System

Abstract

An object of a system according to an embodiment is to reproduce a conversation with a previous spouse and reduce loneliness of an elderly person.SOLUTION: A system according to an embodiment includes an information collection unit, a learning unit, a speech generation unit, and a voice reproduction unit. The information collection unit collects information on the preceding husband and wife. The learning unit learns the information collected by the information collection unit. The conversation generation unit generates conversation content on the basis of the information learned by the learning unit. The voice reproduction unit reproduces the conversation content generated by the speech generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has not been able to recreate conversations with a deceased spouse, and there has been a problem in that there are not enough means to alleviate the loneliness of elderly people.

[0005] The system according to the embodiment aims to reduce the sense of loneliness felt by elderly people by recreating conversations with their deceased spouses. [Means for solving the problem]

[0006] The system according to the embodiment includes an information collection unit, a learning unit, a conversation generation unit, and a voice reproduction unit. The information collection unit collects information about the deceased husband or wife. The learning unit learns the information collected by the information collection unit. The conversation generation unit generates conversation content based on the information learned by the learning unit. The voice reproduction unit reproduces the conversation content generated by the conversation generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can recreate conversations with a deceased spouse, thereby reducing the sense of loneliness felt by elderly people. [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 AI ​​partner system according to an embodiment of the present invention is a system that provides enrichment to daily life for the elderly, preventing them from feeling lonely. This system learns information about the deceased spouse and provides conversations that make it seem as if the user is talking to the deceased spouse. This allows the AI ​​partner system to provide enrichment to daily life for the elderly, preventing them from feeling lonely.

[0029] The AI ​​partner system according to the embodiment includes an information collection unit, a learning unit, a conversation generation unit, and a voice reproduction unit. The information collection unit collects information about the deceased husband or wife. For example, it uses materials such as diaries, letters, photos, and videos to gain a detailed understanding of the husband or wife's personality, speaking style, and preferences. The information collection unit can also analyze social media posts and comments to gain a detailed understanding of the husband or wife's personality and hobbies. The learning unit learns the information collected by the information collection unit. For example, it uses machine learning or deep learning to learn the husband or wife's personality, speaking style, and preferences. The conversation generation unit generates conversation content based on the information learned by the learning unit. For example, it uses a generation AI (e.g., GPT-3) to generate natural conversation based on the husband or wife's personality and speaking style. The conversation generation unit can also use an emotion estimation function to learn the husband or wife's emotional changes in real time and reflect those changes in the conversation. The voice reproduction unit reproduces the conversation content generated by the conversation generation unit. For example, speech synthesis technology can be used to analyze the tone and rhythm of a husband or wife's voice in detail to reproduce a more natural voice. Furthermore, the voice reproduction unit can also reproduce background and environmental sounds when reproducing voice information, providing a more realistic conversation experience. This allows the AI ​​partner system according to the embodiment to enrich daily life without causing elderly people to feel lonely. For example, they can enjoy reminiscing with their deceased spouse or enjoying conversations with family members who live far away. Furthermore, receiving psychological support can provide a sense of security in daily life.

[0030] The information collection unit can use materials such as diaries, letters, photographs, and videos to gain a detailed understanding of the personality, speaking style, and preferences of a husband or wife. The information collection unit, for example, uses materials such as diaries, letters, photographs, and videos to gain a detailed understanding of the personality, speaking style, and preferences of a husband or wife. For example, the information collection unit analyzes diaries to understand the husband or wife's daily actions and emotions; analyzes letters to understand the husband or wife's communication style and emotions; analyzes photos to understand the husband or wife's hobbies and interests; and analyzes videos to learn the husband or wife's speaking style and tone of voice. This allows a detailed understanding of the husband or wife's personality, speaking style, and preferences to provide a more natural conversation.

[0031] The learning unit can analyze social media posts or comments to gain a detailed understanding of the husband or wife's personality or hobbies. For example, the learning unit analyzes social media posts and comments to gain a detailed understanding of the husband or wife's personality and hobbies. For example, it analyzes posts on Facebook (registered trademark) and Twitter (registered trademark) to learn the husband or wife's interests. It analyzes photos and comments on Instagram (registered trademark) to gain an understanding of the husband or wife's preferences and lifestyle. It analyzes the husband or wife's personality and hobbies in detail based on social media posts and comments. For example, it analyzes what topics the husband or wife is interested in and reflects that information in conversations. In this way, by analyzing social media information, it is possible to gain a more detailed understanding of the husband or wife's personality and hobbies.

