System

Abstract

An object of a system according to an embodiment is to enable even a person who is handicapped in hearing or speech to easily make a phone call.SOLUTION: A system according to an embodiment includes a text input unit, a speech generation unit, and a call acting unit. The text input unit receives a text input from a user. The conversation generation unit generates a natural conversation based on the text received by the text input unit. The call acting part acts for a call based on the conversation generated by the conversation generation part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that people with hearing or speech disabilities have difficulty making phone calls.

[0005] The system according to the embodiment aims to enable even people with hearing or speech disabilities to easily make phone calls. [Means for solving the problem]

[0006] The system according to the embodiment includes a text input unit, a conversation generation unit, and a call answering unit. The text input unit accepts text input from a user. The conversation generation unit generates natural conversation based on the text accepted by the text input unit. The call answering unit answers calls based on the conversation generated by the conversation generation unit. [Effects of the Invention]

[0007] The system according to the embodiment allows even people with hearing or speech disabilities to easily make phone calls. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The telephone support AI system according to an embodiment of the present invention is a system that generates natural conversations from simple text input by people with hearing or speech disabilities and handles phone calls on their behalf. This allows people with hearing or speech disabilities to smoothly make reservations or contact hospitals, stores, etc.

[0029] A telephone support AI system according to an embodiment includes a text input unit, a conversation generation unit, and a call answering unit. The text input unit accepts text input from a user. For example, the user may enter, "I'd like to make a hospital appointment." The conversation generation unit generates natural conversation based on the text accepted by the text input unit. For example, the generation AI uses a text generation AI (e.g., LLM) to generate, "Hello, I'd like to make a hospital appointment. What time is available?" The generation AI can also use a multimodal generation AI to generate conversation that combines text, images, and audio. The call answering unit handles calls based on the conversation generated by the conversation generation unit. For example, the generation AI calls a hospital and conveys that it would like to make an appointment. This allows even people with hearing or speech impairments to easily make reservations or make contact by generating natural conversation from simple text input and handling the call.

[0030] The conversation generation unit can understand the context of the text received by the text input unit and generate a conversation by adjusting the appropriate tone and formality. For example, when a user inputs "I'd like to make a doctor's appointment," the generation AI understands the context and generates "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" in a formal tone. The generation AI can also generate "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" in a casual tone. This allows for more natural conversations by generating a conversation by adjusting the appropriate tone and formality to the user's input text.

[0031] The conversation generation unit can learn the user's past input history and generate a conversation style optimized for each individual user. For example, the conversation generation unit learns the user's past input history of "I would like to make a doctor's appointment," and the generation AI generates "Hello, I would like to make another doctor's appointment. Please let me know what time is available." The generation AI can also generate a more personalized conversation style based on the user's preferences and past conversation patterns. In this way, by learning the user's past input history, a conversation style optimized for each individual user can be generated.

[0032] The conversation generation unit can analyze image and voice input in addition to text input to generate richer conversations. For example, if a user inputs "I'd like to make a doctor's appointment" and attaches a photo of the hospital, the generation AI will generate "Hello, I'd like to make a doctor's appointment. Please let me know the available times at this hospital." In addition, when a user provides voice input, the generation AI can analyze the voice and generate appropriate conversation. This allows for the generation of richer conversations by analyzing image and voice input in addition to text input.

[0033] The conversation generation unit supports text input in different languages ​​and can generate multilingual conversations. For example, when a user inputs "I want to make a reservation at the hospital," the generation AI generates "Hello, I would like to make a reservation at the hospital. Could you please tell me the available times?" The generation AI can also handle other languages ​​in the same way and generate appropriate conversations depending on the language input by the user. This makes it possible to generate multilingual conversations by supporting text input in different languages.

[0034] The call answering unit can analyze the tone and speed of the other party's voice during a call and generate a response at the appropriate time. For example, the call answering unit's generation AI calls a hospital, analyzes the tone and speed of the other party's voice, and responds at the appropriate time, saying, "Hello, I'd like to make an appointment at the hospital. Please let me know what time you're available." In addition, if the other party is in a hurry, the generation AI can respond succinctly, saying, "I'd like to make an appointment. Please let me know what time you're available." This allows for more natural conversations by analyzing the tone and speed of the other party's voice during a call and generating a response at the appropriate time.

