System

Abstract

An object of the system according to the embodiment is to realize a dialogue with the user by reproducing the voice and speech of the deceased.SOLUTION: A system includes a voice generation unit, a sentence generation unit, a storage unit, and an interaction unit. The voice generation part reproduces the voice of the deceased. The sentence generation part generates the speech of the deceased. The storage unit stores information on the deceased. The interaction unit realizes interaction with a user.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] With conventional technology, it is difficult to reproduce conversations with the deceased, and there is room for improvement in technology for reproducing the voices and utterances of the deceased.

[0005] The system according to the embodiment aims to reproduce the voice and words of the deceased and realize a dialogue with the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice generation unit, a sentence generation unit, a memory unit, and a dialogue unit. The voice generation unit reproduces the voice of the deceased. The sentence generation unit generates utterances of the deceased. The memory unit stores information about the deceased. The dialogue unit realizes dialogue with the user. [Effects of the Invention]

[0007] The system according to the embodiment can reproduce the voice and words of the deceased person and realize a dialogue with the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The conversation system according to the embodiment of the present invention is a system in which an AI that memorizes the voice, past statements, and information of the deceased converses as if the deceased had spoken. This allows the conversation system to reproduce the voice and statements of the deceased and realize a dialogue with the user.

[0029] The conversation system according to the embodiment includes a voice generation unit, a sentence generation unit, a memory unit, and a dialogue unit. The voice generation unit reproduces the voice of the deceased. For example, the voice generation unit collects voice data from the deceased's lifetime, and the voice generation AI learns the deceased's voice based on the collected data. The voice generation unit can also analyze and reproduce the characteristics of the deceased's voice using audio and video messages recorded by the deceased. The voice generation unit generates a voice response in the deceased's voice in response to user input. The sentence generation unit generates statements from the deceased. For example, the sentence generation unit collects the deceased's statements, written notes, diary entries, and social media posts, and the sentence generation AI learns the characteristics of the deceased's statements based on the collected data. The sentence generation unit can also analyze and reproduce the style and content of the deceased's statements using letters and blog posts written by the deceased. The sentence generation unit generates the deceased's statements based on user questions and the flow of conversation. The memory unit stores information about the deceased. For example, the memory unit collects information about the deceased's life, and the AI ​​builds a memory of the deceased based on that information. The memory unit can also collect information about the deceased, such as their hobbies, interests, and relationships with family and friends, and the AI ​​can store that information. The memory unit also allows the AI ​​to converse as if the deceased were the deceased based on the stored information. The dialogue unit realizes dialogue with the user. For example, the dialogue unit realizes dialogue with the user by combining a voice generation AI and a sentence generation AI. When the user speaks to the deceased, the voice generation AI can respond in the deceased's voice, and the sentence generation AI can generate the deceased's utterances. When the user asks, "Mom, how was your day?", the dialogue unit can respond with, "Today was a great day. How was it for you?" In this way, the conversation system according to the embodiment can reproduce the voice and utterances of the deceased and realize dialogue with the user. For example, the user can reminisce about memories with the deceased or receive advice from the deceased. Conversation with the deceased can also provide emotional healing and comfort to the user.

[0030] The voice generation unit learns the subtle acoustic characteristics of the deceased's voice and is able to reproduce breathing and voice tremors. The voice generation unit, for example, analyzes voice data from the deceased's lifetime, and the voice generation AI learns the subtle acoustic characteristics of the deceased's voice. For example, to reproduce the deceased's breathing and voice tremors, the voice generation AI learns the characteristics of the deceased's voice and reproduces them. The voice generation unit also learns the characteristics of the deceased's voice to reproduce the subtle acoustic characteristics of the deceased's voice. For example, to reproduce the deceased's voice tremors and breathing, the voice generation AI learns the characteristics of the deceased's voice and reproduces them. The voice generation unit also learns the characteristics of the deceased's voice to reproduce the subtle acoustic characteristics of the deceased's voice. For example, to reproduce the deceased's voice tremors and breathing, the voice generation AI learns the characteristics of the deceased's voice and reproduces them. This makes it possible to reproduce the subtle acoustic characteristics of the deceased's voice.

[0031] The voice generation unit learns voice data from the deceased's lifetime and can generate a voice that corresponds to their age and health condition. For example, the voice generation unit collects voice data from the deceased's lifetime, and the voice generation AI learns a voice that corresponds to their age and health condition. For example, to reproduce the voice of the deceased when they were young and when they were elderly, the voice generation AI learns changes in the deceased's voice and reproduces it. The voice generation unit also collects voice data from the deceased's lifetime and the voice generation AI learns a voice that corresponds to their age and health condition. For example, to reproduce the voice of the deceased when they were healthy and when they were ill, the voice generation AI learns changes in the deceased's voice and reproduces it. The voice generation unit also collects voice data from the deceased's lifetime and the voice generation AI learns a voice that corresponds to their age and health condition. For example, to reproduce the voice of the deceased when they were young and when they were elderly, the voice generation AI learns changes in the deceased's voice and reproduces it. This makes it possible to reproduce a voice that corresponds to the deceased's age and health condition.

[0032] The voice generation unit can learn and reproduce the singing voice and recitation style of the deceased. For example, the voice generation unit collects recitations of songs and poems that the deceased sang before their death, and the voice generation AI learns the singing voice and recitation style of the deceased. For example, the voice generation AI reproduces the singing voice of the deceased based on audio data of songs sung by the deceased. The voice generation unit also collects recitations of songs and poems that the deceased sang before their death, and the voice generation AI learns the singing voice and recitation style of the deceased. For example, the voice generation AI reproduces the recitation style of the deceased based on audio data of poems recited by the deceased. The voice generation unit also collects recitations of songs and poems that the deceased sang before their death, and the voice generation AI learns the singing voice and recitation style of the deceased. For example, the voice generation AI reproduces the singing voice of the deceased based on audio data of songs sung by the deceased. In this way, the singing voice and recitation style of the deceased can be reproduced.

