteristics of the user's voice and continue the conversation. The response unit can also achieve natural conversation by utilizing previously learned information and the characteristics of the user's voice. For example, the response unit can generate natural responses based on the characteristics of the user's voice and continue the conversation. In this way, the response unit can continue the conversation in response to each other's responses.

[0035] The prediction unit can request confirmation from the user until the prediction accuracy improves, and make corrections if necessary. For example, if the user instructs "I want to make a reservation," the prediction unit understands the intent and predicts appropriate conversation content, but if the prediction accuracy is low, it will request confirmation from the user. Similarly, if the user instructs "I want to make an inquiry," the prediction unit understands the intent and predicts appropriate conversation content, but if the prediction accuracy is low, it will request confirmation from the user. This allows the prediction unit to request confirmation from the user until the prediction accuracy improves, and make corrections if necessary.

[0036] The response unit can achieve natural conversation by utilizing pre-learned information and the characteristics of the user's voice. For example, the response unit can generate a natural response based on the characteristics of the user's voice and continue the conversation. Furthermore, the response unit can generate an appropriate response based on pre-learned information. For example, the response unit can generate a natural response based on the characteristics of the user's voice and continue the conversation. In this way, the response unit can achieve natural conversation by utilizing pre-learned information and the characteristics of the user's voice.

[0037] The reception desk can analyze the user's past instruction history and select the appropriate method for receiving instructions via voice or text. For example, the reception desk can analyze the user's past instruction history and select the optimal method for receiving instructions via voice or text. For instance, the reception desk can prioritize suggesting instruction methods (voice, text, etc.) that the user has frequently used in the past. The reception desk can also predict and suggest instruction methods to be used during specific time periods based on the user's past instruction history. Furthermore, the reception desk can suggest the optimal input method based on the content of instructions the user has used in the past. This allows the reception desk to select the optimal method for receiving instructions based on the user's past instruction history.

[0038] The reception system can filter how instructions are received, either by voice or text, based on the user's current situation and environment. For example, if the user is on a train, the reception system might prioritize text input and suppress voice input. Alternatively, if the user is in a quiet environment, the reception system might prioritize voice input and offer text input as a supplement. Furthermore, if the user is on the move, the reception system might prioritize voice input to receive instructions quickly. This allows the reception system to filter how instructions are received based on the user's current situation and environment.

[0039] The reception desk can prioritize receiving instructions that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the reception desk will prioritize instructions related to that location. Furthermore, if the user is on the move, the reception desk can prioritize instructions related to travel. Additionally, if the user is at home, the reception desk can prioritize instructions related to home. This allows the reception desk to prioritize receiving instructions that are highly relevant based on the user's geographical location.

[0040] The reception desk can analyze the user's social media activity when receiving instructions and receive relevant instructions. For example, if the reception desk indicates on social media that the user is attending a particular event, it will prioritize receiving instructions related to that event. Similarly, if the reception desk indicates on social media that the user is in a specific location, it can prioritize receiving instructions related to that location. Furthermore, if the reception desk indicates on social media that the user is engaging in a specific activity, it can prioritize receiving instructions related to that activity. This allows the reception desk to receive relevant instructions based on the user's social media activity.

[0041] The prediction unit can improve prediction accuracy by referring to the user's past conversation history when predicting conversation content. For example, the prediction unit predicts similar conversation content based on the user's past conversations. The prediction unit can also extract specific patterns from the user's past conversation history to improve prediction accuracy. Furthermore, the prediction unit can improve prediction accuracy based on phrases and expressions the user has used in the past. In this way, the prediction unit can improve prediction accuracy based on the user's past conversation history.

[0042] The prediction unit can adjust its prediction algorithm based on the user's current situation and environment when predicting conversation content. For example, if the user is at work, the prediction unit can predict conversation content related to business. It can also predict conversation content related to home if the user is at home. Furthermore, if the user is traveling, the prediction unit can predict conversation content related to travel. This allows the prediction unit to adjust its prediction algorithm based on the user's current situation and environment.

[0043] The prediction unit can prioritize predicting conversation content that is highly relevant by considering the user's geographical location when predicting conversation content. For example, if the user is in a specific location, the prediction unit will prioritize predicting conversation content related to that location. Furthermore, if the user is on the move, the prediction unit can prioritize predicting conversation content related to movement. Additionally, if the user is at home, the prediction unit can prioritize predicting conversation content related to home. This allows the prediction unit to prioritize predicting conversation content that is highly relevant based on the user's geographical location.

[0044] The prediction unit can analyze a user's social media activity and predict relevant conversation content when predicting conversation content. For example, if the prediction unit indicates on social media that a user is participating in a specific event, it will prioritize predicting conversation content related to that event. It can also prioritize predicting conversation content related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the prediction unit indicates on social media that a user is engaging in a specific activity, it can prioritize predicting conversation content related to that activity. In this way, the prediction unit can predict relevant conversation content based on the user's social media activity.

[0045] The generation unit can improve generation accuracy by referring to the user's past voice data during voice generation. For example, the generation unit can generate similar voices based on voice data previously used by the user. Furthermore, the generation unit can extract specific patterns from the user's past voice data to improve generation accuracy. In addition, the generation unit can improve generation accuracy based on phrases and expressions previously used by the user. Thus, the generation unit can improve generation accuracy based on the user's past voice data.