[0035] The call answering unit translates the contents of the call in real time, allowing for smooth conversations with people speaking different languages. For example, the generation AI calls a hospital, translates the contents of the call in real time, and responds in English with, "Hello, I would like to make a reservation at the hospital. Could you please tell me the available times?" The generation AI can also handle other languages ​​in the same way, translating the contents of the call in real time. This allows for smooth conversations with people speaking different languages ​​by translating the contents of the call in real time.

[0036] The call answering unit can automatically summarize the contents of the call and provide it to the user in text. For example, the generation AI calls a hospital, automatically summarizes the contents of the call, and provides the user with a text message such as, "Your hospital appointment has been completed. The appointment date and time is XX / XX / XX." The generation AI can also summarize the contents of the call and save it so that the user can check it later. This allows the user to easily check the contents of the call by automatically summarizing the contents of the call and providing it to the user in text.

[0037] The call answering unit can remove noise that occurs during a call, enabling clearer audio conversations. For example, the generation AI calls a hospital, removes noise that occurs during the call, and then has a clear voice conversation, saying, "Hello, I'd like to make an appointment with the hospital. Please let me know what time you're available." The generation AI can also use noise filtering technology to reduce background noise during the call, enabling clearer audio conversations. This removes noise that occurs during the call, enabling clearer audio conversations.

[0038] The call answering unit can automatically determine the priority of calls and give priority to important calls. For example, when the generation AI calls a hospital, the call answering unit will prioritize urgent appointments and respond with, "Hello, I'd like to make an urgent appointment. Please let me know what time is available." The generation AI can also prioritize important calls based on the user's settings. This allows for efficient call management by automatically determining the priority of calls and giving priority to important calls.

[0039] The call answering unit can use the waiting time that occurs during a call to provide the user with relevant information or entertainment. For example, the generation AI can call a hospital and provide the user with health information during the waiting time, saying, "Please wait. We will provide you with the latest health information in the meantime." The generation AI can also provide the user with entertainment such as music or videos during the waiting time. This allows the user to make effective use of the waiting time by providing the user with relevant information or entertainment during the call.

[0040] The call answering unit allows the user to use the waiting time for other tasks, thereby achieving efficient time management. For example, the generation AI calls a hospital and provides a message saying, "Please wait. Please do other tasks in the meantime," so that the user can do other tasks while waiting. The generation AI can also support the user by allowing them to check emails or schedules while waiting. This allows the user to use the waiting time for other tasks, enabling efficient time management.

[0041] The call answering unit can provide a multitasking function so that the user can use other services while waiting. For example, the generation AI can call a hospital and provide a message saying, "Please wait. Please use other services in the meantime," so that the user can use other services while waiting. The generation AI can also support the user in using internet services or entertainment services while waiting. This improves user convenience by allowing the user to use other services while waiting.

[0042] The call answering unit can verify the user's identity using the user's voice or facial recognition. For example, when the generation AI calls a hospital, the call answering unit uses the user's voice recognition to verify the user's identity by saying, "This is ____. I'd like to make an appointment." The generation AI can also use the user's facial recognition to verify the user's identity with higher accuracy. This strengthens security by verifying the user's identity using the user's voice or facial recognition.

[0043] The call answering unit can improve the accuracy of identity verification by referencing the user's past call history. For example, when the generation AI calls a hospital, the call answering unit refers to the user's past call history and verifies the user's identity by saying, "This is ____. I made an appointment last time, but I'd like to make another appointment this time." The generation AI can also perform more accurate identity verification based on the user's past call history. This makes it possible to improve the accuracy of identity verification by referencing the user's past call history.

[0044] The call answering unit can strengthen security by combining multiple authentication methods (password, fingerprint, facial recognition, etc.) when verifying identity. For example, when the generation AI calls a hospital, the call answering unit combines voice recognition and a password to verify identity by saying, "This is ____. Please enter your password." The generation AI can also combine fingerprint authentication and facial recognition to perform more accurate identity verification. This allows for stronger security by combining multiple authentication methods.

[0045] The call answering unit can automate the identity verification process, allowing users to authenticate without hassle. For example, when the generation AI calls a hospital, the call answering unit uses voice recognition to automatically verify the user's identity by saying, "This is ____. I'd like to make an appointment." The generation AI can also use facial recognition to allow users to authenticate without hassle. By automating the identity verification process, this allows users to authenticate without hassle.