[0033] The speech generation unit learns multilingual speech data and can reproduce speech in different languages ​​and dialects. For example, the speech generation unit collects speech data in different languages ​​and dialects spoken by the deceased during their lifetime, and the speech generation AI learns the multilingual speech data. For example, the speech generation AI reproduces speech in different languages ​​based on speech data of the deceased spoken in English or French. The speech generation unit also collects speech data in different languages ​​and dialects spoken by the deceased during their lifetime, and the speech generation AI learns the multilingual speech data. For example, the speech generation AI reproduces speech in a dialect based on speech data of the deceased spoken in a Japanese dialect. The speech generation unit also collects speech data in different languages ​​and dialects spoken by the deceased during their lifetime, and the speech generation AI learns the multilingual speech data. For example, the speech generation AI reproduces speech in a different language based on speech data of the deceased spoken in English or French. This makes it possible to reproduce speech in different languages ​​and dialects.

[0034] The sentence generation unit can learn and reproduce the specific phrases and expressions of the deceased. For example, the sentence generation unit analyzes speech data from the deceased's lifetime, and the sentence generation AI learns the specific phrases and expressions of the deceased. For example, in order to reproduce phrases and expressions that the deceased often used, the sentence generation AI learns the speech style of the deceased and reproduces them. In addition, in order to reproduce the speech style of the deceased, the sentence generation AI learns the specific phrases and expressions of the deceased. For example, in order to reproduce phrases and expressions that the deceased often used, the sentence generation AI learns the speech style of the deceased and reproduces them. In addition, in order to reproduce the speech style of the deceased, the sentence generation AI learns the specific phrases and expressions of the deceased. For example, in order to reproduce phrases and expressions that the deceased often used, the sentence generation AI learns the speech style of the deceased and reproduces them. In this way, the specific phrases and expressions of the deceased can be reproduced.

[0035] The sentence generation unit can learn background information of the deceased's utterances and generate utterances appropriate for different situations and contexts. For example, the sentence generation unit analyzes data of utterances made by the deceased while they were alive, and the sentence generation AI learns the background information of the deceased's utterances. For example, to reproduce what the deceased said in a specific situation, the sentence generation AI learns the background information of the deceased's utterances and reproduces them. In addition, the sentence generation unit analyzes the utterance data of the deceased to learn the background information of the deceased's utterances. For example, to reproduce what the deceased said in a specific situation, the sentence generation AI learns the background information of the deceased's utterances and reproduces them. In addition, the sentence generation unit analyzes the utterance data of the deceased to learn the background information of the deceased's utterances. For example, to reproduce what the deceased said in a specific situation, the sentence generation AI learns the background information of the deceased's utterances and reproduces them. This makes it possible to generate utterances appropriate for different situations and contexts.

[0036] The text generation unit can learn the literary works of the deceased and reproduce their poems and essays. For example, the text generation unit collects poems and essays written by the deceased before they died, and the text generation AI learns the deceased's literary works. For example, to reproduce the style and content of the poems written by the deceased, the text generation AI learns the deceased's literary works and reproduces them. The text generation unit also collects poems and essays written by the deceased before they died, and the text generation AI learns the deceased's literary works. For example, to reproduce the style and content of the essays written by the deceased, the text generation AI learns the deceased's literary works and reproduces them. The text generation unit also collects poems and essays written by the deceased before they died, and the text generation AI learns the deceased's literary works. For example, to reproduce the style and content of the poems written by the deceased, the text generation AI learns the deceased's literary works and reproduces them. This makes it possible to reproduce poems and essays written by the deceased.

[0037] The sentence generation unit learns multilingual text data and can reproduce utterances in different languages ​​and cultural spheres. For example, the sentence generation unit collects text data in different languages ​​and cultural spheres written by the deceased during their lifetime, and the sentence generation AI learns the multilingual text data. For example, the sentence generation AI reproduces utterances in different languages ​​based on text data written by the deceased in English and French. The sentence generation unit also collects text data in different languages ​​and cultural spheres written by the deceased during their lifetime, and the sentence generation AI learns the multilingual text data. For example, the sentence generation AI reproduces utterances in the dialect based on text data written by the deceased in a Japanese dialect. The sentence generation unit also collects text data in different languages ​​and cultural spheres written by the deceased during their lifetime, and the sentence generation AI learns the multilingual text data. For example, the sentence generation AI reproduces utterances in different languages ​​based on text data written by the deceased in English and French. This makes it possible to reproduce utterances in different languages ​​and cultural spheres.

[0038] The memory unit learns information from the deceased's lifetime and can recreate memories corresponding to different periods and events. For example, the memory unit collects information from the deceased's lifetime, and the AI ​​learns memories corresponding to different periods and events. For example, to recreate memories from when the deceased was young and memories from when they were old, the AI ​​learns and recreates information about the deceased. The memory unit also collects information from the deceased's lifetime and the AI ​​learns memories corresponding to different periods and events. For example, to recreate memories the deceased had in response to a particular event, the AI ​​learns and recreates information about the deceased. The memory unit also collects information from the deceased's lifetime and the AI ​​learns memories corresponding to different periods and events. For example, to recreate memories from when the deceased was young and memories from when they were old, the AI ​​learns and recreates information about the deceased. This makes it possible to recreate memories corresponding to different periods and events.

[0039] The memory unit learns the experiences of the deceased and is able to recreate the events they experienced. The memory unit, for example, collects information about the deceased when they were alive, and the AI ​​learns the experiences of the deceased. For example, the AI ​​learns and recreates the experiences of the deceased in order to recreate the feelings the deceased had in response to specific events. The memory unit also learns the experiences of the deceased in order to recreate the events they experienced. For example, the AI ​​learns and recreates the feelings the deceased had in response to specific events. The memory unit also learns the experiences of the deceased in order to recreate the events they experienced. For example, the AI ​​learns and recreates the feelings the deceased had in response to specific events. In this way, the events the deceased experienced can be recreated.

[0040] The memory unit learns multicultural information and can recreate memories from different cultures and backgrounds. For example, the memory unit collects information from the deceased's lifetime, and the AI ​​learns multicultural information. For example, to recreate events that the deceased experienced in different cultures and backgrounds, the AI ​​learns multicultural information. In addition, the memory unit learns multicultural information to recreate the deceased's memories. For example, to recreate events that the deceased experienced in different cultures and backgrounds, the AI ​​learns multicultural information to recreate the deceased's memories. In addition, the memory unit learns multicultural information to recreate the deceased's memories. For example, to recreate events that the deceased experienced in different cultures and backgrounds, the AI ​​learns multicultural information to recreate the deceased's memories. In this way, memories from different cultures and backgrounds can be recreated.