[0046] The generation unit can adjust its generation algorithm based on the user's current situation and environment when generating speech. For example, if the user is at work, the generation unit can generate business-related speech. It can also generate home-related speech if the user is at home. Furthermore, if the user is traveling, the generation unit can generate travel-related speech. This allows the generation unit to adjust its generation algorithm based on the user's current situation and environment.

[0047] The generation unit can prioritize generating highly relevant audio by considering the user's geographical location information during audio generation. For example, the generation unit prioritizes generating highly relevant audio by considering the user's geographical location information during audio generation. For example, if the user is in a specific location, the generation unit will prioritize generating audio related to that location. Furthermore, if the user is on the move, the generation unit can also prioritize generating audio related to movement. In addition, if the user is at home, the generation unit can also prioritize generating audio related to home. As a result, the generation unit can prioritize generating highly relevant audio based on the user's geographical location information.

[0048] The generation unit can analyze the user's social media activity and generate relevant audio during audio generation. For example, if the generation unit indicates on social media that the user is participating in a particular event, it will prioritize generating audio related to that event. It can also prioritize generating audio related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the generation unit indicates on social media that the user is engaging in a specific activity, it can prioritize generating audio related to that activity. This allows the generation unit to generate relevant audio based on the user's social media activity.

[0049] The calling unit can select the optimal calling method by referring to the user's past calling history when a call is made. For example, the calling unit may prioritize suggesting calling methods that the user has frequently used in the past. The calling unit can also predict and suggest calling methods to be used during specific time periods based on the user's past calling history. Furthermore, the calling unit can suggest the optimal calling method based on the content of calls the user has made in the past. In this way, the calling unit can select the optimal calling method based on the user's past calling history.

[0050] The calling unit can adjust the calling algorithm based on the user's current situation and environment when making a call. For example, if the user is at work, the calling unit can provide a calling method related to business. It can also provide a calling method related to home if the user is at home. Furthermore, if the user is on the move, it can provide a calling method related to travel. This allows the calling unit to adjust the calling algorithm based on the user's current situation and environment.

[0051] The calling unit can prioritize making calls that are highly relevant to the user's geographical location when making a call. For example, if the user is in a specific location, the calling unit will prioritize making calls related to that location. Furthermore, if the user is on the move, the calling unit can prioritize making calls related to their movement. Additionally, if the user is at home, the calling unit can prioritize making calls related to their home. This allows the calling unit to prioritize making calls that are highly relevant based on the user's geographical location.

[0052] The calling unit can analyze a user's social media activity when making a call and make relevant calls. For example, if the calling unit indicates on social media that the user is attending a particular event, it will prioritize making calls related to that event. It can also prioritize making calls related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the calling unit indicates on social media that the user is engaging in a specific activity, it can prioritize making calls related to that activity. This allows the calling unit to make relevant calls based on the user's social media activity.

[0053] The response unit can select the optimal response method when responding to a conversation by referring to the user's past response history. For example, the response unit can select the optimal response method when responding to a conversation by referring to the user's past response history. For example, the response unit can suggest the optimal response method based on the response methods the user has used in the past. The response unit can also extract specific patterns from the user's past response history and suggest the optimal response method. Furthermore, the response unit can suggest the optimal response method based on phrases and expressions the user has used in the past. In this way, the response unit can select the optimal response method based on the user's past response history.

[0054] The response unit can adjust its response algorithm based on the user's current situation and environment when responding to a conversation. For example, if the user is at work, the response unit can provide business-related responses. It can also provide home-related responses if the user is at home. Furthermore, if the user is on the move, it can provide travel-related responses. This allows the response unit to adjust its response algorithm based on the user's current situation and environment.

[0055] The response unit can prioritize responding to conversations that are highly relevant, taking into account the user's geographical location. For example, when responding to a conversation, the response unit prioritizes responding to conversations that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the response unit will prioritize responding to conversations related to that location. Also, if the user is on the move, the response unit can prioritize responding to conversations related to movement. Furthermore, if the user is at home, the response unit can prioritize responding to conversations related to home. In this way, the response unit can prioritize responding to conversations that are highly relevant based on the user's geographical location.

[0056] The response unit can analyze the user's social media activity and respond with relevant conversations when responding to a conversation. For example, if the response unit indicates on social media that the user is attending a particular event, it will prioritize responding with conversations related to that event. It can also prioritize responding with conversations related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the response unit indicates on social media that the user is engaging in a specific activity, it can prioritize responding with conversations related to that activity. This allows the response unit to respond with relevant conversations based on the user's social media activity.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The reception desk can analyze the user's past instruction history and select the appropriate method for receiving instructions, whether by voice or text. For example, the reception desk can prioritize suggesting instruction methods (voice, text, etc.) that the user has frequently used in the past. It can also predict and suggest instruction methods to be used during specific time periods based on the user's past instruction history. Furthermore, the reception desk can suggest the optimal input method based on the content of instructions the user has used in the past. This allows the reception desk to select the most suitable method for receiving instructions based on the user's past instruction history.

[0059] The prediction unit can improve its prediction accuracy by referring to the user's past conversation history when predicting conversation content. For example, the prediction unit can predict similar conversation content based on the user's past conversations. Furthermore, the prediction unit can extract specific patterns from the user's past conversation history to improve prediction accuracy. In addition, the prediction unit can improve prediction accuracy based on phrases and expressions the user has used in the past. Thus, the prediction unit can improve its prediction accuracy based on the user's past conversation history.