[0046] The call answering unit can automatically categorize the user's reservation and contact history, making it easier to search. For example, the generation AI in the call answering unit can automatically categorize the user's hospital reservation history and prompt the user, "Would you like to check your past hospital reservation history?" The generation AI can also display the user's contact history in a format that is easier to search. This improves user convenience by automatically categorizing the user's reservation and contact history and making it easier to search.

[0047] The call answering unit analyzes historical data, learns the user's behavioral patterns, and can predict the next appointment or contact. For example, the generation AI in the call answering unit analyzes the user's hospital reservation history and predicts and guides them, asking, "Will your next appointment be around XX / XX?" The generation AI can also predict the next contact based on the user's behavioral patterns and notify them at the appropriate time. In this way, by analyzing historical data and learning the user's behavioral patterns, it is possible to predict the next appointment or contact.

[0048] The call answering unit can link the history data with other applications to provide an integrated user experience. For example, the generation AI can link the user's hospital reservation history with other health management apps and ask, "Would you like to link your next appointment with the health management app?" The generation AI can also link with other applications based on the user's history data to provide a more integrated user experience. In this way, an integrated user experience can be provided by linking the history data with other applications.

[0049] The call answering unit can visualize the historical data, allowing the user to intuitively understand it. For example, the generation AI can visualize the user's hospital reservation history and prompt the user, "Would you like to view your past reservation history in a graph?" The generation AI can also visualize the user's contact history and display it in a more intuitively understandable form. This allows the user to intuitively understand the historical data by visualizing it.

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

[0051] The telephone support AI system can monitor the user's health condition and automatically contact a medical institution if necessary. For example, if the user detects an abnormality in their heart rate or blood pressure, the generating AI will contact the medical institution and say, "Hello, something is wrong with your health. I would like to make an appointment. Please let me know what time is available." The generating AI can also automatically schedule regular health checkups based on the user's health data. This allows the system to monitor the user's health condition and automatically contact a medical institution if necessary, thereby supporting the user's health management.

[0052] The telephone support AI system can manage the user's schedule and suggest the optimal call time. For example, when a user inputs "I would like to make a doctor's appointment," the generating AI will check the user's schedule and suggest "The next available time is XX month, XX day, XX hour." The generating AI can also automatically set the optimal call time based on the user's schedule. This allows for efficient time management by managing the user's schedule and suggesting the optimal call time.

[0053] The telephone support AI system can provide a customizable voice according to the user's preferences. For example, when a user inputs "I would like to make a doctor's appointment," the generation AI generates a voice according to the user's preferences: "Hello, I would like to make a doctor's appointment. Please let me know your available times." The generation AI can also generate conversations in a casual or formal tone based on the voice style selected by the user. This provides a more personalized experience by providing a customizable voice according to the user's preferences.

[0054] The telephone support AI system can predict the content of the next call based on the user's past call history and prepare for it in advance. For example, if a user previously inputs "I would like to make a hospital appointment," the generation AI can predict and guide them by asking, "Would you like to make your next appointment at the same hospital?" The generation AI can also prepare the content of the next call in advance based on the user's past call history to support smooth calls. This allows for efficient calls by predicting the content of the next call based on the user's past call history and preparing in advance.

[0055] The telephone support AI system can automatically summarize the contents of a user's call and save it for later review. For example, the generation AI can call a hospital, automatically summarize the contents of the call, and provide a text message to the user saying, "Your hospital appointment has been completed. The appointment date and time is XX / XX / XX." The generation AI can also summarize the contents of the call and save it for later review by the user. This allows the user to easily review the contents of the call by automatically summarizing the contents of the call and providing it to the user as text.

