System

Abstract

An object of the system according to the embodiment is to store the information of the deceased so that the remaining relatives can have a pseudo conversation with the deceased.SOLUTION: A system includes a stock part, a designation part, a generation part, and an interaction part. The stock unit stocks information. The designation part designates an expression method of the information stocked by the stock part. The generation part generates the AI robot on the basis of the expression method designated by the designation part. The dialogue unit performs a dialogue using the AI robot generated by the 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 technologies do not adequately provide a means for effectively storing information about the deceased and for surviving relatives to virtually communicate with the deceased, and there is room for improvement.

[0005] The system according to the embodiment aims to store information about the deceased and enable surviving relatives to virtually interact with the deceased. [Means for solving the problem]

[0006] The system according to the embodiment includes a storage unit, a designation unit, a generation unit, and a dialogue unit. The storage unit stores information. The designation unit designates a representation method for the information stored by the storage unit. The generation unit generates an AI robot based on the representation method designated by the designation unit. The dialogue unit conducts dialogue using the AI ​​robot generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can store information about the deceased and allow surviving relatives to virtually interact with the deceased. [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) An information storage system according to an embodiment of the present invention executes information stored by a user in advance using a specified expression method, allowing for simulated interactive communication with the deceased. The information storage system allows users to store information such as photos, videos, favorite TV programs, books, magazines, movies, hobbies, favorite things, favorite words, letters, diaries, maternal and child health handbooks, medicine records, children's artwork, words of gratitude, and secret stories. The system then generates an AI robot based on the specified expression method and engages in dialogue. For example, the information storage system allows users to store memorable photos and videos of family memories and create lists of favorite movies and books. It is also possible to digitize and store letters and diaries. Next, the information storage system allows users to specify the expression method for the stored information. For example, when playing audio only, the user's voice can be recorded. When playing text only, letters and diaries written by the user are saved as text data. When playing with background music, the user's favorite music can be played in the background. Furthermore, the information storage system can use AI to generate a user's appearance and voice, making them resemble the user. Finally, the information storage system allows surviving relatives to engage in simulated interactive communication with the deceased. For example, through a conversational AI robot, users can converse with a robot that replicates the voice and appearance of the deceased. It is also possible to have a text chat while reading letters and diaries written by the deceased. This allows the information storage system to preserve the user's memories and messages, and surviving relatives can find peace of mind through conversations with the deceased. This allows the information storage system to preserve the user's memories and messages, and surviving relatives can find peace of mind through conversations with the deceased. For example, by having the AI ​​robot talk about a user's favorite movie, family members can share the deceased's hobbies and preferences and feel a connection with the deceased. It is also possible to receive memories and words of gratitude from the deceased through letters and diaries.

[0029] An information storage system according to an embodiment includes a storage unit, a designation unit, a generation unit, and a dialogue unit. The storage unit stores information such as photos, videos, favorite TV programs, books, magazines, movies, hobbies, favorite things, favorite words, letters, diaries, maternal and child health handbooks, medicine handbooks, children's artwork, words of gratitude, and insider stories. For example, the storage unit has a function that allows the user to upload photos and videos of family memories. The storage unit can also digitize and store letters and diaries. The designation unit specifies how to express the information stored by the storage unit. For example, the designation unit can record the user's voice when playing audio only. When playing text only, the designation unit saves letters and diaries written by the user as text data. When playing with background music, the user's favorite music can be played in the background. The generation unit generates an AI robot based on the expression method specified by the designation unit. For example, the generation unit can generate the user's appearance and voice using AI to resemble the user. The generation unit can generate the user's appearance and voice using text generation AI (e.g., LLM) or multimodal generation AI. The dialogue unit engages in dialogue using the AI ​​robot generated by the generation unit. For example, the dialogue unit can converse with an AI robot that reproduces the voice and appearance of the deceased in a conversational format. The dialogue unit can also converse in a text chat format while reading letters or diaries written by the deceased. In this way, the information storage system according to the embodiment allows the user's memories and messages to be preserved, and surviving relatives can find peace of mind through dialogue with the deceased.

[0030] The stock unit may have a function that allows users to upload images and videos. Examples of image and video formats include, but are not limited to, JPEG, PNG, and MP4. The stock unit may have a function that allows users to upload images and videos from their own devices. For example, the stock unit may upload images and videos directly from a smartphone or PC. The stock unit may also store images and videos using cloud storage. For example, the stock unit may link with a cloud storage service to securely store images and videos uploaded by users. This allows users to easily store photos and videos. Some or all of the above-described processing in the stock unit may be performed using, or without, AI. For example, the stock unit may input images and videos uploaded by users into AI and have the AI ​​classify and tag the images and videos.