[0060] The generation unit can improve generation accuracy by referring to the user's past voice data during voice generation. For example, the generation unit can generate similar voices based on voice data previously used by the user. Furthermore, the generation unit can extract specific patterns from the user's past voice data to improve generation accuracy. In addition, the generation unit can improve generation accuracy based on phrases and expressions previously used by the user. Thus, the generation unit can improve generation accuracy based on the user's past voice data.

[0061] The calling unit can select the optimal calling method by referring to the user's past calling history when making a call. For example, the calling unit can prioritize suggesting calling methods that the user has frequently used in the past. Furthermore, the calling unit can predict and suggest calling methods to be used during specific time periods based on the user's past calling history. In addition, the calling unit can suggest the optimal calling method based on the content of past calls made by the user. This allows the calling unit to select the optimal calling method based on the user's past calling history.

[0062] The response unit can select the optimal response method by referring to the user's past response history when responding to a conversation. For example, the response unit can suggest the optimal response method based on response methods the user has used in the past. Furthermore, the response unit can extract specific patterns from the user's past response history and suggest the optimal response method. In addition, the response unit can suggest the optimal response method based on phrases and expressions the user has used in the past. This allows the response unit to select the optimal response method based on the user's past response history.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The reception desk receives instructions from the user. These instructions can include voice and text instructions. The reception desk can receive voice instructions using voice recognition technology and text instructions using text analysis technology. For example, if the user says "Make a phone call" by voice, the reception desk recognizes the voice and analyzes the content of the instruction. Similarly, if the user types "I want to make a reservation" in text, the reception desk analyzes the text and understands the content of the instruction. Step 2: The prediction unit predicts the conversation content based on the instructions received by the reception unit. The prediction of conversation content takes into account past conversation history, contextual information, and the user's intent. The prediction unit uses natural language processing technology and machine learning algorithms to predict the conversation content. For example, based on past conversation history, if the user instructs "I want to make a reservation," the prediction unit understands the user's intent and predicts appropriate conversation content. Step 3: The generation unit generates the user's voice based on the conversation content predicted by the prediction unit. Speech synthesis technology and voice quality adjustment methods are used for speech generation. The generation unit generates speech that mimics the user's voice quality and tone, and extracts the characteristics of the user's voice to generate natural-sounding speech. Step 4: The calling unit makes a call using the voice generated by the generating unit. The method of selecting the phone number and the timing of the call are considered when making a call. The calling unit sends the generated voice to the telephone system and makes the call. It can also automatically select a phone number and make the call at the appropriate time. For example, if the user instructs "I want to make a reservation," the system will select the appropriate restaurant's phone number and make the call using the generated voice. Step 5: The response unit continues the conversation on the call initiated by the caller. The timing of responses and methods for managing the flow of the conversation are considered when responding to a conversation. The response unit continues the conversation in response to each other's responses, and uses pre-learned information and the characteristics of the user's voice to achieve a natural conversation. For example, it generates natural responses and continues the conversation based on the characteristics of the user's voice.

[0065] (Example of form 2) The telephone communication system according to an embodiment of the present invention is a system that fundamentally overturns the current state of telephone communication by utilizing generative AI, ultimately enabling AI to handle all human phone calls. This telephone communication system targets people who have difficulty making phone calls due to time or location constraints, or who lack confidence in certain communication skills. Ultimately, it targets all people who make phone calls. Telephone communication presents various problems such as time constraints (e.g., during work), location constraints (e.g., on trains or in libraries), lack of confidence in certain communication skills (e.g., telephone phobia, difficulty with foreign languages, deaf people, etc.), and privacy (e.g., confidential calls that must not be overheard by others). Users simply give instructions to the AI, and the AI ​​makes the call on their behalf. The AI ​​predicts what the user wants to convey over the phone using machine learning, understands the user's needs, and generates natural conversational audio using the user's voice. This allows users to overcome time and location constraints, reduce stress, and enable professional communication. The ultimate goal of this telephone communication system is to enable AI to handle all human phone calls, transforming them into more efficient and higher-quality communication. For example, the user tells the AI ​​"who they want to call" and "what they want to talk about." While voice communication is recommended, text is also an option in environments such as on a train. The AI ​​analyzes the information provided by the user, predicts the conversation, and generates text. This text is reviewed by the user until the prediction accuracy reaches 100%, and any necessary revisions are made before it is approved for use in the conversation. If the prediction accuracy remains at 100%, this step is skipped. Next, the AI ​​generates the user's voice, speaks with the same voice quality and tone as the user, and makes the call on the user's behalf. The AI ​​appropriately continues the conversation based on each other's responses, utilizing pre-learned information and the user's own voice characteristics to achieve a natural conversation. This service can be used in various ways, such as making restaurant reservations, inquiries, and business negotiations. The AI ​​can confirm reservations and make inquiries on behalf of the user, and make calls on behalf of the user when they are busy or lack confidence. Furthermore, it aims to enhance and improve user communication by utilizing the highest quality voice generation AI.By accumulating training data, more accurate predictions and responses become possible. This allows telephone communication systems to automatically handle user calls, providing efficient and high-quality communication.