[0041] The dialogue unit can learn the user's past dialogue history and understand the context of the dialogue. For example, the dialogue unit collects the user's past dialogue history, and the AI ​​learns the context of the dialogue. For example, it understands the flow of the dialogue based on what the user has said in the past and generates an appropriate response. The dialogue unit also collects the user's past dialogue history, and the AI ​​learns the context of the dialogue. For example, it understands the flow of the dialogue based on what the user has said in the past and generates an appropriate response. The dialogue unit also collects the user's past dialogue history, and the AI ​​learns the context of the dialogue. For example, it understands the flow of the dialogue based on what the user has said in the past and generates an appropriate response. In this way, the context of the dialogue can be understood based on the user's past dialogue history.

[0042] The dialogue unit can learn the user's situation information and generate dialogues that correspond to different situations and contexts. For example, the dialogue unit collects the user's situation information and the AI ​​generates dialogues that correspond to different situations and contexts. For example, the dialogue unit determines whether the user is at work or on vacation and generates dialogue content accordingly. The dialogue unit also collects the user's situation information and the AI ​​generates dialogues that correspond to different situations and contexts. For example, the dialogue unit determines whether the user is at home or out and generates dialogue content accordingly. The dialogue unit also collects the user's situation information and the AI ​​generates dialogues that correspond to different situations and contexts. For example, the dialogue unit determines whether the user is alone or with someone and generates dialogue content accordingly. This makes it possible to generate dialogues that correspond to different situations and contexts.

[0043] The dialogue unit learns the user's memories and can recreate memories spent with the deceased. For example, the dialogue unit collects memories the user spent with the deceased, and the AI ​​learns them. For example, to recreate memories of a trip the user took with the deceased, the AI ​​learns that information and recreates it. The dialogue unit also collects memories the user spent with the deceased, and the AI ​​learns them. For example, to recreate memories of a specific event the user spent with the deceased, the AI ​​learns that information and recreates it. The dialogue unit also collects memories the user spent with the deceased, and the AI ​​learns them. For example, to recreate everyday memories the user spent with the deceased, the AI ​​learns that information and recreates it. In this way, memories spent with the deceased can be recreated.

[0044] The dialogue unit learns multilingual dialogue data and can reproduce dialogues in different languages ​​and cultures. For example, the dialogue unit collects experiences of users conversing with the deceased in different languages ​​and cultures, and the AI ​​learns the data. For example, to reproduce the user's experience of conversing with the deceased in English or French, the AI ​​learns multilingual dialogue data and reproduces it. The dialogue unit also collects experiences of users conversing with the deceased in different languages ​​and cultures, and the AI ​​learns the data. For example, to reproduce the user's experience of conversing with the deceased in a Japanese dialect, the AI ​​learns multilingual dialogue data and reproduces it. The dialogue unit also collects experiences of users conversing with the deceased in different languages ​​and cultures, and the AI ​​learns the data. For example, to reproduce the user's experience of conversing with the deceased in English or French, the AI ​​learns multilingual dialogue data and reproduces it. This makes it possible to reproduce dialogues in different languages ​​and cultures.

[0045] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0046] The conversation system may further include a health management unit that monitors the user's health condition. For example, the health management unit may monitor the user's vital signs, such as heart rate, blood pressure, and body temperature, in real time, and issue an appropriate alert if an abnormality is detected. The health management unit may also provide appropriate advice and reminders based on the user's health condition. For example, if the user is feeling stressed, the health management unit may provide advice on how to relax. The health management unit may also record the user's health data over the long term and track changes in the user's health condition. This may support the user's health management.

[0047] The conversation system may further include a hobby providing unit that provides customized content based on the user's hobbies and interests. For example, the hobby providing unit may collect information about the user's favorite music, movies, books, etc., and provide recommended content based on that information. The hobby providing unit may also analyze the user's past preference data and make suggestions to help the user discover new hobbies and interests. For example, if the user likes movies of a particular genre, the hobby providing unit may recommend new movies of the same genre. The hobby providing unit may also provide information about events and activities related to the user's hobbies. This may help the user deepen their hobbies and interests.

[0048] The conversation system may further include a learning support unit that supports the user's learning. For example, the learning support unit may provide information on themes or fields the user wants to study and support the user in creating a study plan. The learning support unit may also track the user's learning progress and provide appropriate feedback. For example, when the user is working on a specific task, the learning support unit may provide advice and resources according to the user's progress. The learning support unit may also provide customized learning content that matches the user's learning style and pace. This may help improve the user's learning effectiveness.

[0049] The conversation system may further include a lifestyle management unit that supports the user's lifestyle. For example, the lifestyle management unit may manage the user's schedule and tasks and provide reminders. The lifestyle management unit may also track the user's sleep patterns and dietary records and provide advice on maintaining a healthy lifestyle. For example, if the user is not getting enough sleep, the lifestyle management unit may make suggestions for improving sleep. The lifestyle management unit may also provide customized reminders and notifications that are tailored to the user's lifestyle. This may help improve the user's quality of life.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The voice generation unit reproduces the voice of the deceased. For example, the voice generation unit collects voice data from the deceased's lifetime, and the voice generation AI learns the deceased's voice based on that data. The voice generation unit can also analyze and reproduce the characteristics of the deceased's voice using audio or video messages recorded by the deceased during their lifetime. The voice generation unit also generates a voice response in the deceased's voice in response to user input. Step 2: The text generation unit generates the deceased's statements. For example, the text generation unit collects statements made by the deceased, as well as notes, diaries, and social media posts made by the deceased, and the text generation AI learns the characteristics of the deceased's statements based on these. The text generation unit can also analyze and reproduce the style and content of the deceased's statements using letters and blog posts written by the deceased. The text generation unit also generates the deceased's statements in response to questions from the user and the flow of the conversation. Step 3: The memory unit stores information about the deceased. For example, the memory unit collects information about the deceased while they were alive, and the AI ​​uses this information to construct a memory of the deceased. The memory unit can also collect information about the deceased, such as their hobbies and interests, and relationships with family and friends, and the AI ​​can store this information. The memory unit also uses the stored information to allow the AI ​​to converse as if they were the deceased. Step 4: The dialogue unit realizes a dialogue with the user. For example, the dialogue unit realizes a dialogue with the user by combining a voice generation AI and a sentence generation AI. In addition, when the user speaks to the deceased, the dialogue unit can have the voice generation AI respond in the deceased's voice, and the sentence generation AI generate the deceased's words. In addition, when the user asks, "Mom, how was your day?", the dialogue unit can have the AI ​​respond in the form of, "Today was a great day. How was it for you?"