[0056] The telephone support AI system can remove noise that occurs during a call, enabling clearer conversations. For example, the generation AI can call a hospital, remove noise that occurs during the call, and have a clear conversation saying, "Hello, I'd like to make an appointment with the hospital. What time is available?" The generation AI can also use noise filtering technology to reduce background noise during the call, enabling clearer conversations. This removes noise that occurs during the call, enabling clearer conversations.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The text input unit accepts text input from the user. For example, the user inputs "I would like to make an appointment at the hospital." Step 2: The conversation generation unit generates natural conversation based on the text received by the text input unit. For example, the generation AI uses a text generation AI (e.g., LLM) to generate "Hello, I'd like to make an appointment with a doctor. Please let me know your available times." The generation AI can also use a multimodal generation AI to generate conversations that combine text with images and audio. Step 3: The call answering unit handles the call based on the conversation generated by the conversation generation unit. For example, the generation AI calls a hospital and conveys a request to make an appointment. This allows even people with hearing or speech disabilities to easily make appointments or make contact by generating natural conversation from simple text input and handling the call on their behalf.

[0059] (Example 2) The telephone support AI system according to an embodiment of the present invention is a system that generates natural conversations from simple text input by people with hearing or speech disabilities and handles phone calls on their behalf. This allows people with hearing or speech disabilities to smoothly make reservations or contact hospitals, stores, etc.

[0060] A telephone support AI system according to an embodiment includes a text input unit, a conversation generation unit, and a call answering unit. The text input unit accepts text input from a user. For example, the user may enter, "I'd like to make a hospital appointment." The conversation generation unit generates natural conversation based on the text accepted by the text input unit. For example, the generation AI uses a text generation AI (e.g., LLM) to generate, "Hello, I'd like to make a hospital appointment. What time is available?" The generation AI can also use a multimodal generation AI to generate conversation that combines text, images, and audio. The call answering unit handles calls based on the conversation generated by the conversation generation unit. For example, the generation AI calls a hospital and conveys that it would like to make an appointment. This allows even people with hearing or speech impairments to easily make reservations or make contact by generating natural conversation from simple text input and handling the call.

[0061] The conversation generation unit can understand the context of the text received by the text input unit and generate a conversation by adjusting the appropriate tone and formality. For example, when a user inputs "I'd like to make a doctor's appointment," the generation AI understands the context and generates "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" in a formal tone. The generation AI can also generate "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" in a casual tone. This allows for more natural conversations by generating a conversation by adjusting the appropriate tone and formality to the user's input text.

[0062] The conversation generation unit can learn the user's past input history and generate a conversation style optimized for each individual user. For example, the conversation generation unit learns the user's past input history of "I would like to make a doctor's appointment," and the generation AI generates "Hello, I would like to make another doctor's appointment. Please let me know what time is available." The generation AI can also generate a more personalized conversation style based on the user's preferences and past conversation patterns. In this way, by learning the user's past input history, a conversation style optimized for each individual user can be generated.

[0063] The conversation generation unit can use the emotion estimation function to estimate the user's emotional state and generate a conversation that reflects the appropriate emotion. For example, if the conversation generation unit detects nervousness when the emotion estimation function detects that the user is nervous when they input "I'd like to make a doctor's appointment," the generation AI will generate a gentle tone of "Hello, I'd like to make a doctor's appointment. Can you tell me what time is available?" If the user is relaxed, the generation AI can also generate a casual tone of "Hello, I'd like to make a doctor's appointment. Can you tell me what time is available?" This allows the system to estimate the user's emotional state and generate a conversation that reflects the appropriate emotion, enabling a more considerate response to the user.

[0064] The conversation generation unit can analyze image and voice input in addition to text input to generate richer conversations. For example, if a user inputs "I'd like to make a doctor's appointment" and attaches a photo of the hospital, the generation AI will generate "Hello, I'd like to make a doctor's appointment. Please let me know the available times at this hospital." In addition, when a user provides voice input, the generation AI can analyze the voice and generate appropriate conversation. This allows for the generation of richer conversations by analyzing image and voice input in addition to text input.

[0065] The conversation generation unit supports text input in different languages ​​and can generate multilingual conversations. For example, when a user inputs "I want to make a reservation at the hospital," the generation AI generates "Hello, I would like to make a reservation at the hospital. Could you please tell me the available times?" The generation AI can also handle other languages ​​in the same way and generate appropriate conversations depending on the language input by the user. This makes it possible to generate multilingual conversations by supporting text input in different languages.

[0066] The conversation generation unit uses the emotion estimation function to analyze the emotions of users as they input data in real time and generate conversations that elicit positive emotions. For example, if the conversation generation unit detects anxiety when the emotion estimation function detects anxiety when a user inputs "I'd like to make a doctor's appointment," the generation AI generates a reassuring tone of voice, saying, "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" If the user is relaxed, the generation AI can also generate a casual tone of voice, saying, "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" This improves the user experience by analyzing the emotions of users as they input data in real time and generating conversations that elicit positive emotions.