[0066] The telephone communication system according to the embodiment comprises a reception unit, a prediction unit, a generation unit, a transmission unit, and a response unit. The reception unit receives instructions from the user. Instructions from the user include, but are not limited to, voice instructions and text instructions. The reception unit receives voice instructions using, for example, speech recognition technology. The reception unit can also receive text instructions using text analysis technology. For example, if the user gives a voice instruction, "Make a phone call," the reception unit recognizes the voice and analyzes the content of the instruction. If the user enters text, "I want to make a reservation," the reception unit analyzes the text and understands the content of the instruction. The prediction unit predicts the content of the conversation based on the instructions received by the reception unit. Prediction of the conversation content takes into account, for example, past conversation history, contextual information, and the user's intent, but is not limited to these examples. The prediction unit predicts the content of the conversation using, for example, natural language processing technology. The prediction unit can also predict the content of the conversation using machine learning algorithms. For example, the prediction unit, based on past conversation history, understands the user's intent when they instruct "I want to make a reservation" and predicts appropriate conversation content. The generation unit generates the user's voice based on the conversation content predicted by the prediction unit. Voice generation may, but is not limited to, speech synthesis technology or voice quality adjustment methods. The generation unit may, for example, generate voice that mimics the user's voice quality and tone. The generation unit can also extract the characteristics of the user's voice and generate voice based on them. For example, the generation unit learns the characteristics of the user's voice and generates natural-sounding voice based on those characteristics. The calling unit makes a phone call using the voice generated by the generation unit. Making a phone call may, but is not limited to, the selection method of the phone number and the timing of the call. The calling unit may, for example, send the generated voice to the telephone system and make a call. The calling unit can also automatically select a phone number and make a call at the appropriate time. For example, when the user instructs "I want to make a reservation," the calling unit selects the phone number of an appropriate restaurant and makes a call using the generated voice. The response unit continues the conversation on the phone call initiated by the caller unit.The response to a conversation may, for example, take into account the timing of responses and how to manage the flow of the conversation, but is not limited to such examples. The response unit can, for example, continue the conversation in response to each other's responses. The response unit can also achieve natural conversation by utilizing previously learned information and the characteristics of the user's voice. For example, the response unit can generate a natural response based on the characteristics of the user's voice and continue the conversation. As a result, the telephone communication system according to the embodiment can predict the content of the conversation based on the user's instructions, generate speech, make a call, and continue the conversation.

[0067] The reception desk can accept instructions via voice or text. For example, the reception desk can accept voice instructions using speech recognition technology. For instance, if a user says "make a phone call," the reception desk will recognize the voice and analyze the instruction. The reception desk can also accept text instructions using text analysis technology. For example, if a user types "I want to make a reservation," the reception desk will analyze the text and understand the instruction. This allows the reception desk to accept instructions via voice or text.

[0068] The prediction unit can predict conversation content and generate text based on user instructions. For example, the prediction unit can predict conversation content using natural language processing techniques. For instance, based on past conversation history, if a user instructs "I want to make a reservation," the prediction unit understands the user's intent and predicts appropriate conversation content. The prediction unit can also predict conversation content using machine learning algorithms. For example, the prediction unit understands the user's intent and generates appropriate text. Thus, the prediction unit can predict conversation content and generate text based on user instructions.

[0069] The generation unit can generate speech that reproduces the user's voice quality and tone. For example, the generation unit can use speech synthesis technology to generate speech that reproduces the user's voice quality and tone. For instance, the generation unit can learn the characteristics of the user's voice and generate natural-sounding speech based on those characteristics. Alternatively, the generation unit can extract the characteristics of the user's voice and generate speech based on those characteristics. For example, the generation unit can generate natural-sounding speech based on the characteristics of the user's voice. In this way, the generation unit can generate speech that reproduces the user's voice quality and tone.

[0070] The calling unit can make phone calls using the generated voice. For example, the calling unit can send the generated voice to a telephone system and make a call. For instance, if the user instructs the calling unit to "make a reservation," it can select the appropriate restaurant's phone number and make the call using the generated voice. The calling unit can also automatically select a phone number and make a call at the appropriate time. For example, if the user instructs the calling unit to "make an inquiry," it can select the appropriate company's phone number and make the call using the generated voice. In this way, the calling unit can make phone calls using the generated voice.

[0071] The response unit can continue the conversation in response to each other's responses. For example, the response unit can continue the conversation in response to each other's responses. For example, the response unit can generate natural responses based on the characteristics of the user's voice and continue the conversation. The response unit can also achieve natural conversation by utilizing previously learned information and the characteristics of the user's voice. For example, the response unit can generate natural responses based on the characteristics of the user's voice and continue the conversation. In this way, the response unit can continue the conversation in response to each other's responses.

[0072] The prediction unit can request confirmation from the user until the prediction accuracy improves, and make corrections if necessary. For example, if the user instructs "I want to make a reservation," the prediction unit understands the intent and predicts appropriate conversation content, but if the prediction accuracy is low, it will request confirmation from the user. Similarly, if the user instructs "I want to make an inquiry," the prediction unit understands the intent and predicts appropriate conversation content, but if the prediction accuracy is low, it will request confirmation from the user. This allows the prediction unit to request confirmation from the user until the prediction accuracy improves, and make corrections if necessary.

[0073] The response unit can achieve natural conversation by utilizing pre-learned information and the characteristics of the user's voice. For example, the response unit can generate a natural response based on the characteristics of the user's voice and continue the conversation. Furthermore, the response unit can generate an appropriate response based on pre-learned information. For example, the response unit can generate a natural response based on the characteristics of the user's voice and continue the conversation. In this way, the response unit can achieve natural conversation by utilizing pre-learned information and the characteristics of the user's voice.