[0052] (Example 2) The conversation system according to the embodiment of the present invention is a system in which an AI that memorizes the voice, past statements, and information of the deceased converses as if the deceased had spoken. This allows the conversation system to reproduce the voice and statements of the deceased and realize a dialogue with the user.

[0053] The conversation system according to the embodiment includes a voice generation unit, a sentence generation unit, a memory unit, and a dialogue unit. The voice generation unit reproduces the voice of the deceased. For example, the voice generation unit collects voice data from the deceased's lifetime, and the voice generation AI learns the deceased's voice based on the collected data. The voice generation unit can also analyze and reproduce the characteristics of the deceased's voice using audio and video messages recorded by the deceased. The voice generation unit generates a voice response in the deceased's voice in response to user input. The sentence generation unit generates statements from the deceased. For example, the sentence generation unit collects the deceased's statements, written notes, diary entries, and social media posts, and the sentence generation AI learns the characteristics of the deceased's statements based on the collected data. The sentence generation unit can also analyze and reproduce the style and content of the deceased's statements using letters and blog posts written by the deceased. The sentence generation unit generates the deceased's statements based on user questions and the flow of conversation. The memory unit stores information about the deceased. For example, the memory unit collects information about the deceased's life, and the AI ​​builds a memory of the deceased based on that information. The memory unit can also collect information about the deceased, such as their hobbies, interests, and relationships with family and friends, and the AI ​​can store that information. The memory unit also allows the AI ​​to converse as if the deceased were the deceased based on the stored information. The dialogue unit realizes dialogue with the user. For example, the dialogue unit realizes dialogue with the user by combining a voice generation AI and a sentence generation AI. When the user speaks to the deceased, the voice generation AI can respond in the deceased's voice, and the sentence generation AI can generate the deceased's utterances. When the user asks, "Mom, how was your day?", the dialogue unit can respond with, "Today was a great day. How was it for you?" In this way, the conversation system according to the embodiment can reproduce the voice and utterances of the deceased and realize dialogue with the user. For example, the user can reminisce about memories with the deceased or receive advice from the deceased. Conversation with the deceased can also provide emotional healing and comfort to the user.

[0054] The voice generation unit can learn emotional changes using the emotion estimation function and adjust the tone and pitch of the voice according to the emotion. For example, the voice generation unit analyzes the voice data of the deceased while they were alive and learns emotional changes using the emotion estimation function. For example, to reproduce the tone and pitch of the voice of a happy person, the voice generation AI learns the emotional changes and generates a voice according to the emotion. In addition, to reproduce the emotional nuances of the deceased's voice, the voice generation AI uses the emotion estimation function to adjust the tone and pitch of the deceased's voice. For example, to reproduce the tone and pitch of the voice of a sad person, the voice generation AI learns the emotional changes and generates a voice according to the emotion. In addition, to reproduce the emotional nuances of the deceased's voice, the voice generation AI uses the emotion estimation function to adjust the tone and pitch of the deceased's voice. For example, to reproduce the tone and pitch of the voice of an angry person, the voice generation AI learns the emotional changes and generates a voice according to the emotion. This allows the emotional nuances of the deceased's voice to be reproduced.

[0055] The voice generation unit learns the subtle acoustic characteristics of the deceased's voice and is able to reproduce breathing and voice tremors. The voice generation unit, for example, analyzes voice data from the deceased's lifetime, and the voice generation AI learns the subtle acoustic characteristics of the deceased's voice. For example, to reproduce the deceased's breathing and voice tremors, the voice generation AI learns the characteristics of the deceased's voice and reproduces them. The voice generation unit also learns the characteristics of the deceased's voice to reproduce the subtle acoustic characteristics of the deceased's voice. For example, to reproduce the deceased's voice tremors and breathing, the voice generation AI learns the characteristics of the deceased's voice and reproduces them. The voice generation unit also learns the characteristics of the deceased's voice to reproduce the subtle acoustic characteristics of the deceased's voice. For example, to reproduce the deceased's voice tremors and breathing, the voice generation AI learns the characteristics of the deceased's voice and reproduces them. This makes it possible to reproduce the subtle acoustic characteristics of the deceased's voice.

[0056] The voice generation unit learns voice data from the deceased's lifetime and can generate a voice that corresponds to their age and health condition. For example, the voice generation unit collects voice data from the deceased's lifetime, and the voice generation AI learns a voice that corresponds to their age and health condition. For example, to reproduce the voice of the deceased when they were young and when they were elderly, the voice generation AI learns changes in the deceased's voice and reproduces it. The voice generation unit also collects voice data from the deceased's lifetime and the voice generation AI learns a voice that corresponds to their age and health condition. For example, to reproduce the voice of the deceased when they were healthy and when they were ill, the voice generation AI learns changes in the deceased's voice and reproduces it. The voice generation unit also collects voice data from the deceased's lifetime and the voice generation AI learns a voice that corresponds to their age and health condition. For example, to reproduce the voice of the deceased when they were young and when they were elderly, the voice generation AI learns changes in the deceased's voice and reproduces it. This makes it possible to reproduce a voice that corresponds to the deceased's age and health condition.

[0057] The voice generation unit can learn and reproduce the singing voice and recitation style of the deceased. For example, the voice generation unit collects recitations of songs and poems that the deceased sang before their death, and the voice generation AI learns the singing voice and recitation style of the deceased. For example, the voice generation AI reproduces the singing voice of the deceased based on audio data of songs sung by the deceased. The voice generation unit also collects recitations of songs and poems that the deceased sang before their death, and the voice generation AI learns the singing voice and recitation style of the deceased. For example, the voice generation AI reproduces the recitation style of the deceased based on audio data of poems recited by the deceased. The voice generation unit also collects recitations of songs and poems that the deceased sang before their death, and the voice generation AI learns the singing voice and recitation style of the deceased. For example, the voice generation AI reproduces the singing voice of the deceased based on audio data of songs sung by the deceased. In this way, the singing voice and recitation style of the deceased can be reproduced.