[0067] The call answering unit can analyze the tone and speed of the other party's voice during a call and generate a response at the appropriate time. For example, the call answering unit's generation AI calls a hospital, analyzes the tone and speed of the other party's voice, and responds at the appropriate time, saying, "Hello, I'd like to make an appointment at the hospital. Please let me know what time you're available." In addition, if the other party is in a hurry, the generation AI can respond succinctly, saying, "I'd like to make an appointment. Please let me know what time you're available." This allows for more natural conversations by analyzing the tone and speed of the other party's voice during a call and generating a response at the appropriate time.

[0068] The call answering unit translates the contents of the call in real time, allowing for smooth conversations with people speaking different languages. For example, the generation AI calls a hospital, translates the contents of the call in real time, and responds in English with, "Hello, I would like to make a reservation at the hospital. Could you please tell me the available times?" The generation AI can also handle other languages ​​in the same way, translating the contents of the call in real time. This allows for smooth conversations with people speaking different languages ​​by translating the contents of the call in real time.

[0069] The call answering unit can use its emotion estimation function to analyze the emotions of the other party and generate a response that reflects the appropriate emotion. For example, the call answering unit's generation AI calls a hospital, analyzes the other party's emotions, and if the other party appears busy, responds concisely, "Hello, I'd like to make a hospital appointment. Can you tell me when you're free?" Alternatively, if the other party appears relaxed, the generation AI can respond in a casual tone, "Hello, I'd like to make a hospital appointment. Can you tell me when you're free?" This allows the caller to analyze their emotions and generate a response that reflects the appropriate emotion, enabling more natural and effective communication.

[0070] The call answering unit can automatically summarize the contents of the call and provide it to the user in text. For example, the generation AI calls a hospital, automatically summarizes the contents of the call, and provides the user with a text message such as, "Your hospital appointment has been completed. The appointment date and time is XX / XX / XX." The generation AI can also summarize the contents of the call and save it so that the user can check it later. This allows the user to easily check the contents of the call by automatically summarizing the contents of the call and providing it to the user in text.

[0071] The call answering unit can remove noise that occurs during a call, enabling clearer audio conversations. For example, the generation AI calls a hospital, removes noise that occurs during the call, and then has a clear voice conversation, saying, "Hello, I'd like to make an appointment with the hospital. Please let me know what time you're available." The generation AI can also use noise filtering technology to reduce background noise during the call, enabling clearer audio conversations. This removes noise that occurs during the call, enabling clearer audio conversations.

[0072] The call answering unit can use its emotion estimation function to monitor the user's emotions during a call in real time and provide appropriate support. For example, the call answering unit's generation AI calls a hospital and monitors the user's emotions during the call in real time. If the user feels anxious, the generation AI can speak in a reassuring tone, saying, "Hello, I'd like to make a hospital appointment. Can you tell me when you're available?" If the user feels relaxed, the generation AI can also speak in a casual tone, saying, "Hello, I'd like to make a hospital appointment. Can you tell me when you're available?" This allows the call answering unit to monitor the user's emotions during a call in real time and provide appropriate support, improving the user experience.

[0073] The call answering unit can automatically determine the priority of calls and give priority to important calls. For example, when the generation AI calls a hospital, the call answering unit will prioritize urgent appointments and respond with, "Hello, I'd like to make an urgent appointment. Please let me know what time is available." The generation AI can also prioritize important calls based on the user's settings. This allows for efficient call management by automatically determining the priority of calls and giving priority to important calls.

[0074] The call answering unit can use the waiting time that occurs during a call to provide the user with relevant information or entertainment. For example, the generation AI can call a hospital and provide the user with health information during the waiting time, saying, "Please wait. We will provide you with the latest health information in the meantime." The generation AI can also provide the user with entertainment such as music or videos during the waiting time. This allows the user to make effective use of the waiting time by providing the user with relevant information or entertainment during the call.