[0074] The reception desk can estimate the user's emotions and adjust how it receives instructions via voice or text based on those emotions. For example, if the user is nervous, the reception desk can provide a simple and intuitive interface and minimize the input steps. If the user is relaxed, the reception desk can also provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception desk can prioritize voice input and receive instructions quickly. This allows the reception desk to adjust how it receives instructions based on the user's emotions.

[0075] The reception desk can analyze the user's past instruction history and select the appropriate method for receiving instructions via voice or text. For example, the reception desk can analyze the user's past instruction history and select the optimal method for receiving instructions via voice or text. For instance, the reception desk can prioritize suggesting instruction methods (voice, text, etc.) that the user has frequently used in the past. The reception desk can also predict and suggest instruction methods to be used during specific time periods based on the user's past instruction history. Furthermore, the reception desk can suggest the optimal input method based on the content of instructions the user has used in the past. This allows the reception desk to select the optimal method for receiving instructions based on the user's past instruction history.

[0076] The reception system can filter how instructions are received, either by voice or text, based on the user's current situation and environment. For example, if the user is on a train, the reception system might prioritize text input and suppress voice input. Alternatively, if the user is in a quiet environment, the reception system might prioritize voice input and offer text input as a supplement. Furthermore, if the user is on the move, the reception system might prioritize voice input to receive instructions quickly. This allows the reception system to filter how instructions are received based on the user's current situation and environment.

[0077] The reception desk can estimate the user's emotions and determine the priority of instructions to accept based on those emotions. For example, if the user is feeling stressed, the reception desk will prioritize important instructions. Similarly, if the user is relaxed, the reception desk may prioritize detailed instructions. Furthermore, if the user is in a hurry, the reception desk may prioritize urgent instructions. This allows the reception desk to prioritize instructions based on the user's emotions.

[0078] The reception desk can prioritize receiving instructions that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the reception desk will prioritize instructions related to that location. Furthermore, if the user is on the move, the reception desk can prioritize instructions related to travel. Additionally, if the user is at home, the reception desk can prioritize instructions related to home. This allows the reception desk to prioritize receiving instructions that are highly relevant based on the user's geographical location.

[0079] The reception desk can analyze the user's social media activity when receiving instructions and receive relevant instructions. For example, if the reception desk indicates on social media that the user is attending a particular event, it will prioritize receiving instructions related to that event. Similarly, if the reception desk indicates on social media that the user is in a specific location, it can prioritize receiving instructions related to that location. Furthermore, if the reception desk indicates on social media that the user is engaging in a specific activity, it can prioritize receiving instructions related to that activity. This allows the reception desk to receive relevant instructions based on the user's social media activity.

[0080] The prediction unit can estimate the user's emotions and adjust its conversation prediction method based on those emotions. For example, if the user is relaxed, the prediction unit can predict detailed conversation content. If the user is in a hurry, the prediction unit can also predict concise conversation content. Furthermore, if the user is nervous, the prediction unit can predict reassuring conversation content. In this way, the prediction unit can adjust its conversation prediction method based on the user's emotions.

[0081] The prediction unit can improve prediction accuracy by referring to the user's past conversation history when predicting conversation content. For example, the prediction unit predicts similar conversation content based on the user's past conversations. The prediction unit can also extract specific patterns from the user's past conversation history to improve prediction accuracy. Furthermore, the prediction unit can improve prediction accuracy based on phrases and expressions the user has used in the past. In this way, the prediction unit can improve prediction accuracy based on the user's past conversation history.

[0082] The prediction unit can adjust its prediction algorithm based on the user's current situation and environment when predicting conversation content. For example, if the user is at work, the prediction unit can predict conversation content related to business. It can also predict conversation content related to home if the user is at home. Furthermore, if the user is traveling, the prediction unit can predict conversation content related to travel. This allows the prediction unit to adjust its prediction algorithm based on the user's current situation and environment.

[0083] The prediction unit can estimate the user's emotions and determine the priority of predicted conversation content based on those emotions. For example, if the user is feeling stressed, the prediction unit will prioritize predicting important conversation content. Similarly, if the user is relaxed, the prediction unit can prioritize predicting detailed conversation content. Furthermore, if the user is in a hurry, the prediction unit can prioritize predicting urgent conversation content. This allows the prediction unit to prioritize conversation content based on the user's emotions.

[0084] The prediction unit can prioritize predicting conversation content that is highly relevant by considering the user's geographical location when predicting conversation content. For example, if the user is in a specific location, the prediction unit will prioritize predicting conversation content related to that location. Furthermore, if the user is on the move, the prediction unit can prioritize predicting conversation content related to movement. Additionally, if the user is at home, the prediction unit can prioritize predicting conversation content related to home. This allows the prediction unit to prioritize predicting conversation content that is highly relevant based on the user's geographical location.

[0085] The prediction unit can analyze a user's social media activity and predict relevant conversation content when predicting conversation content. For example, if the prediction unit indicates on social media that a user is participating in a specific event, it will prioritize predicting conversation content related to that event. It can also prioritize predicting conversation content related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the prediction unit indicates on social media that a user is engaging in a specific activity, it can prioritize predicting conversation content related to that activity. In this way, the prediction unit can predict relevant conversation content based on the user's social media activity.