[0031] The designation unit may have a function for inputting an expression method designated by the user. Examples of input include, but are not limited to, keyboard input and voice input. For example, the designation unit may allow the user to input the expression method using a keyboard. The designation unit may also allow the designation unit to input the expression method using voice input. For example, the designation unit may allow the user to give a voice instruction and analyze the voice to set the expression method. Furthermore, the designation unit may also allow the designation unit to input the expression method using a touchscreen. For example, the designation unit may allow the user to set the expression method by tapping an option on the touchscreen. This allows the user to easily set the expression method designated by the user. Some or all of the above-described processing in the designation unit may be performed using, for example, AI, or may be performed without AI. For example, the designation unit may input the user's voice input to AI and have the AI ​​set the expression method from the voice data.

[0032] The generation unit can create an AI robot based on a specified expression method. Examples of the creation include, but are not limited to, training an AI model and using data. The generation unit can generate the user's appearance and voice using, for example, a text generation AI (e.g., LLM). The generation unit can also generate the user's appearance and voice using a multimodal generation AI. For example, the generation unit inputs a user's photo and voice data, and the AI ​​generates an appearance and voice that resembles the user. The generation unit can also customize the appearance and voice of the AI ​​robot to suit the user's preferences. For example, the generation unit generates an AI robot based on characteristics specified by the user (e.g., hairstyle, clothing, tone of voice, etc.). This allows the AI ​​robot to be generated based on the specified expression method. Some or all of the above-described processing in the generation unit is performed using AI. For example, the generation unit inputs a user's photo and voice data into the AI, and the AI ​​generates an appearance and voice that resembles the user.

[0033] The dialogue unit can conduct a dialogue using the created AI robot. Dialogue can include, but is not limited to, the use of natural language processing technology and dialogue scenarios. For example, the dialogue unit can converse with a robot that reproduces the voice and appearance of the deceased in a conversational format with the AI ​​robot. The dialogue unit can also converse with the AI ​​robot in a text chat format, reading letters or diaries written by the deceased. For example, the dialogue unit can use natural language processing technology to generate an appropriate response to a user's input. Furthermore, the dialogue unit can set a dialogue scenario and progress the dialogue by the user selecting options. For example, the dialogue unit determines the content and direction of the dialogue by the user selecting options. This allows a dialogue to be conducted using the created AI robot. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without AI. For example, the dialogue unit inputs a user's input to AI, which then generates an appropriate response.

[0034] The stock unit may include a storage unit that stores the stored information. Examples of storage include, but are not limited to, storing in a database or using cloud storage. For example, the storage unit stores information stored by the user in a database. The storage unit can also store information using cloud storage. For example, the storage unit works in conjunction with a cloud storage service to safely store the information stored by the user. Furthermore, the storage unit has a function to periodically back up information. For example, the storage unit periodically creates backups of data to prevent data loss. This allows the stored information to be safely stored. Some or all of the above-mentioned processing in the storage unit may be performed using AI, or may be performed without using AI. For example, the storage unit inputs the information stored by the user into AI, which then classifies and tags the data.

[0035] The designation unit may include a unit that manages the designated expression methods. Examples of management include, but are not limited to, using a database management system and setting access permissions. For example, the management unit stores and manages the expression methods designated by the user in a database. The management unit can also set access permissions so that only specific users can change the expression methods. For example, the management unit stores the expression methods designated by the user in a database so that only specific users can access them. Furthermore, the management unit has a function for saving a history of changes to the expression methods and allowing past settings to be referenced. For example, the management unit saves the history of changes to the expression methods in a database so that users can reference past settings. This allows for efficient management of the designated expression methods. Some or all of the above-described processing in the management unit may be performed using AI, or may be performed without AI. For example, the management unit inputs the expression methods designated by the user into AI, which then manages the data and sets access permissions.

[0036] The generation unit may include a unit for managing the created AI robot. Examples of management include, but are not limited to, using a database management system and setting access permissions. For example, the management unit stores and manages data of the generated AI robot in a database. The management unit can also set access permissions so that only specific users can access the AI ​​robot's data. For example, the management unit stores data of the generated AI robot in a database so that only specific users can access it. Furthermore, the management unit has a function for saving the AI ​​robot's update history and allowing users to refer to past versions. For example, the management unit saves the AI ​​robot's update history in a database so that users can refer to past versions. This allows for efficient management of the generated AI robot. Some or all of the above-described processing in the management unit may be performed using AI, or may be performed without AI. For example, the management unit inputs data of the generated AI robot into AI, which then manages the data and sets access permissions.