[0032] The information collection unit collects information about the husband's or wife's music and movie preferences, thereby broadening the scope of conversation. The information collection unit, for example, collects information about the husband's or wife's music and movie preferences, thereby broadening the scope of conversation. For example, it collects information about the husband's or wife's favorite music and movies, and incorporates that topic into the conversation. It collects information about entertainment to understand the husband's or wife's preferences. For example, it collects information about the husband's or wife's favorite artists and film directors, and reflects that topic in the conversation. It analyzes the husband's or wife's music and movie preferences in detail, thereby broadening the scope of conversation. For example, it analyzes the genres of music and movies that the husband or wife prefers, and develops the conversation based on that information. In this way, by collecting music and movie preferences, the scope of conversation can be broadened.

[0033] The conversation generation unit uses a generation AI to provide a virtual travel experience based on information about the husband or wife, allowing the user to feel as if they are traveling together. The conversation generation unit, for example, uses a generation AI to provide a virtual travel experience based on information about the husband or wife. For example, it collects information about travel destinations and tourist spots that the husband or wife liked, and virtually recreates those places. By providing a virtual travel experience, the user can feel as if they are traveling with the husband or wife. For example, it virtually recreates places that the husband or wife has visited or places that hold memories, and develops a conversation about those places. The generation AI provides a virtual travel experience based on information about the husband or wife. For example, it collects information about travel destinations and tourist spots that the husband or wife liked, virtually recreates those places, and reflects them in a conversation with the user. In this way, by providing a virtual travel experience, the user can feel as if they are traveling together.

[0034] The voice reproduction unit uses generation AI to analyze the tone and rhythm of the husband and wife's voices in detail, allowing for more natural reproduction of their voices. The voice reproduction unit, for example, uses generation AI to analyze the tone and rhythm of the husband and wife's voices in detail. For example, it learns the characteristics of the husband and wife's voices based on video and audio recordings and reproduces a natural voice. It analyzes the tone and rhythm of the voices in detail and reproduces the husband and wife's voices. For example, it analyzes the husband and wife's speaking style and intonation and then uses a voice that reproduces those characteristics to carry out a conversation. The generation AI learns the tone and rhythm of the husband and wife's voices and reproduces a natural voice. For example, it analyzes the characteristics of the husband and wife's voices based on video messages and telephone recordings and then uses that voice to carry out a conversation. In this way, by analyzing the tone and rhythm of the voices in detail, it is possible to reproduce a more natural voice.

[0035] The voice reproduction unit reproduces background sounds and environmental sounds when reproducing voice information, thereby providing a more realistic conversation experience. The voice reproduction unit, for example, reproduces background sounds and environmental sounds when reproducing voice information. For example, the background sounds of the place where the husband or wife was talking may be reproduced to provide a more realistic conversation experience. The generation AI learns background sounds and environmental sounds and reflects them in the reproduction of the voice information. For example, the sounds of the place where the husband or wife was talking may be reproduced, and the conversation may take place with that sound as the background. When reproducing voice information, the background sounds and environmental sounds are analyzed in detail to provide a realistic conversation experience. For example, the sounds of the place where the husband or wife was talking may be reproduced, and the conversation may take place with that sound as the background. In this way, by reproducing background sounds and environmental sounds, a more realistic conversation experience may be provided.

[0036] The voice reproduction unit can accommodate different languages ​​and dialects when reproducing voice information, enabling multilingual conversations. The voice reproduction unit can accommodate different languages ​​and dialects when reproducing voice information, for example. For example, it can learn the language and dialect spoken by a husband or wife and converse in that language or dialect. The generation AI can learn different languages ​​and dialects, enabling multilingual conversations. For example, it can reproduce the language and dialect spoken by a husband or wife and converse in that language or dialect. When reproducing voice information, different languages ​​and dialects can be analyzed in detail to provide multilingual conversations. For example, it can learn the language and dialect spoken by a husband or wife and converse in that language or dialect. This allows for support for different languages ​​and dialects, enabling multilingual conversations.

[0037] The voice reproduction unit uses the generation AI to provide recitations of songs and poems based on the voices of the husband or wife, thereby adding content that the user can enjoy. The voice reproduction unit, for example, uses the generation AI to provide recitations of songs and poems based on the voices of the husband or wife. For example, songs and poems that the husband or wife liked are reproduced and recited in that voice. In reproducing the voice information, recitations of songs and poems based on the voices of the husband or wife are added. For example, songs and poems that the husband or wife often sang are reproduced and recited in that voice. The generation AI provides recitations of songs and poems based on the voices of the husband or wife. For example, songs and poems that the husband or wife liked are reproduced and recited in that voice. In this way, content that the user can enjoy can be added by providing recitations of songs and poems.