[0086] The generation unit can estimate the user's emotions and adjust the voice generation method based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate voices that proceed at a relaxed pace. It can also generate fast and concise voices if the user is in a hurry. Furthermore, if the user is stressed, the generation unit can generate reassuring voices. In this way, the generation unit can adjust the voice generation method based on the user's emotions.

[0087] The generation unit can improve generation accuracy by referring to the user's past voice data during voice generation. For example, the generation unit can generate similar voices based on voice data previously used by the user. Furthermore, the generation unit can extract specific patterns from the user's past voice data to improve generation accuracy. In addition, the generation unit can improve generation accuracy based on phrases and expressions previously used by the user. Thus, the generation unit can improve generation accuracy based on the user's past voice data.

[0088] The generation unit can adjust its generation algorithm based on the user's current situation and environment when generating speech. For example, if the user is at work, the generation unit can generate business-related speech. It can also generate home-related speech if the user is at home. Furthermore, if the user is traveling, the generation unit can generate travel-related speech. This allows the generation unit to adjust its generation algorithm based on the user's current situation and environment.

[0089] The generation unit can estimate the user's emotions and determine the priority of the audio to generate based on those estimated emotions. For example, if the user is feeling stressed, the generation unit will prioritize generating important audio. It can also prioritize generating detailed audio if the user is relaxed. Furthermore, if the user is in a hurry, the generation unit can prioritize generating urgent audio. This allows the generation unit to determine the priority of the audio to generate based on the user's emotions.

[0090] The generation unit can prioritize generating highly relevant audio by considering the user's geographical location information during audio generation. For example, the generation unit prioritizes generating highly relevant audio by considering the user's geographical location information during audio generation. For example, if the user is in a specific location, the generation unit will prioritize generating audio related to that location. Furthermore, if the user is on the move, the generation unit can also prioritize generating audio related to movement. In addition, if the user is at home, the generation unit can also prioritize generating audio related to home. As a result, the generation unit can prioritize generating highly relevant audio based on the user's geographical location information.

[0091] The generation unit can analyze the user's social media activity and generate relevant audio during audio generation. For example, if the generation unit indicates on social media that the user is participating in a particular event, it will prioritize generating audio related to that event. It can also prioritize generating audio related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the generation unit indicates on social media that the user is engaging in a specific activity, it can prioritize generating audio related to that activity. This allows the generation unit to generate relevant audio based on the user's social media activity.

[0092] The calling unit can estimate the user's emotions and adjust the calling method based on those emotions. For example, if the calling unit is nervous, it can display a relaxing message before making a call. If the user is relaxed, it can also provide a normal calling method. Furthermore, if the user is in a hurry, it can make a call quickly. In this way, the calling unit can adjust the calling method based on the user's emotions.

[0093] The calling unit can select the optimal calling method by referring to the user's past calling history when a call is made. For example, the calling unit may prioritize suggesting calling methods that the user has frequently used in the past. The calling unit can also predict and suggest calling methods to be used during specific time periods based on the user's past calling history. Furthermore, the calling unit can suggest the optimal calling method based on the content of calls the user has made in the past. In this way, the calling unit can select the optimal calling method based on the user's past calling history.

[0094] The calling unit can adjust the calling algorithm based on the user's current situation and environment when making a call. For example, if the user is at work, the calling unit can provide a calling method related to business. It can also provide a calling method related to home if the user is at home. Furthermore, if the user is on the move, it can provide a calling method related to travel. This allows the calling unit to adjust the calling algorithm based on the user's current situation and environment.

[0095] The calling unit can estimate the user's emotions and determine the priority of outgoing calls based on those emotions. For example, if the user is feeling stressed, the calling unit will prioritize important calls. It can also prioritize detailed calls if the user is relaxed. Furthermore, if the user is in a hurry, the calling unit can prioritize urgent calls. In this way, the calling unit can determine the priority of outgoing calls based on the user's emotions.

[0096] The calling unit can prioritize making calls that are highly relevant to the user's geographical location when making a call. For example, if the user is in a specific location, the calling unit will prioritize making calls related to that location. Furthermore, if the user is on the move, the calling unit can prioritize making calls related to their movement. Additionally, if the user is at home, the calling unit can prioritize making calls related to their home. This allows the calling unit to prioritize making calls that are highly relevant based on the user's geographical location.

[0097] The calling unit can analyze a user's social media activity when making a call and make relevant calls. For example, if the calling unit indicates on social media that the user is attending a particular event, it will prioritize making calls related to that event. It can also prioritize making calls related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the calling unit indicates on social media that the user is engaging in a specific activity, it can prioritize making calls related to that activity. This allows the calling unit to make relevant calls based on the user's social media activity.

[0098] The response unit can estimate the user's emotions and adjust its response method based on those emotions. For example, if the user is nervous, the response unit can provide a reassuring response. If the user is relaxed, the response unit can provide a more detailed response. Furthermore, if the user is in a hurry, the response unit can provide a quick and concise response. In this way, the response unit can adjust its response method based on the user's emotions.

[0099] The response unit can select the optimal response method when responding to a conversation by referring to the user's past response history. For example, the response unit can select the optimal response method when responding to a conversation by referring to the user's past response history. For example, the response unit can suggest the optimal response method based on the response methods the user has used in the past. The response unit can also extract specific patterns from the user's past response history and suggest the optimal response method. Furthermore, the response unit can suggest the optimal response method based on phrases and expressions the user has used in the past. In this way, the response unit can select the optimal response method based on the user's past response history.