[0058] The speech generation unit learns multilingual speech data and can reproduce speech in different languages ​​and dialects. For example, the speech generation unit collects speech data in different languages ​​and dialects spoken by the deceased during their lifetime, and the speech generation AI learns the multilingual speech data. For example, the speech generation AI reproduces speech in different languages ​​based on speech data of the deceased spoken in English or French. The speech generation unit also collects speech data in different languages ​​and dialects spoken by the deceased during their lifetime, and the speech generation AI learns the multilingual speech data. For example, the speech generation AI reproduces speech in a dialect based on speech data of the deceased spoken in a Japanese dialect. The speech generation unit also collects speech data in different languages ​​and dialects spoken by the deceased during their lifetime, and the speech generation AI learns the multilingual speech data. For example, the speech generation AI reproduces speech in a different language based on speech data of the deceased spoken in English or French. This makes it possible to reproduce speech in different languages ​​and dialects.

[0059] The voice generation unit can use an emotion estimation function to adjust the tone and content of the voice according to the user's emotions. For example, the voice generation unit analyzes the user's emotions in real time, and the voice generation AI adjusts the tone and content of the deceased's voice. For example, when the user is sad, the voice generation unit softens the tone of the deceased's voice and generates comforting content. The voice generation unit also analyzes the user's emotions in real time, and the voice generation AI adjusts the tone and content of the deceased's voice. For example, when the user is happy, the voice generation unit brightens the tone of the deceased's voice and generates empathetic content. The voice generation unit also analyzes the user's emotions in real time, and the voice generation AI adjusts the tone and content of the deceased's voice. For example, when the user is angry, the voice generation unit calms the tone of the deceased's voice and generates calm content. This allows the tone and content of the deceased's voice to be adjusted according to the user's emotions.

[0060] The sentence generation unit can learn emotional changes using the emotion estimation function and generate speech content that corresponds to the emotions. For example, the sentence generation unit analyzes speech data from the deceased's lifetime and learns emotional changes using the emotion estimation function. For example, to reproduce speech content from when the deceased was happy, the sentence generation AI learns emotional changes and generates speech that corresponds to the emotions. Furthermore, to reproduce the emotional nuances of the deceased's speech, the sentence generation AI uses the emotion estimation function to adjust the speech content of the deceased. For example, to reproduce speech content from when the deceased was sad, the sentence generation AI learns emotional changes and generates speech that corresponds to the emotions. Furthermore, to reproduce the emotional nuances of the deceased's speech, the sentence generation AI uses the emotion estimation function to adjust the speech content of the deceased. For example, to reproduce speech content from when the deceased was angry, the sentence generation AI learns emotional changes and generates speech that corresponds to the emotions. This makes it possible to reproduce the emotional nuances of the deceased's speech.

[0061] The sentence generation unit can learn and reproduce the specific phrases and expressions of the deceased. For example, the sentence generation unit analyzes speech data from the deceased's lifetime, and the sentence generation AI learns the specific phrases and expressions of the deceased. For example, in order to reproduce phrases and expressions that the deceased often used, the sentence generation AI learns the speech style of the deceased and reproduces them. In addition, in order to reproduce the speech style of the deceased, the sentence generation AI learns the specific phrases and expressions of the deceased. For example, in order to reproduce phrases and expressions that the deceased often used, the sentence generation AI learns the speech style of the deceased and reproduces them. In addition, in order to reproduce the speech style of the deceased, the sentence generation AI learns the specific phrases and expressions of the deceased. For example, in order to reproduce phrases and expressions that the deceased often used, the sentence generation AI learns the speech style of the deceased and reproduces them. In this way, the specific phrases and expressions of the deceased can be reproduced.

[0062] The sentence generation unit can learn background information of the deceased's utterances and generate utterances appropriate for different situations and contexts. For example, the sentence generation unit analyzes data of utterances made by the deceased while they were alive, and the sentence generation AI learns the background information of the deceased's utterances. For example, to reproduce what the deceased said in a specific situation, the sentence generation AI learns the background information of the deceased's utterances and reproduces them. In addition, the sentence generation unit analyzes the utterance data of the deceased to learn the background information of the deceased's utterances. For example, to reproduce what the deceased said in a specific situation, the sentence generation AI learns the background information of the deceased's utterances and reproduces them. In addition, the sentence generation unit analyzes the utterance data of the deceased to learn the background information of the deceased's utterances. For example, to reproduce what the deceased said in a specific situation, the sentence generation AI learns the background information of the deceased's utterances and reproduces them. This makes it possible to generate utterances appropriate for different situations and contexts.

[0063] The text generation unit can learn the literary works of the deceased and reproduce their poems and essays. For example, the text generation unit collects poems and essays written by the deceased before they died, and the text generation AI learns the deceased's literary works. For example, to reproduce the style and content of the poems written by the deceased, the text generation AI learns the deceased's literary works and reproduces them. The text generation unit also collects poems and essays written by the deceased before they died, and the text generation AI learns the deceased's literary works. For example, to reproduce the style and content of the essays written by the deceased, the text generation AI learns the deceased's literary works and reproduces them. The text generation unit also collects poems and essays written by the deceased before they died, and the text generation AI learns the deceased's literary works. For example, to reproduce the style and content of the poems written by the deceased, the text generation AI learns the deceased's literary works and reproduces them. This makes it possible to reproduce poems and essays written by the deceased.

[0064] The sentence generation unit learns multilingual text data and can reproduce utterances in different languages ​​and cultural spheres. For example, the sentence generation unit collects text data in different languages ​​and cultural spheres written by the deceased during their lifetime, and the sentence generation AI learns the multilingual text data. For example, the sentence generation AI reproduces utterances in different languages ​​based on text data written by the deceased in English and French. The sentence generation unit also collects text data in different languages ​​and cultural spheres written by the deceased during their lifetime, and the sentence generation AI learns the multilingual text data. For example, the sentence generation AI reproduces utterances in the dialect based on text data written by the deceased in a Japanese dialect. The sentence generation unit also collects text data in different languages ​​and cultural spheres written by the deceased during their lifetime, and the sentence generation AI learns the multilingual text data. For example, the sentence generation AI reproduces utterances in different languages ​​based on text data written by the deceased in English and French. This makes it possible to reproduce utterances in different languages ​​and cultural spheres.