[0075] The call answering unit can use the emotion estimation function to analyze the user's emotions while waiting and provide measures to reduce stress. For example, the call answering unit's generation AI can call a hospital, analyze the user's emotions while waiting, and if the user is feeling stressed, say, "Please wait. Please enjoy some relaxing music." If the user is relaxed, the generation AI can also say in a casual tone, "Please wait. We will provide you with information to help you relax." This improves the user experience by analyzing the user's emotions while waiting and providing measures to reduce stress.

[0076] The call answering unit allows the user to use the waiting time for other tasks, thereby achieving efficient time management. For example, the generation AI calls a hospital and provides a message saying, "Please wait. Please do other tasks in the meantime," so that the user can do other tasks while waiting. The generation AI can also support the user by allowing them to check emails or schedules while waiting. This allows the user to use the waiting time for other tasks, enabling efficient time management.

[0077] The call answering unit can provide a multitasking function so that the user can use other services while waiting. For example, the generation AI can call a hospital and provide a message saying, "Please wait. Please use other services in the meantime," so that the user can use other services while waiting. The generation AI can also support the user in using internet services or entertainment services while waiting. This improves user convenience by allowing the user to use other services while waiting.

[0078] The call answering unit can use the emotion estimation function to analyze the user's emotions in real time while they are waiting and provide content that elicits positive emotions. For example, the call answering unit's generation AI can call a hospital, analyze the user's emotions in real time while they are waiting, and provide a message saying, "Please wait. Enjoy some relaxing music" to elicit positive emotions. If the user is relaxed, the generation AI can also provide a message in a casual tone saying, "Please wait. We will provide you with some relaxing information in the meantime." This improves the user experience by analyzing the user's emotions in real time while they are waiting and providing content that elicits positive emotions.

[0079] The call answering unit can verify the user's identity using the user's voice or facial recognition. For example, when the generation AI calls a hospital, the call answering unit uses the user's voice recognition to verify the user's identity by saying, "This is ____. I'd like to make an appointment." The generation AI can also use the user's facial recognition to verify the user's identity with higher accuracy. This strengthens security by verifying the user's identity using the user's voice or facial recognition.

[0080] The call answering unit can improve the accuracy of identity verification by referencing the user's past call history. For example, when the generation AI calls a hospital, the call answering unit refers to the user's past call history and verifies the user's identity by saying, "This is ____. I made an appointment last time, but I'd like to make another appointment this time." The generation AI can also perform more accurate identity verification based on the user's past call history. This makes it possible to improve the accuracy of identity verification by referencing the user's past call history.

[0081] The call answering unit can use the emotion estimation function to analyze the user's emotions during identity verification and provide measures to reduce stress. For example, when the generation AI calls a hospital, the call answering unit analyzes the user's emotions during identity verification and, if the user is feeling stressed, provides guidance such as, "This is ____. Please relax and we would like to make an appointment." Alternatively, if the user is relaxed, the generation AI can provide guidance in a casual tone, such as, "This is ____. We would like to make an appointment." This improves the user experience by analyzing the user's emotions during identity verification and providing measures to reduce stress.

[0082] The call answering unit can strengthen security by combining multiple authentication methods (password, fingerprint, facial recognition, etc.) when verifying identity. For example, when the generation AI calls a hospital, the call answering unit combines voice recognition and a password to verify identity by saying, "This is ____. Please enter your password." The generation AI can also combine fingerprint authentication and facial recognition to perform more accurate identity verification. This allows for stronger security by combining multiple authentication methods.

[0083] The call answering unit can automate the identity verification process, allowing users to authenticate without hassle. For example, when the generation AI calls a hospital, the call answering unit uses voice recognition to automatically verify the user's identity by saying, "This is ____. I'd like to make an appointment." The generation AI can also use facial recognition to allow users to authenticate without hassle. By automating the identity verification process, this allows users to authenticate without hassle.

[0084] The call answering unit can use its emotion estimation function to analyze the user's emotions during identity verification in real time and provide an authentication process that elicits positive emotions. For example, when the generation AI calls a hospital, the call answering unit analyzes the user's emotions during identity verification in real time and provides guidance such as, "This is ____. Please relax and we'd like to make an appointment," to elicit positive emotions. In addition, if the user is relaxed, the generation AI can also provide guidance in a casual tone, such as, "This is ____. We'd like to make an appointment." This improves the user experience by analyzing the user's emotions during identity verification in real time and providing an authentication process that elicits positive emotions.