[0038] The information collection unit can take into account family life events or anniversaries and reflect them in conversations. The information collection unit, for example, collects family life events and anniversaries and reflects them in conversations. For example, it collects information such as family birthdays and wedding anniversaries and incorporates that topic into the conversation. It analyzes family life events and anniversaries in detail and reflects them in the conversation. For example, it collects information about important events and anniversaries experienced by the family and incorporates that topic into the conversation. The generation AI learns family life events and anniversaries and reflects them in the conversation. For example, it collects information such as family birthdays and wedding anniversaries and incorporates that topic into the conversation. This allows for more intimate conversations by taking family life events and anniversaries into consideration.

[0039] The information gathering unit can collect information about family members' hobbies and interests, thereby broadening the scope of conversation. The information gathering unit, for example, collects information about family members' hobbies and interests, thereby broadening the scope of conversation. For example, it collects information about family members' favorite sports and hobbies, and incorporates that topic into the conversation. It analyzes family members' hobbies and interests in detail, thereby broadening the scope of conversation. For example, it analyzes what hobbies and interests family members have, and develops the conversation based on that information. The generation AI learns family members' hobbies and interests, thereby broadening the scope of conversation. For example, it collects information about family members' favorite activities and areas of interest, and incorporates that topic into the conversation. In this way, by collecting information about family members' hobbies and interests, it is possible to broaden the scope of conversation.

[0040] The conversation generation unit uses the generation AI to provide a virtual family event based on family information, allowing the user to feel as if they are enjoying the event together. The conversation generation unit, for example, uses the generation AI to provide a virtual family event based on family information. For example, it collects information about events and occasions that the family liked and virtually recreates those events. By providing a virtual family event, the user can feel as if they are enjoying an event with their family. For example, it virtually recreates events and occasions that the family has participated in and develops a conversation about those events. The generation AI provides a virtual family event based on family information. For example, it collects information about events and occasions that the family liked, virtually recreates those events, and reflects them in a conversation with the user. In this way, by providing a virtual family event, the user can feel as if they are enjoying an event together.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The AI ​​Partner System can further include a health management unit. The health management unit monitors the user's health status and provides appropriate advice. For example, it can collect the user's diet and exercise records and provide advice to promote healthy lifestyle habits. It can also send reminders for regular health checks and provide support for the user to maintain their health. Furthermore, the health management unit can analyze the user's medical data and connect with medical institutions as necessary. This allows the user's health status to be managed comprehensively, allowing them to live a more secure life.

[0043] The AI ​​Partner System can further include a hobby suggestion unit. The hobby suggestion unit suggests new hobbies and activities based on the user's interests and past activity history. For example, it can analyze the hobbies and interests that the user has enjoyed in the past and suggest new activities related to them. It can also provide information on local events and workshops to help the user find a new hobby. Furthermore, the hobby suggestion unit can find common hobbies with the user's friends and family and make suggestions for activities to enjoy together. This allows the user to find a new hobby and add new enjoyment to their daily life.

[0044] The AI ​​Partner System can further include a pet care unit. The pet care unit supports the user's pet's health and daily care. For example, it collects records of the pet's diet and exercise and suggests appropriate care methods. The pet care unit can also send reminders for pet health checks and support the user in maintaining the pet's health. Furthermore, the pet care unit can analyze the pet's behavior and emotions and provide advice to reduce the pet's stress. This allows the user to maintain the health and happiness of their pet and build a better relationship with it.

[0045] The AI ​​Partner System can further include a cooking support unit. The cooking support unit proposes recipes that take into account the user's preferences and nutritional balance. For example, it can collect information on the user's favorite ingredients and dishes and propose new recipes based on that information. The cooking support unit can also provide nutritionally balanced recipes that match the user's health condition and diet goals. Furthermore, the cooking support unit can also propose simple recipes and cooking methods that match the user's cooking skills and time. This allows users to enjoy cooking while maintaining a healthy diet.

[0046] The processing flow of the first embodiment will be briefly explained below.

[0047] Step 1: The information gathering department collects information about the deceased spouse. For example, they use diaries, letters, photos, videos, and other materials to gain a detailed understanding of the spouse's personality, speech patterns, and preferences. They can also analyze social media posts and comments to gain a detailed understanding of the spouse's personality and hobbies. Step 2: The learning unit learns the information collected by the information gathering unit. For example, it uses machine learning and deep learning to learn about the husband or wife's personality, speaking style, preferences, etc. Step 3: The conversation generation unit generates conversation content based on the information learned by the learning unit. For example, a generation AI (e.g., GPT-3) can be used to generate natural conversation based on the husband or wife's personality and speaking style. It can also use an emotion estimation function to learn the husband or wife's emotional changes in real time and reflect those changes in the conversation. Step 4: The voice reproduction unit reproduces the conversation generated by the conversation generation unit. For example, it uses voice synthesis technology to analyze the tone and rhythm of the husband and wife's voices in detail to reproduce more natural voices. It can also reproduce background and environmental sounds to provide a more realistic conversation experience.