[0037] The dialogue unit may include a unit for storing a dialogue history. Examples of history storage include, but are not limited to, storing the history in a database or using cloud storage. For example, the history storage unit stores the dialogue history between the user and the AI ​​robot in a database. The history storage unit can also store the dialogue history using cloud storage. For example, the history storage unit works with a cloud storage service to securely store the dialogue history between the user and the AI ​​robot. Furthermore, the history storage unit includes a dialogue history search function. For example, the history storage unit allows the user to search past dialogue history and refer to specific dialogue content. By storing the dialogue history, the past dialogue content can be referenced. Some or all of the above-described processing in the history storage unit may be performed using AI, or may be performed without AI. For example, the history storage unit inputs the dialogue history between the user and the AI ​​robot into AI, which then classifies and tags the data.

[0038] When stocking, the stocking unit can analyze the user's past stocking history and select the optimal stocking method. Examples of stocking methods include, but are not limited to, storing information in a database or using cloud storage. For example, the stocking unit can analyze the types of information the user frequently stocked in the past and prioritize stocking similar information. The stocking unit can also analyze the format (text, image, video, etc.) of the information the user previously stocked and stock it in the optimal format. Furthermore, the stocking unit can analyze the user's tendency to stock at specific time periods based on the user's past stocking history and encourage stocking at those time periods. For example, the stocking unit can analyze the information the user previously stocked at specific time periods and send a notification encouraging stocking at those time periods. In this way, the optimal stocking method can be selected by analyzing the user's past stocking history. Some or all of the above-described processing in the stocking unit may be performed using AI or without AI. For example, the stocking unit can input the user's past stocking history data into a generation AI and have the generation AI select the optimal stocking method.

[0039] The stock unit can filter information based on the user's current lifestyle and areas of interest when storing the information. Examples of filtering include, but are not limited to, keyword filtering and category filtering. For example, the stock unit prioritizes storing information related to the user's current areas of interest (e.g., hobbies and favorite things). The stock unit can also filter related information based on the user's current lifestyle (e.g., raising children, working). Furthermore, the stock unit can filter information based on topics in which the user has recently shown interest (e.g., new hobbies and interests). For example, the stock unit filters related information based on keywords recently searched by the user or information on websites visited by the user. This allows information to be filtered based on the user's current lifestyle and areas of interest. Some or all of the above-described processing in the stock unit may be performed using AI or without AI. For example, the stock unit can input data on the user's current lifestyle and areas of interest into the generation AI and have the generation AI perform the filtering.

[0040] The stock unit can select the optimal stocking method depending on the user's input method when stocking. Input methods include, but are not limited to, voice input, text input, and image input. For example, when a user uses voice input, the stock unit automatically converts the voice data into text and stores it. Furthermore, when a user uploads an image, the stock unit can analyze the content using image recognition technology and store related information. Furthermore, when a user uses text input, the stock unit can automatically classify and store the input text. For example, when a user uses voice input, the stock unit inputs the voice data into an AI, which then converts the voice data into text and stores it. This allows the optimal stocking method to be selected depending on the user's input method. Some or all of the above-described processing in the stock unit may be performed using AI, or may be performed without AI. For example, the stock unit can input the user's input data into a generation AI and have the generation AI select the optimal stocking method.

[0041] The stock unit can classify information taking into account the user's family structure and relationships when storing the information. Examples of family structure and relationships include, but are not limited to, survey results and family trees. For example, when a user stores messages addressed to family members, the stock unit classifies the messages into appropriate categories based on the family structure. Furthermore, when a user stores messages addressed to friends, the stock unit can classify the messages into appropriate categories based on the relationship with the friends. Furthermore, when a user stores messages addressed to relatives, the stock unit can classify the messages into appropriate categories based on the relationship with the relatives. For example, when a user stores messages addressed to family members, the stock unit classifies the messages based on the family structure and prioritizes displaying information related to specific family members. This allows information to be classified taking into account the user's family structure and relationships. Some or all of the above-described processing in the stock unit may be performed using AI or without AI. For example, the stock unit can input data on the user's family structure and relationships into a generation AI and have the generation AI classify the information.