[0085] The call answering unit can automatically categorize the user's reservation and contact history, making it easier to search. For example, the generation AI in the call answering unit can automatically categorize the user's hospital reservation history and prompt the user, "Would you like to check your past hospital reservation history?" The generation AI can also display the user's contact history in a format that is easier to search. This improves user convenience by automatically categorizing the user's reservation and contact history and making it easier to search.

[0086] The call answering unit analyzes historical data, learns the user's behavioral patterns, and can predict the next appointment or contact. For example, the generation AI in the call answering unit analyzes the user's hospital reservation history and predicts and guides them, asking, "Will your next appointment be around XX / XX?" The generation AI can also predict the next contact based on the user's behavioral patterns and notify them at the appropriate time. In this way, by analyzing historical data and learning the user's behavioral patterns, it is possible to predict the next appointment or contact.

[0087] The call answering unit can use the emotion estimation function to analyze changes in the user's emotions from historical data and make suggestions to provide a positive experience. For example, the call answering unit's generation AI can analyze the user's hospital reservation history and use the emotion estimation function to suggest, "Would you like to make your next appointment at a time when you can relax?" in order to provide a positive experience. The generation AI can also make more appropriate suggestions based on changes in the user's emotions. This improves the user's experience by analyzing changes in the user's emotions from historical data and making suggestions to provide a positive experience.

[0088] The call answering unit can link the history data with other applications to provide an integrated user experience. For example, the generation AI can link the user's hospital reservation history with other health management apps and ask, "Would you like to link your next appointment with the health management app?" The generation AI can also link with other applications based on the user's history data to provide a more integrated user experience. In this way, an integrated user experience can be provided by linking the history data with other applications.

[0089] The call answering unit can visualize the historical data, allowing the user to intuitively understand it. For example, the generation AI can visualize the user's hospital reservation history and prompt the user, "Would you like to view your past reservation history in a graph?" The generation AI can also visualize the user's contact history and display it in a more intuitively understandable form. This allows the user to intuitively understand the historical data by visualizing it.

[0090] The call answering unit can use the emotion estimation function to analyze changes in the user's emotions from historical data in real time and make suggestions to provide a positive experience. For example, the call answering unit's generation AI can analyze the user's hospital reservation history in real time and use the emotion estimation function to suggest, "Would you like to make your next appointment at a time when you can relax?" in order to provide a positive experience. The generation AI can also make more appropriate suggestions based on changes in the user's emotions. This improves the user's experience by analyzing changes in the user's emotions from historical data in real time and making suggestions to provide a positive experience.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The telephone support AI system can monitor the user's health condition and automatically contact a medical institution if necessary. For example, if the user detects an abnormality in their heart rate or blood pressure, the generating AI will contact the medical institution and say, "Hello, something is wrong with your health. I would like to make an appointment. Please let me know what time is available." The generating AI can also automatically schedule regular health checkups based on the user's health data. This allows the system to monitor the user's health condition and automatically contact a medical institution if necessary, thereby supporting the user's health management.

[0093] The telephone support AI system can manage the user's schedule and suggest the optimal call time. For example, when a user inputs "I would like to make a doctor's appointment," the generating AI will check the user's schedule and suggest "The next available time is XX month, XX day, XX hour." The generating AI can also automatically set the optimal call time based on the user's schedule. This allows for efficient time management by managing the user's schedule and suggesting the optimal call time.

[0094] The telephone support AI system can provide a customizable voice according to the user's preferences. For example, when a user inputs "I would like to make a doctor's appointment," the generation AI generates a voice according to the user's preferences: "Hello, I would like to make a doctor's appointment. Please let me know your available times." The generation AI can also generate conversations in a casual or formal tone based on the voice style selected by the user. This provides a more personalized experience by providing a customizable voice according to the user's preferences.

[0095] The telephone support AI system can estimate the user's emotions and provide relaxation content to reduce stress. For example, if a user inputs "I would like to make a doctor's appointment," and the emotion estimation function detects stress, the generation AI will respond with, "Please wait. Please enjoy some relaxing music in the meantime." If the user is relaxed, the generation AI can also respond in a casual tone with, "Please wait. We will provide you with some relaxing information in the meantime." This improves the user experience by estimating the user's emotions and providing relaxation content to reduce stress.