[0048] (Example 2) The AI ​​partner system according to an embodiment of the present invention is a system that provides enrichment to daily life for the elderly, preventing them from feeling lonely. This system learns information about the deceased spouse and provides conversations that make it seem as if the user is talking to the deceased spouse. This allows the AI ​​partner system to provide enrichment to daily life for the elderly, preventing them from feeling lonely.

[0049] The AI ​​partner system according to the embodiment includes an information collection unit, a learning unit, a conversation generation unit, and a voice reproduction unit. The information collection unit collects information about the deceased husband or wife. For example, it uses materials such as diaries, letters, photos, and videos to gain a detailed understanding of the husband or wife's personality, speaking style, and preferences. The information collection unit can also analyze social media posts and comments to gain a detailed understanding of the husband or wife's personality and hobbies. The learning unit learns the information collected by the information collection unit. For example, it uses machine learning or deep learning to learn the husband or wife's personality, speaking style, and preferences. The conversation generation unit generates conversation content based on the information learned by the learning unit. For example, it uses a generation AI (e.g., GPT-3) to generate natural conversation based on the husband or wife's personality and speaking style. The conversation generation unit can also use an emotion estimation function to learn the husband or wife's emotional changes in real time and reflect those changes in the conversation. The voice reproduction unit reproduces the conversation content generated by the conversation generation unit. For example, speech synthesis technology can be used to analyze the tone and rhythm of a husband or wife's voice in detail to reproduce a more natural voice. Furthermore, the voice reproduction unit can also reproduce background and environmental sounds when reproducing voice information, providing a more realistic conversation experience. This allows the AI ​​partner system according to the embodiment to enrich daily life without causing elderly people to feel lonely. For example, they can enjoy reminiscing with their deceased spouse or enjoying conversations with family members who live far away. Furthermore, receiving psychological support can provide a sense of security in daily life.

[0050] The information collection unit can use materials such as diaries, letters, photographs, and videos to gain a detailed understanding of the personality, speaking style, and preferences of a husband or wife. The information collection unit, for example, uses materials such as diaries, letters, photographs, and videos to gain a detailed understanding of the personality, speaking style, and preferences of a husband or wife. For example, the information collection unit analyzes diaries to understand the husband or wife's daily actions and emotions; analyzes letters to understand the husband or wife's communication style and emotions; analyzes photos to understand the husband or wife's hobbies and interests; and analyzes videos to learn the husband or wife's speaking style and tone of voice. This allows a detailed understanding of the husband or wife's personality, speaking style, and preferences to provide a more natural conversation.

[0051] The learning unit can analyze social media posts or comments to gain a detailed understanding of the husband or wife's personality or hobbies. For example, the learning unit analyzes social media posts and comments to gain a detailed understanding of the husband or wife's personality and hobbies. For example, it analyzes posts on Facebook (registered trademark) and Twitter (registered trademark) to learn the husband or wife's interests. It analyzes photos and comments on Instagram (registered trademark) to gain an understanding of the husband or wife's preferences and lifestyle. It analyzes the husband or wife's personality and hobbies in detail based on social media posts and comments. For example, it analyzes what topics the husband or wife is interested in and reflects that information in conversations. In this way, by analyzing social media information, it is possible to gain a more detailed understanding of the husband or wife's personality and hobbies.

[0052] The conversation generation unit can use the emotion estimation function to learn the emotional changes of the husband or wife in real time and reflect those changes in the conversation. The conversation generation unit, for example, uses the emotion estimation function to learn the emotional changes of the husband or wife in real time. For example, it analyzes how the husband or wife's emotions change during the conversation and responds by reflecting those changes. The generation AI uses the emotion estimation function to learn the emotional changes of the husband or wife and reflects those changes in the conversation. For example, it predicts how the husband or wife will feel about a particular topic and advances the conversation based on that emotion. The emotion estimation function can be used to analyze the emotional changes of the husband or wife in real time and provide a conversation that reflects those changes. For example, it can recreate scenes in which the husband or wife feels joy or sadness and reflect those changes in the conversation with the user. In this way, by learning emotional changes in real time and reflecting them in the conversation, it is possible to provide a more natural conversation.