[0100] The response unit can adjust its response algorithm based on the user's current situation and environment when responding to a conversation. For example, if the user is at work, the response unit can provide business-related responses. It can also provide home-related responses if the user is at home. Furthermore, if the user is on the move, it can provide travel-related responses. This allows the response unit to adjust its response algorithm based on the user's current situation and environment.

[0101] The response unit can estimate the user's emotions and determine the priority of conversations to respond to based on those emotions. For example, if the user is feeling stressed, the response unit will prioritize important conversations. It can also prioritize detailed conversations if the user is relaxed. Furthermore, if the user is in a hurry, the response unit can prioritize urgent conversations. In this way, the response unit can determine the priority of conversations to respond to based on the user's emotions.

[0102] The response unit can prioritize responding to conversations that are highly relevant, taking into account the user's geographical location. For example, when responding to a conversation, the response unit prioritizes responding to conversations that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the response unit will prioritize responding to conversations related to that location. Also, if the user is on the move, the response unit can prioritize responding to conversations related to movement. Furthermore, if the user is at home, the response unit can prioritize responding to conversations related to home. In this way, the response unit can prioritize responding to conversations that are highly relevant based on the user's geographical location.

[0103] The response unit can analyze the user's social media activity and respond with relevant conversations when responding to a conversation. For example, if the response unit indicates on social media that the user is attending a particular event, it will prioritize responding with conversations related to that event. It can also prioritize responding with conversations related to a specific location if the user indicates on social media that they are in that location. Furthermore, if the response unit indicates on social media that the user is engaging in a specific activity, it can prioritize responding with conversations related to that activity. This allows the response unit to respond with relevant conversations based on the user's social media activity. === Hard Collateral 1-1 === Each of the multiple elements described above, including the reception unit, prediction unit, generation unit, transmission unit, and response unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives voice and text instructions from the user. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts the content of the conversation based on past conversation history and contextual information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates voice that mimics the user's voice quality and tone. The transmission unit is implemented by the control unit 46A of the smart device 14 and makes a phone call using the generated voice. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and continues the conversation according to each other's responses. The reception unit estimates the user's emotions and adjusts the method of receiving instructions based on the estimated emotions. === Hard Collateral 1-2 === Each of the multiple elements described above, including the reception unit, prediction unit, generation unit, transmission unit, and response unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives voice and text instructions from the user. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts the content of the conversation based on past conversation history and contextual information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates voice that mimics the user's voice quality and tone. The transmission unit is implemented by the control unit 46A of the smart glasses 214 and makes a phone call using the generated voice. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and continues the conversation according to each other's responses. The reception unit estimates the user's emotions and adjusts the method of receiving instructions based on the estimated emotions. === Hard Collateral 1-3 === Each of the multiple elements described above, including the reception unit, prediction unit, generation unit, transmission unit, and response unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives voice and text instructions from the user. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts the content of the conversation based on past conversation history and contextual information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates voice that mimics the user's voice quality and tone. The transmission unit is implemented by the control unit 46A of the headset terminal 314 and makes a phone call using the generated voice. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and continues the conversation according to each other's responses. The reception unit estimates the user's emotions and adjusts the method of receiving instructions based on the estimated emotions. === Hard Collateral 1-4 === Each of the multiple elements described above, including the reception unit, prediction unit, generation unit, transmission unit, and response unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives voice and text instructions from the user. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts the content of the conversation based on past conversation history and contextual information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates voice that mimics the user's voice quality and tone. The transmission unit is implemented by the control unit 46A of the robot 414 and makes a phone call using the generated voice. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and continues the conversation according to each other's responses. The reception unit estimates the user's emotions and adjusts the method of receiving instructions based on the estimated emotions.

[0104] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0105] The reception desk can estimate the user's emotions and adjust how instructions are received based on those estimates. For example, if the user is nervous, the reception desk can provide a simple and intuitive 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 and receive instructions quickly. In this way, the reception desk can adjust how instructions are received based on the user's emotions.

[0106] The prediction unit can estimate the user's emotions and adjust its conversation prediction method based on those emotions. For example, if the user is relaxed, it can predict detailed conversation content. If the user is in a hurry, it can predict concise conversation content. Furthermore, if the user is nervous, it can predict conversation content that provides reassurance. In this way, the prediction unit can adjust its conversation prediction method based on the user's emotions.

[0107] The generation unit can estimate the user's emotions and adjust the voice generation method based on those emotions. For example, if the user is relaxed, it can generate a voice that proceeds at a leisurely pace. If the user is in a hurry, it can generate a fast and concise voice. Furthermore, if the user is stressed, it can generate a voice that provides a sense of reassurance. In this way, the generation unit can adjust the voice generation method based on the user's emotions.

[0108] The calling unit can estimate the user's emotions and adjust the calling method based on those emotions. For example, if the user is nervous, it can display a relaxing message before making a call. If the user is relaxed, it can provide a normal calling method. Furthermore, if the user is in a hurry, it can make a call quickly. In this way, the calling unit can adjust the calling method based on the user's emotions.

[0109] The response unit can estimate the user's emotions and adjust its response method based on those emotions. For example, if the user is nervous, it can provide a reassuring response. If the user is relaxed, it can provide a more detailed response. Furthermore, if the user is in a hurry, it can provide a quick and concise response. In this way, the response unit can adjust its response method based on the user's emotions.