[0065] The sentence generation unit can use the emotion estimation function to adjust the content of the utterances according to the user's emotions. For example, the sentence generation unit analyzes the user's emotions in real time, and the sentence generation AI adjusts the content of the utterances of the deceased. For example, when the user is sad, the content of the utterances of the deceased is adjusted to be comforting. The sentence generation unit also analyzes the user's emotions in real time, and the sentence generation AI adjusts the content of the utterances of the deceased. For example, when the user is happy, the content of the utterances of the deceased is adjusted to be empathetic. The sentence generation unit also analyzes the user's emotions in real time, and the sentence generation AI adjusts the content of the utterances of the deceased. For example, when the user is angry, the content of the utterances of the deceased is adjusted to be calm. In this way, the content of the utterances of the deceased can be adjusted according to the user's emotions.

[0066] The memory unit can learn the emotional memories of the deceased and recreate memories corresponding to the emotions. The memory unit, for example, analyzes information about the deceased while they were alive and learns the emotional memories of the deceased using an emotion estimation function. For example, to recreate the emotions the deceased felt in response to a specific event, the AI ​​learns changes in emotions and recreates memories corresponding to the emotions. The memory unit also learns the emotional memories of the deceased using the emotion estimation function in order to recreate the memories in more detail. For example, to recreate the emotions the deceased felt in response to a specific event, the AI ​​learns changes in emotions and recreates memories corresponding to the emotions. The memory unit also learns the emotional memories of the deceased using the emotion estimation function in order to recreate the memories in more detail. For example, to recreate the emotions the deceased felt in response to a specific event, the AI ​​learns changes in emotions and recreates memories corresponding to the emotions. In this way, the emotional memories of the deceased can be recreated.

[0067] The memory unit learns information from the deceased's lifetime and can recreate memories corresponding to different periods and events. For example, the memory unit collects information from the deceased's lifetime, and the AI ​​learns memories corresponding to different periods and events. For example, to recreate memories from when the deceased was young and memories from when they were old, the AI ​​learns and recreates information about the deceased. The memory unit also collects information from the deceased's lifetime and the AI ​​learns memories corresponding to different periods and events. For example, to recreate memories the deceased had in response to a particular event, the AI ​​learns and recreates information about the deceased. The memory unit also collects information from the deceased's lifetime and the AI ​​learns memories corresponding to different periods and events. For example, to recreate memories from when the deceased was young and memories from when they were old, the AI ​​learns and recreates information about the deceased. This makes it possible to recreate memories corresponding to different periods and events.

[0068] The memory unit can learn the perspective and emotions of the deceased and recreate memories that reflect those perspectives and emotions. For example, the memory unit analyzes information about the deceased while they were alive, and the AI ​​learns the perspective and emotions of the deceased. For example, to recreate the emotions and perspective the deceased felt toward a specific event, the AI ​​learns the perspective and emotions of the deceased and recreates them. The memory unit also learns the perspective and emotions of the deceased to generate memories that reflect those perspectives and emotions. For example, to recreate the emotions and perspective the deceased felt toward a specific event, the AI ​​learns the perspective and emotions of the deceased and recreates them. The memory unit also learns the perspective and emotions of the deceased to generate memories that reflect those perspectives and emotions. For example, to recreate the emotions and perspective the deceased felt toward a specific event, the AI ​​learns the perspective and emotions of the deceased and recreates them. This makes it possible to recreate memories that reflect the perspective and emotions of the deceased.

[0069] The memory unit learns the experiences of the deceased and is able to recreate the events they experienced. The memory unit, for example, collects information about the deceased when they were alive, and the AI ​​learns the experiences of the deceased. For example, the AI ​​learns and recreates the experiences of the deceased in order to recreate the feelings the deceased had in response to specific events. The memory unit also learns the experiences of the deceased in order to recreate the events they experienced. For example, the AI ​​learns and recreates the feelings the deceased had in response to specific events. The memory unit also learns the experiences of the deceased in order to recreate the events they experienced. For example, the AI ​​learns and recreates the feelings the deceased had in response to specific events. In this way, the events the deceased experienced can be recreated.

[0070] The memory unit learns multicultural information and can recreate memories from different cultures and backgrounds. For example, the memory unit collects information from the deceased's lifetime, and the AI ​​learns multicultural information. For example, to recreate events that the deceased experienced in different cultures and backgrounds, the AI ​​learns multicultural information. In addition, the memory unit learns multicultural information to recreate the deceased's memories. For example, to recreate events that the deceased experienced in different cultures and backgrounds, the AI ​​learns multicultural information to recreate the deceased's memories. In addition, the memory unit learns multicultural information to recreate the deceased's memories. For example, to recreate events that the deceased experienced in different cultures and backgrounds, the AI ​​learns multicultural information to recreate the deceased's memories. In this way, memories from different cultures and backgrounds can be recreated.

[0071] The memory unit can adjust the memory contents according to the user's emotions using an emotion estimation function. For example, the memory unit analyzes the user's emotions in real time, and the AI ​​adjusts the memory contents of the deceased. For example, when the user is sad, the memory contents of the deceased are adjusted to be comforting. The memory unit also analyzes the user's emotions in real time, and the AI ​​adjusts the memory contents of the deceased. For example, when the user is happy, the memory contents of the deceased are adjusted to be empathetic. The memory unit also analyzes the user's emotions in real time, and the AI ​​adjusts the memory contents of the deceased. For example, when the user is angry, the memory contents of the deceased are adjusted to be calm. In this way, the memory contents of the deceased can be adjusted according to the user's emotions.

[0072] The dialogue unit can use the emotion estimation function to analyze the user's emotions in real time and generate dialogue content that corresponds to the emotions. For example, the dialogue unit analyzes the user's emotions in real time, and the AI ​​generates dialogue content that corresponds to the emotions. For example, when the user is sad, it generates dialogue that comforts the user. The dialogue unit also analyzes the user's emotions in real time, and the AI ​​generates dialogue content that corresponds to the emotions. For example, when the user is happy, it generates dialogue that empathizes with the user. The dialogue unit also analyzes the user's emotions in real time, and the AI ​​generates dialogue content that corresponds to the user's emotions. For example, when the user is angry, it generates dialogue that calms the user. In this way, dialogue content that corresponds to the user's emotions can be generated.