[0053] The information collection unit collects information about the husband's or wife's music and movie preferences, thereby broadening the scope of conversation. The information collection unit, for example, collects information about the husband's or wife's music and movie preferences, thereby broadening the scope of conversation. For example, it collects information about the husband's or wife's favorite music and movies, and incorporates that topic into the conversation. It collects information about entertainment to understand the husband's or wife's preferences. For example, it collects information about the husband's or wife's favorite artists and film directors, and reflects that topic in the conversation. It analyzes the husband's or wife's music and movie preferences in detail, thereby broadening the scope of conversation. For example, it analyzes the genres of music and movies that the husband or wife prefers, and develops the conversation based on that information. In this way, by collecting music and movie preferences, the scope of conversation can be broadened.

[0054] The conversation generation unit uses a generation AI to provide a virtual travel experience based on information about the husband or wife, allowing the user to feel as if they are traveling together. The conversation generation unit, for example, uses a generation AI to provide a virtual travel experience based on information about the husband or wife. For example, it collects information about travel destinations and tourist spots that the husband or wife liked, and virtually recreates those places. By providing a virtual travel experience, the user can feel as if they are traveling with the husband or wife. For example, it virtually recreates places that the husband or wife has visited or places that hold memories, and develops a conversation about those places. The generation AI provides a virtual travel experience based on information about the husband or wife. For example, it collects information about travel destinations and tourist spots that the husband or wife liked, virtually recreates those places, and reflects them in a conversation with the user. In this way, by providing a virtual travel experience, the user can feel as if they are traveling together.

[0055] The conversation generation unit can use the emotion estimation function to predict what emotions a user will have about a specific topic and provide topics that correspond to those emotions. The conversation generation unit, for example, uses the emotion estimation function to predict what emotions a user will have about a specific topic. For example, it predicts topics that will make the user feel happy or sad and provides topics that correspond to those emotions. The generation AI uses the emotion estimation function to predict the user's emotions and provide topics that correspond to those emotions. For example, it predicts what emotions a user will have about a specific topic and advances the conversation based on those emotions. The emotion estimation function is used to analyze the user's emotions in real time and provide topics that correspond to those emotions. For example, it predicts topics that will make the user feel happy or sad and develops a conversation that corresponds to those emotions. In this way, more natural conversations can be provided by providing topics that correspond to the user's emotions.

[0056] The voice reproduction unit uses generation AI to analyze the tone and rhythm of the husband and wife's voices in detail, allowing for more natural reproduction of their voices. The voice reproduction unit, for example, uses generation AI to analyze the tone and rhythm of the husband and wife's voices in detail. For example, it learns the characteristics of the husband and wife's voices based on video and audio recordings and reproduces a natural voice. It analyzes the tone and rhythm of the voices in detail and reproduces the husband and wife's voices. For example, it analyzes the husband and wife's speaking style and intonation and then uses a voice that reproduces those characteristics to carry out a conversation. The generation AI learns the tone and rhythm of the husband and wife's voices and reproduces a natural voice. For example, it analyzes the characteristics of the husband and wife's voices based on video messages and telephone recordings and then uses that voice to carry out a conversation. In this way, by analyzing the tone and rhythm of the voices in detail, it is possible to reproduce a more natural voice.

[0057] The voice reproduction unit reproduces background sounds and environmental sounds when reproducing voice information, thereby providing a more realistic conversation experience. The voice reproduction unit, for example, reproduces background sounds and environmental sounds when reproducing voice information. For example, the background sounds of the place where the husband or wife was talking may be reproduced to provide a more realistic conversation experience. The generation AI learns background sounds and environmental sounds and reflects them in the reproduction of the voice information. For example, the sounds of the place where the husband or wife was talking may be reproduced, and the conversation may take place with that sound as the background. When reproducing voice information, the background sounds and environmental sounds are analyzed in detail to provide a realistic conversation experience. For example, the sounds of the place where the husband or wife was talking may be reproduced, and the conversation may take place with that sound as the background. In this way, by reproducing background sounds and environmental sounds, a more realistic conversation experience may be provided.

[0058] The voice reproduction unit can use the emotion estimation function to adjust the tone and volume of the voice according to the user's emotions during a conversation. For example, the voice reproduction unit uses the emotion estimation function to adjust the tone and volume of the voice according to the user's emotions during a conversation. For example, if the user is happy, it speaks in a bright tone, and if the user is sad, it speaks in a gentle tone. The generation AI uses the emotion estimation function to analyze the user's emotions and adjust the tone and volume of the voice according to those emotions. For example, if the user is angry, it speaks in a calm tone, and if the user is having fun, it speaks in a lively tone. The emotion estimation function is used to adjust the tone and volume of the voice according to the user's emotions in real time. For example, if the user is feeling anxious, it speaks in a reassuring tone, and if the user is excited, it speaks in a gentle tone. In this way, by adjusting the tone and volume of the voice according to the user's emotions, more natural conversations can be provided.