[0096] The telephone support AI system can estimate the user's emotions and generate conversations designed to elicit positive emotions. For example, if a user types "I'd like to make a doctor's appointment," and the emotion estimation function detects anxiety, the generation AI will generate a reassuring tone, saying, "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" If the user is relaxed, the generation AI can also generate a casual tone, saying, "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" This improves the user experience by estimating the user's emotions and generating conversations designed to elicit positive emotions.

[0097] The telephone support AI system can estimate the user's emotions and generate conversations that reflect appropriate emotions. For example, if a user inputs "I'd like to make a doctor's appointment," and the emotion estimation function detects nervousness, the generation AI will generate a gentle tone of voice saying, "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" If the user is relaxed, the generation AI can also generate a casual tone of voice saying, "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" This allows the system to estimate the user's emotions and generate conversations that reflect appropriate emotions, enabling a more considerate response to the user.

[0098] The telephone support AI system can estimate the user's emotions and provide feedback according to their emotions. For example, if a user inputs "I'd like to make a doctor's appointment," and the emotion estimation function detects anxiety, the generation AI will provide reassuring feedback such as "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" If the user is relaxed, the generation AI can also provide feedback in a casual tone, such as "Hello, I'd like to make a doctor's appointment. Can you tell me what time you're available?" This improves the user experience by estimating the user's emotions and providing feedback according to their emotions.

[0099] The telephone support AI system can predict the content of the next call based on the user's past call history and prepare for it in advance. For example, if a user previously inputs "I would like to make a hospital appointment," the generation AI can predict and guide them by asking, "Would you like to make your next appointment at the same hospital?" The generation AI can also prepare the content of the next call in advance based on the user's past call history to support smooth calls. This allows for efficient calls by predicting the content of the next call based on the user's past call history and preparing in advance.

[0100] The telephone support AI system can automatically summarize the contents of a user's call and save it for later review. For example, the generation AI can call a hospital, automatically summarize the contents of the call, and provide a text message to the user saying, "Your hospital appointment has been completed. The appointment date and time is XX / XX / XX." The generation AI can also summarize the contents of the call and save it for later review by the user. This allows the user to easily review the contents of the call by automatically summarizing the contents of the call and providing it to the user as text.

[0101] The telephone support AI system can remove noise that occurs during a call, enabling clearer conversations. For example, the generation AI can call a hospital, remove noise that occurs during the call, and have a clear conversation saying, "Hello, I'd like to make an appointment with the hospital. What time is available?" The generation AI can also use noise filtering technology to reduce background noise during the call, enabling clearer conversations. This removes noise that occurs during the call, enabling clearer conversations.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The text input unit accepts text input from the user. For example, the user inputs "I would like to make an appointment at the hospital." Step 2: The conversation generation unit generates natural conversation based on the text received by the text input unit. For example, the generation AI uses a text generation AI (e.g., LLM) to generate "Hello, I'd like to make an appointment with a doctor. Please let me know your available times." The generation AI can also use a multimodal generation AI to generate conversations that combine text with images and audio. Step 3: The call answering unit handles the call based on the conversation generated by the conversation generation unit. For example, the generation AI calls a hospital and conveys a request to make an appointment. This allows even people with hearing or speech disabilities to easily make appointments or make contact by generating natural conversation from simple text input and handling the call on their behalf.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

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

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

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

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0132] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

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

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0148] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] 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.

[0163] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0164] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a text input unit that accepts text input from a user; a conversation generation unit that generates natural conversation based on the text received by the text input unit; a call handling unit that handles calls based on the conversation generated by the conversation generation unit. A system characterized by:

2. The conversation generation unit In addition to text input, it analyzes images and voice input to generate richer conversations.

2. The system of claim 1.

3. The call answering unit Analyzes the tone and speed of the other person's voice during a call and generates a response at the appropriate time 2. The system of claim 1.

4. The call answering unit Automatically prioritize calls and prioritize important calls 2. The system of claim 1.

5. The call answering unit Verify the user's identity using voice and facial recognition 2. The system of claim 1.

6. The call answering unit Analyze changes in user emotions from historical data and make suggestions to provide a positive experience 2. The system of claim 1.

7. The conversation generation unit Estimate the user's emotional state and generate conversations that reflect appropriate emotions 2. The system of claim 1.

Images