[0073] The dialogue unit can learn the user's past dialogue history and understand the context of the dialogue. For example, the dialogue unit collects the user's past dialogue history, and the AI ​​learns the context of the dialogue. For example, it understands the flow of the dialogue based on what the user has said in the past and generates an appropriate response. The dialogue unit also collects the user's past dialogue history, and the AI ​​learns the context of the dialogue. For example, it understands the flow of the dialogue based on what the user has said in the past and generates an appropriate response. The dialogue unit also collects the user's past dialogue history, and the AI ​​learns the context of the dialogue. For example, it understands the flow of the dialogue based on what the user has said in the past and generates an appropriate response. In this way, the context of the dialogue can be understood based on the user's past dialogue history.

[0074] The dialogue unit can learn the user's situation information and generate dialogues that correspond to different situations and contexts. For example, the dialogue unit collects the user's situation information and the AI ​​generates dialogues that correspond to different situations and contexts. For example, the dialogue unit determines whether the user is at work or on vacation and generates dialogue content accordingly. The dialogue unit also collects the user's situation information and the AI ​​generates dialogues that correspond to different situations and contexts. For example, the dialogue unit determines whether the user is at home or out and generates dialogue content accordingly. The dialogue unit also collects the user's situation information and the AI ​​generates dialogues that correspond to different situations and contexts. For example, the dialogue unit determines whether the user is alone or with someone and generates dialogue content accordingly. This makes it possible to generate dialogues that correspond to different situations and contexts.

[0075] The dialogue unit learns the user's memories and can recreate memories spent with the deceased. For example, the dialogue unit collects memories the user spent with the deceased, and the AI ​​learns them. For example, to recreate memories of a trip the user took with the deceased, the AI ​​learns that information and recreates it. The dialogue unit also collects memories the user spent with the deceased, and the AI ​​learns them. For example, to recreate memories of a specific event the user spent with the deceased, the AI ​​learns that information and recreates it. The dialogue unit also collects memories the user spent with the deceased, and the AI ​​learns them. For example, to recreate everyday memories the user spent with the deceased, the AI ​​learns that information and recreates it. In this way, memories spent with the deceased can be recreated.

[0076] The dialogue unit learns multilingual dialogue data and can reproduce dialogues in different languages ​​and cultures. For example, the dialogue unit collects experiences of users conversing with the deceased in different languages ​​and cultures, and the AI ​​learns the data. For example, to reproduce the user's experience of conversing with the deceased in English or French, the AI ​​learns multilingual dialogue data and reproduces it. The dialogue unit also collects experiences of users conversing with the deceased in different languages ​​and cultures, and the AI ​​learns the data. For example, to reproduce the user's experience of conversing with the deceased in a Japanese dialect, the AI ​​learns multilingual dialogue data and reproduces it. The dialogue unit also collects experiences of users conversing with the deceased in different languages ​​and cultures, and the AI ​​learns the data. For example, to reproduce the user's experience of conversing with the deceased in English or French, the AI ​​learns multilingual dialogue data and reproduces it. This makes it possible to reproduce dialogues in different languages ​​and cultures.

[0077] The dialogue unit can use an emotion estimation function to adjust the dialogue content according to the user's emotions. For example, the dialogue unit analyzes the user's emotions in real time, and the AI ​​adjusts the dialogue content. For example, when the user is sad, it generates a dialogue with comforting content. The dialogue unit also analyzes the user's emotions in real time, and the AI ​​adjusts the dialogue content. For example, when the user is happy, it generates a dialogue with empathetic content. The dialogue unit also analyzes the user's emotions in real time, and the AI ​​adjusts the dialogue content. For example, when the user is angry, it generates a dialogue with calm content. This makes it possible to adjust the dialogue content according to the user's emotions.

[0078] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0079] The conversation system may further include a health management unit that monitors the user's health condition. For example, the health management unit may monitor the user's vital signs, such as heart rate, blood pressure, and body temperature, in real time, and issue an appropriate alert if an abnormality is detected. The health management unit may also provide appropriate advice and reminders based on the user's health condition. For example, if the user is feeling stressed, the health management unit may provide advice on how to relax. The health management unit may also record the user's health data over the long term and track changes in the user's health condition. This may support the user's health management.

[0080] The conversation system may further include a hobby providing unit that provides customized content based on the user's hobbies and interests. For example, the hobby providing unit may collect information about the user's favorite music, movies, books, etc., and provide recommended content based on that information. The hobby providing unit may also analyze the user's past preference data and make suggestions to help the user discover new hobbies and interests. For example, if the user likes movies of a particular genre, the hobby providing unit may recommend new movies of the same genre. The hobby providing unit may also provide information about events and activities related to the user's hobbies. This may help the user deepen their hobbies and interests.

[0081] The conversation system may further include a learning support unit that supports the user's learning. For example, the learning support unit may provide information on themes or fields the user wants to study and support the user in creating a study plan. The learning support unit may also track the user's learning progress and provide appropriate feedback. For example, when the user is working on a specific task, the learning support unit may provide advice and resources according to the user's progress. The learning support unit may also provide customized learning content that matches the user's learning style and pace. This may help improve the user's learning effectiveness.

[0082] The conversation system may further include a lifestyle management unit that supports the user's lifestyle. For example, the lifestyle management unit may manage the user's schedule and tasks and provide reminders. The lifestyle management unit may also track the user's sleep patterns and dietary records and provide advice on maintaining a healthy lifestyle. For example, if the user is not getting enough sleep, the lifestyle management unit may make suggestions for improving sleep. The lifestyle management unit may also provide customized reminders and notifications that are tailored to the user's lifestyle. This may help improve the user's quality of life.

[0083] The conversation system may further include an entertainment providing unit that estimates the user's emotions and provides music and videos based on the emotions. For example, the entertainment providing unit may analyze the user's emotions in real time and select music and videos that correspond to the emotions. For example, when the user is sad, relaxing music and moving videos may be provided. The entertainment providing unit may also analyze the user's emotions in real time and select music and videos that correspond to the emotions. For example, when the user is happy, cheerful and upbeat music and videos may be provided. The entertainment providing unit may also analyze the user's emotions in real time and select music and videos that correspond to the emotions. For example, when the user is angry, calming music and videos may be provided. In this way, entertainment that corresponds to the user's emotions may be provided.