[0110] The reception desk can analyze the user's past instruction history and select the appropriate method for receiving instructions, whether by voice or text. For example, the reception desk can prioritize suggesting instruction methods (voice, text, etc.) that the user has frequently used in the past. It can also predict and suggest instruction methods to be used during specific time periods based on the user's past instruction history. Furthermore, the reception desk can suggest the optimal input method based on the content of instructions the user has used in the past. This allows the reception desk to select the most suitable method for receiving instructions based on the user's past instruction history.

[0111] The prediction unit can improve its prediction accuracy by referring to the user's past conversation history when predicting conversation content. For example, the prediction unit can predict similar conversation content based on the user's past conversations. Furthermore, the prediction unit can extract specific patterns from the user's past conversation history to improve prediction accuracy. In addition, the prediction unit can improve prediction accuracy based on phrases and expressions the user has used in the past. Thus, the prediction unit can improve its prediction accuracy based on the user's past conversation history.

[0112] The generation unit can improve generation accuracy by referring to the user's past voice data during voice generation. For example, the generation unit can generate similar voices based on voice data previously used by the user. Furthermore, the generation unit can extract specific patterns from the user's past voice data to improve generation accuracy. In addition, the generation unit can improve generation accuracy based on phrases and expressions previously used by the user. Thus, the generation unit can improve generation accuracy based on the user's past voice data.

[0113] The calling unit can select the optimal calling method by referring to the user's past calling history when making a call. For example, the calling unit can prioritize suggesting calling methods that the user has frequently used in the past. Furthermore, the calling unit can predict and suggest calling methods to be used during specific time periods based on the user's past calling history. In addition, the calling unit can suggest the optimal calling method based on the content of past calls made by the user. This allows the calling unit to select the optimal calling method based on the user's past calling history.

[0114] The response unit can select the optimal response method by referring to the user's past response history when responding to a conversation. For example, the response unit can suggest the optimal response method based on response methods the user has used in the past. Furthermore, the response unit can extract specific patterns from the user's past response history and suggest the optimal response method. In addition, the response unit can suggest the optimal response method based on phrases and expressions the user has used in the past. This allows the response unit to select the optimal response method based on the user's past response history.

[0115] The following briefly describes the processing flow for example form 2.

[0116] Step 1: The reception desk receives instructions from the user. These instructions can include voice and text instructions. The reception desk can receive voice instructions using voice recognition technology and text instructions using text analysis technology. For example, if the user says "Make a phone call" by voice, the reception desk recognizes the voice and analyzes the content of the instruction. Similarly, if the user types "I want to make a reservation" in text, the reception desk analyzes the text and understands the content of the instruction. Step 2: The prediction unit predicts the conversation content based on the instructions received by the reception unit. The prediction of conversation content takes into account past conversation history, contextual information, and the user's intent. The prediction unit uses natural language processing technology and machine learning algorithms to predict the conversation content. For example, based on past conversation history, if the user instructs "I want to make a reservation," the prediction unit understands the user's intent and predicts appropriate conversation content. Step 3: The generation unit generates the user's voice based on the conversation content predicted by the prediction unit. Speech synthesis technology and voice quality adjustment methods are used for speech generation. The generation unit generates speech that mimics the user's voice quality and tone, and extracts the characteristics of the user's voice to generate natural-sounding speech. Step 4: The calling unit makes a call using the voice generated by the generating unit. The method of selecting the phone number and the timing of the call are considered when making a call. The calling unit sends the generated voice to the telephone system and makes the call. It can also automatically select a phone number and make the call at the appropriate time. For example, if the user instructs "I want to make a reservation," the system will select the appropriate restaurant's phone number and make the call using the generated voice. Step 5: The response unit continues the conversation on the call initiated by the caller. The timing of responses and methods for managing the flow of the conversation are considered when responding to a conversation. The response unit continues the conversation in response to each other's responses, and uses pre-learned information and the characteristics of the user's voice to achieve a natural conversation. For example, it generates natural responses and continues the conversation based on the characteristics of the user's voice.

[0117] 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.

[0118] 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 the following. 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 (for example, 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. 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 a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0119] 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.

[0120] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0121] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.).

[0133] 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.

[0134] 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. 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.

[0135] 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.

[0136] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0137] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] 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.

[0150] 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. 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.

[0151] 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.

[0152] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0153] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.).

[0166] 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.

[0167] 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. 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.

[0168] 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.

[0169] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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 prediction unit that predicts the content of a conversation based on instructions received by the reception unit, A generation unit that generates user voice based on the conversation content predicted by the prediction unit, A calling unit that makes a phone call using the voice generated by the generation unit, A response unit that continues the conversation in a telephone call made by the aforementioned calling unit, Equipped with A system characterized by the following features.

2. The aforementioned reception unit is We accept instructions via voice or text. The system according to feature 1.

3. The prediction unit, It predicts conversation content and generates text based on user instructions. The system according to feature 1.

4. The generating unit is Generates voice that replicates the user's voice quality and tone. The system according to feature 1.

5. The transmitting unit is Make a phone call using the generated voice. The system according to feature 1.

6. The response unit is Continue the conversation based on each other's responses. The system according to feature 1.

7. The prediction unit, We will ask users for confirmation until the prediction accuracy improves, and make corrections if necessary. The system according to feature 1.

8. The response unit is It enables natural conversation by utilizing pre-learned information and the characteristics of user voices. The system according to feature 1.

Images