[0059] The voice reproduction unit can accommodate different languages ​​and dialects when reproducing voice information, enabling multilingual conversations. The voice reproduction unit can accommodate different languages ​​and dialects when reproducing voice information, for example. For example, it can learn the language and dialect spoken by a husband or wife and converse in that language or dialect. The generation AI can learn different languages ​​and dialects, enabling multilingual conversations. For example, it can reproduce the language and dialect spoken by a husband or wife and converse in that language or dialect. When reproducing voice information, different languages ​​and dialects can be analyzed in detail to provide multilingual conversations. For example, it can learn the language and dialect spoken by a husband or wife and converse in that language or dialect. This allows for support for different languages ​​and dialects, enabling multilingual conversations.

[0060] The voice reproduction unit uses the generation AI to provide recitations of songs and poems based on the voices of the husband or wife, thereby adding content that the user can enjoy. The voice reproduction unit, for example, uses the generation AI to provide recitations of songs and poems based on the voices of the husband or wife. For example, songs and poems that the husband or wife liked are reproduced and recited in that voice. In reproducing the voice information, recitations of songs and poems based on the voices of the husband or wife are added. For example, songs and poems that the husband or wife often sang are reproduced and recited in that voice. The generation AI provides recitations of songs and poems based on the voices of the husband or wife. For example, songs and poems that the husband or wife liked are reproduced and recited in that voice. In this way, content that the user can enjoy can be added by providing recitations of songs and poems.

[0061] The voice reproduction unit can use the emotion estimation function to predict what emotion a user will feel in response to a specific voice tone or rhythm, and adjust the voice according to that emotion. For example, the voice reproduction unit can use the emotion estimation function to predict what emotion a user will feel in response to a specific voice tone or rhythm. For example, it can predict a tone or rhythm that will calm the user and use that voice to carry out the conversation. The generation AI can use the emotion estimation function to predict the user's emotion and adjust the voice tone or rhythm according to that emotion. For example, it can predict a tone or rhythm that will make the user feel at ease and use that voice to carry out the conversation. The emotion estimation function can be used to analyze the user's emotion in real time and adjust the voice tone or rhythm according to that emotion. For example, it can predict a tone or rhythm that will relax the user and use that voice to carry out the conversation. This allows for more natural conversation by adjusting the voice tone or rhythm according to the user's emotion.

[0062] The information collection unit can take into account family life events or anniversaries and reflect them in conversations. The information collection unit, for example, collects family life events and anniversaries and reflects them in conversations. For example, it collects information such as family birthdays and wedding anniversaries and incorporates that topic into the conversation. It analyzes family life events and anniversaries in detail and reflects them in the conversation. For example, it collects information about important events and anniversaries experienced by the family and incorporates that topic into the conversation. The generation AI learns family life events and anniversaries and reflects them in the conversation. For example, it collects information such as family birthdays and wedding anniversaries and incorporates that topic into the conversation. This allows for more intimate conversations by taking family life events and anniversaries into consideration.

[0063] The conversation generation unit can use the emotion estimation function to learn the emotional changes of family members in real time and reflect those changes in the conversation. The conversation generation unit, for example, uses the emotion estimation function to learn the emotional changes of family members in real time. For example, it analyzes how the family members' emotions change during the conversation and responds by reflecting those changes. The generation AI uses the emotion estimation function to learn the emotional changes of family members and reflect those changes in the conversation. For example, it predicts how family members will feel about a particular topic and advances the conversation based on those emotions. The emotion estimation function can be used to analyze the emotional changes of family members in real time and provide a conversation that reflects those changes. For example, it can recreate scenes in which family members feel joy or sadness and reflect those changes in the conversation with the user. In this way, the system can learn the emotional changes of family members in real time and reflect them in the conversation, thereby providing a more natural conversation.

[0064] The information gathering unit can collect information about family members' hobbies and interests, thereby broadening the scope of conversation. The information gathering unit, for example, collects information about family members' hobbies and interests, thereby broadening the scope of conversation. For example, it collects information about family members' favorite sports and hobbies, and incorporates that topic into the conversation. It analyzes family members' hobbies and interests in detail, thereby broadening the scope of conversation. For example, it analyzes what hobbies and interests family members have, and develops the conversation based on that information. The generation AI learns family members' hobbies and interests, thereby broadening the scope of conversation. For example, it collects information about family members' favorite activities and areas of interest, and incorporates that topic into the conversation. In this way, by collecting information about family members' hobbies and interests, it is possible to broaden the scope of conversation.