[0084] The conversation system may further include a relaxation providing unit that estimates the user's emotions and provides a relaxation method based on the emotions. For example, the relaxation providing unit may analyze the user's emotions in real time and suggest a relaxation method according to the emotions. For example, when the user is feeling stressed, it may provide deep breathing or meditation techniques. The relaxation providing unit may also analyze the user's emotions in real time and suggest a relaxation method according to the emotions. For example, when the user is tired, it may provide relaxing music or aromatherapy techniques. The relaxation providing unit may also analyze the user's emotions in real time and suggest a relaxation method according to the emotions. For example, when the user is feeling anxious, it may provide relaxing stretching or yoga techniques. In this way, a relaxation method according to the user's emotions may be provided.

[0085] The conversation system may further include a meal suggestion unit that estimates the user's emotions and suggests meals based on the emotions. For example, the meal suggestion unit may analyze the user's emotions in real time and suggest a meal menu that corresponds to the emotions. For example, when the user is tired, it may suggest a nutritious meal. The meal suggestion unit may also analyze the user's emotions in real time and suggest a meal menu that corresponds to the emotions. For example, when the user is feeling stressed, it may suggest a meal that will help the user relax. The meal suggestion unit may also analyze the user's emotions in real time and suggest a meal menu that corresponds to the emotions. For example, when the user is happy, it may suggest a meal that will make the user feel happy. In this way, meal suggestions may be made that correspond to the user's emotions.

[0086] The conversation system may further include an exercise suggestion unit that estimates the user's emotions and suggests exercises based on the emotions. For example, the exercise suggestion unit may analyze the user's emotions in real time and suggest an exercise menu that corresponds to the emotions. For example, when the user is feeling stressed, it may suggest relaxing yoga or stretching. The exercise suggestion unit may also analyze the user's emotions in real time and suggest an exercise menu that corresponds to the emotions. For example, when the user is tired, it may suggest light walking or relaxing exercise. The exercise suggestion unit may also analyze the user's emotions in real time and suggest an exercise menu that corresponds to the emotions. For example, when the user is happy, it may suggest energetic exercise. In this way, exercises can be suggested that correspond to the user's emotions.

[0087] The conversation system may further include a travel suggestion unit that estimates the user's emotions and suggests travel plans based on the emotions. For example, the travel suggestion unit may analyze the user's emotions in real time and suggest travel plans that correspond to the emotions. For example, when the user is feeling stressed, the travel suggestion unit may suggest a relaxing hot spring trip. The travel suggestion unit may also analyze the user's emotions in real time and suggest travel plans that correspond to the emotions. For example, when the user is tired, the travel suggestion unit may suggest a trip to a place rich in nature where the user can refresh themselves. The travel suggestion unit may also analyze the user's emotions in real time and suggest travel plans that correspond to the emotions. For example, when the user is happy, the travel suggestion unit may suggest travel destinations with plenty of fun activities. In this way, travel suggestions may be made that correspond to the user's emotions.

[0088] The conversation system may further include a reading suggestion unit that estimates the user's emotions and suggests reading based on the emotions. For example, the reading suggestion unit may analyze the user's emotions in real time and suggest a reading menu that corresponds to the emotions. For example, when the user is feeling stressed, it may suggest relaxing novels or essays. The reading suggestion unit may also analyze the user's emotions in real time and suggest a reading menu that corresponds to the emotions. For example, when the user is tired, it may suggest light reading material or short stories. The reading suggestion unit may also analyze the user's emotions in real time and suggest a reading menu that corresponds to the emotions. For example, when the user is happy, it may suggest books that will make the user feel happy. In this way, reading suggestions may be made that correspond to the user's emotions.

[0089] The processing flow of the second embodiment will be briefly explained below.

[0090] Step 1: The voice generation unit reproduces the voice of the deceased. For example, the voice generation unit collects voice data from the deceased's lifetime, and the voice generation AI learns the deceased's voice based on that data. The voice generation unit can also analyze and reproduce the characteristics of the deceased's voice using audio or video messages recorded by the deceased during their lifetime. The voice generation unit also generates a voice response in the deceased's voice in response to user input. Step 2: The text generation unit generates the deceased's statements. For example, the text generation unit collects statements made by the deceased, as well as notes, diaries, and social media posts made by the deceased, and the text generation AI learns the characteristics of the deceased's statements based on these. The text generation unit can also analyze and reproduce the style and content of the deceased's statements using letters and blog posts written by the deceased. The text generation unit also generates the deceased's statements in response to questions from the user and the flow of the conversation. Step 3: The memory unit stores information about the deceased. For example, the memory unit collects information about the deceased while they were alive, and the AI ​​uses this information to construct a memory of the deceased. The memory unit can also collect information about the deceased, such as their hobbies and interests, and relationships with family and friends, and the AI ​​can store this information. The memory unit also uses the stored information to allow the AI ​​to converse as if they were the deceased. Step 4: The dialogue unit realizes a dialogue with the user. For example, the dialogue unit realizes a dialogue with the user by combining a voice generation AI and a sentence generation AI. In addition, when the user speaks to the deceased, the dialogue unit can have the voice generation AI respond in the deceased's voice, and the sentence generation AI generate the deceased's words. In addition, when the user asks, "Mom, how was your day?", the dialogue unit can have the AI ​​respond in the form of, "Today was a great day. How was it for you?"

[0091] 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.

[0092] 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.

[0093] 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.

[0094] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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).

[0100] 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.

[0101] 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.

[0102] 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.

[0103] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0104] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0110] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0119] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0125] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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."

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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]

[0158] 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 voice generator that reproduces the voice of the deceased; a sentence generation unit that generates statements made by the deceased; a storage unit for storing information about the deceased; A dialogue unit that realizes dialogue with a user. A system characterized by:

2. The voice generation unit Learns emotional changes and adjusts voice tone and pitch accordingly 2. The system of claim 1.

3. The voice generation unit Learns the subtle acoustic characteristics of the deceased's voice and reproduces the breathing and trembling of the voice 2. The system of claim 1.

4. The voice generation unit Learn from voice data from the deceased person's lifetime and generate a voice that matches their age and health condition 2. The system of claim 1.

5. The voice generation unit Learn and recreate the singing voice and recitation style of the deceased 2. The system of claim 1.

Images