[0065] The conversation generation unit uses the generation AI to provide a virtual family event based on family information, allowing the user to feel as if they are enjoying the event together. The conversation generation unit, for example, uses the generation AI to provide a virtual family event based on family information. For example, it collects information about events and occasions that the family liked and virtually recreates those events. By providing a virtual family event, the user can feel as if they are enjoying an event with their family. For example, it virtually recreates events and occasions that the family has participated in and develops a conversation about those events. The generation AI provides a virtual family event based on family information. For example, it collects information about events and occasions that the family liked, virtually recreates those events, and reflects them in a conversation with the user. In this way, by providing a virtual family event, the user can feel as if they are enjoying an event together.

[0066] The conversation generation unit can use the emotion estimation function to predict what emotions the user will feel about a specific family topic and provide topics that correspond to those emotions. The conversation generation unit, for example, uses the emotion estimation function to predict what emotions the user will feel about a specific family topic. For example, it predicts family topics that will make the user feel happy or sad and provides topics that correspond to those emotions. The generation AI uses the emotion estimation function to predict the user's emotions and provides family topics that correspond to those emotions. For example, it predicts what emotions the user will feel about a specific family topic and advances the conversation based on those emotions. The emotion estimation function is used to analyze the user's emotions in real time and provide family topics that correspond to those emotions. For example, it predicts family topics that will make the user feel happy or sad and develops a conversation that corresponds to those emotions. In this way, family topics that correspond to the user's emotions can be provided, thereby providing a more natural conversation.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The AI ​​Partner System can further include a health management unit. The health management unit monitors the user's health status and provides appropriate advice. For example, it can collect the user's diet and exercise records and provide advice to promote healthy lifestyle habits. It can also send reminders for regular health checks and provide support for the user to maintain their health. Furthermore, the health management unit can analyze the user's medical data and connect with medical institutions as necessary. This allows the user's health status to be managed comprehensively, allowing them to live a more secure life.

[0069] The AI ​​Partner System can further include a hobby suggestion unit. The hobby suggestion unit suggests new hobbies and activities based on the user's interests and past activity history. For example, it can analyze the hobbies and interests that the user has enjoyed in the past and suggest new activities related to them. It can also provide information on local events and workshops to help the user find a new hobby. Furthermore, the hobby suggestion unit can find common hobbies with the user's friends and family and make suggestions for activities to enjoy together. This allows the user to find a new hobby and add new enjoyment to their daily life.

[0070] The AI ​​partner system can further include a news provider. The news provider provides the latest news and topics based on the user's interests. For example, it can collect news in areas of interest to the user and provide that information in daily conversations. The news provider can also estimate the user's emotions and select news based on those emotions. For example, it can provide light-hearted news when the user is relaxed and more in-depth news when the user is concentrating. This allows the user to enjoy conversations with interest while obtaining the latest information.

[0071] The AI ​​Partner System can further include a reminder module. The reminder module manages the user's schedule and important tasks and sends reminders at appropriate times. For example, it collects the user's plans and tasks and sets reminders to help them remember. The reminder module can also estimate the user's emotions and adjust the content and timing of reminders according to their emotions. For example, it can provide advice on how to relax when the user is feeling stressed, and send reminders for important tasks when the user is concentrating. This allows the user to efficiently manage their schedule and smoothly progress through their daily life.

[0072] The AI ​​partner system can further include an entertainment provider. The entertainment provider recommends entertainment content such as movies, music, and books based on the user's preferences. For example, it can analyze data on movies and music the user has enjoyed in the past and recommend new content based on that. The entertainment provider can also estimate the user's emotions and select content that matches those emotions. For example, it can recommend relaxing music when the user wants to relax, and an energetic movie when the user wants to cheer up. This allows the user to enjoy entertainment that matches their mood at the time.

[0073] The AI ​​Partner System may further include a learning support unit. The learning support unit supports the user in acquiring new knowledge and skills. For example, it may provide learning resources in areas of interest to the user and manage the user's learning progress. The learning support unit may also propose a customized learning plan based on the user's learning style and pace. Furthermore, the learning support unit may estimate the user's emotions and provide advice to maintain motivation for learning. For example, if the user feels stressed about learning, it may provide advice on how to relax, or if the user is concentrating, it may provide support to continue learning. This allows the user to efficiently progress through learning and acquire new knowledge and skills.

[0074] The AI ​​Partner System can further include a travel planning unit. The travel planning unit suggests the next travel destination based on the user's preferences and past travel history. For example, it can analyze information about places the user has visited in the past and favorite tourist spots and suggest new travel destinations based on that information. The travel planning unit can also create travel plans based on the user's budget and schedule. Furthermore, the travel planning unit can estimate the user's emotions and suggest travel destinations and activities based on those emotions. For example, it can suggest resort destinations when the user wants to relax, and suggest active travel destinations when the user is seeking adventure. This allows the user to plan their next trip while looking forward to it.

[0075] The AI ​​Partner System can further include a pet care unit. The pet care unit supports the user's pet's health and daily care. For example, it collects records of the pet's diet and exercise and suggests appropriate care methods. The pet care unit can also send reminders for pet health checks and support the user in maintaining the pet's health. Furthermore, the pet care unit can analyze the pet's behavior and emotions and provide advice to reduce the pet's stress. This allows the user to maintain the health and happiness of their pet and build a better relationship with it.

[0076] The AI ​​Partner System can further include a cooking support unit. The cooking support unit proposes recipes that take into account the user's preferences and nutritional balance. For example, it can collect information on the user's favorite ingredients and dishes and propose new recipes based on that information. The cooking support unit can also provide nutritionally balanced recipes that match the user's health condition and diet goals. Furthermore, the cooking support unit can also propose simple recipes and cooking methods that match the user's cooking skills and time. This allows users to enjoy cooking while maintaining a healthy diet.

[0077] The AI ​​partner system can further include a gardening support unit. The gardening support unit supports the user in managing their garden and plants. For example, it can collect information about the plants the user is growing and suggest appropriate care methods. The gardening support unit can also provide gardening advice according to the season and weather. Furthermore, the gardening support unit can estimate the user's emotions and provide advice to promote relaxation and stress relief through gardening. This allows the user to enjoy gardening while maintaining the health of their plants and spending relaxing time.

[0078] The processing flow of the second embodiment will be briefly explained below.

[0079] Step 1: The information gathering department collects information about the deceased spouse. For example, they use diaries, letters, photos, videos, and other materials to gain a detailed understanding of the spouse's personality, speech patterns, and preferences. They can also analyze social media posts and comments to gain a detailed understanding of the spouse's personality and hobbies. Step 2: The learning unit learns the information collected by the information gathering unit. For example, it uses machine learning and deep learning to learn about the husband or wife's personality, speaking style, preferences, etc. Step 3: The conversation generation unit generates conversation content based on the information learned by the learning unit. For example, a generation AI (e.g., GPT-3) can be used to generate natural conversation based on the husband or wife's personality and speaking style. It can also use an emotion estimation function to learn the husband or wife's emotional changes in real time and reflect those changes in the conversation. Step 4: The voice reproduction unit reproduces the conversation generated by the conversation generation unit. For example, it uses voice synthesis technology to analyze the tone and rhythm of the husband and wife's voices in detail to reproduce more natural voices. It can also reproduce background and environmental sounds to provide a more realistic conversation experience.

[0080] 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.

[0081] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0082] 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.

[0083] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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).

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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 AI 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.

[0097] 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.

[0098] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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 AI 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.

[0112] 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.

[0113] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0114] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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.

[0126] 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.

[0127] 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 AI 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0134] 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."

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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]

[0147] 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. An information gathering department that collects information on deceased husbands and wives, a learning unit that learns the information collected by the information collecting unit; a conversation generation unit that generates conversation content based on the information learned by the learning unit; a voice reproducing unit that reproduces the conversation content generated by the conversation generating unit. A system characterized by:

2. The information collecting unit Using diaries, letters, photographs, and videotapes, gain a detailed understanding of the husband or wife's personality, speech patterns, and preferences 2. The system of claim 1.

3. The learning unit Analyzing social media posts or comments to understand the personality or hobbies of the husband or wife in detail 2. The system of claim 1.

4. The conversation generation unit Learns the emotional changes of the husband or wife in real time and reflects those changes in the conversation 2. The system of claim 1.

5. The information collecting unit Gathering information about the husband's or wife's music and movie preferences to broaden the scope of conversation 2. The system of claim 1.

6. The conversation generation unit Using the generative AI, a virtual travel experience based on the husband or wife's information is provided, allowing the user to feel as if they are traveling together.

2. The system of claim 1.

7. The conversation generation unit Predict how a user feels about a particular topic and provide topics that correspond to those feelings.

2. The system of claim 1.

8. The voice reproduction unit The generation AI is used to analyze in detail the tone and rhythm of the husband's or wife's voice, reproducing a more natural voice.

2. The system of claim 1.

Images