[0042] When storing information, the stock unit can prioritize stocking highly relevant information by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user lives in a specific area, the stock unit can prioritize stocking information related to that area. Furthermore, if the user is traveling, the stock unit can prioritize stocking information related to the user's travel destination. Furthermore, if the user is planning to move, the stock unit can prioritize stocking information related to the user's new residence. For example, if the user lives in a specific area, the stock unit can stock events and news related to that area. This allows highly relevant information to be prioritized by taking into account the user's geographical location information. Some or all of the above-described processing in the stock unit may be performed using AI, or may be performed without using AI. For example, the stock unit can input the user's geographical location information into the generation AI and cause the generation AI to select highly relevant information.

[0043] The stock unit can analyze the user's social media activity and store related information during storage. Social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the stock unit automatically stores photos and videos shared by the user on social media. The stock unit can also analyze the user's social media posts and store related information. Furthermore, the stock unit can store related information based on the activities of the user's friends on social media. For example, the stock unit automatically stores photos and videos shared by the user on social media and adds related tags. This allows the user's social media activity to be analyzed and related information to be stored. Some or all of the above-described processing in the stock unit may be performed using AI or without AI. For example, the stock unit can input the user's social media activity data into a generation AI and have the generation AI select related information.

[0044] The stocking unit can customize the stocking method by reflecting the user's past feedback during stocking. Examples of feedback include, but are not limited to, survey results and user reviews. The stocking unit can improve the stocking method based on, for example, feedback provided by the user in the past. The stocking unit can also customize the stocking method for specific information based on the user's past feedback. Furthermore, the stocking unit can analyze the user's past feedback and propose an optimal stocking method. For example, the stocking unit can improve the stocking method based on the user's past feedback and propose a stocking method tailored to the user's needs. This allows the stocking method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the stocking unit may be performed using AI, or may be performed without AI. For example, the stocking unit can input the user's past feedback data into a generation AI and have the generation AI customize the stocking method.

[0045] The storage unit can adjust the timing of information acquisition during storage, taking into account the user's health condition and lifestyle. Examples of health condition and lifestyle include, but are not limited to, data from a wearable device and self-reported data. For example, the storage unit can set a periodic timing for storing information when the user's health condition is good. Furthermore, the storage unit can flexibly adjust the timing for acquiring the stored information when the user's health condition is deteriorating. Furthermore, the storage unit can suggest the optimal timing for acquiring information in accordance with the user's lifestyle. For example, when the user's health condition is good, the storage unit can set a periodic timing for storing information and send a notification. This allows the timing for acquiring information to be adjusted taking into account the user's health condition and lifestyle. Some or all of the above-described processing in the storage unit may be performed using AI, or may be performed without AI. For example, the storage unit can input data on the user's health condition and lifestyle into the generation AI and cause the generation AI to adjust the timing for acquiring information.

[0046] At the time of designation, the designation unit can analyze the user's past designation history and suggest the optimal expression method. The designation history includes, for example, past setting data, log data, etc., but is not limited to such examples. For example, the designation unit can analyze the user's past designation history and suggest a similar expression method. The designation unit can also predict and suggest an expression method to be used during a specific time period based on the user's past designation history. Furthermore, the designation unit can customize and suggest the optimal expression method based on the user's past designation history. For example, the designation unit can analyze the user's past designation history and suggest a similar expression method. This allows the user's past designation history to be analyzed and the optimal expression method to be suggested. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without AI. For example, the designation unit can input the user's past designation history data into a generation AI and have the generation AI suggest the optimal expression method.

[0047] When designating a method of expression, the designation unit can select the method of expression reflecting the opinions of the user's family and relatives. Opinions of the family and relatives include, but are not limited to, survey results, interview results, etc. For example, the designation unit selects the method of expression reflecting the preference of the user's family. The designation unit can also select the method of expression reflecting the preference of the user's relatives. Furthermore, the designation unit can select the optimal method of expression based on the opinions of the user's family and relatives. For example, the designation unit selects the method of expression reflecting the preference of the user's family. This allows the selection of the method of expression to reflect the opinions of the user's family and relatives. Some or all of the above-described processing in the designation unit may be performed using AI or may be performed without using AI. For example, the designation unit can input opinion data of the user's family and relatives into the generation AI and cause the generation AI to select the method of expression.

[0048] The designation unit may adjust the expression method by taking into consideration the user's cultural background and religious beliefs. Examples of the cultural background and religious beliefs include, but are not limited to, survey results and self-reported data. The designation unit may select an appropriate expression method based on the user's cultural background. The designation unit may also select an appropriate expression method based on the user's religious beliefs. Furthermore, the designation unit may customize the optimal expression method by taking into consideration the user's cultural background and religious beliefs. For example, the designation unit may select an appropriate expression method based on the user's cultural background. This allows the expression method to be adjusted by taking into consideration the user's cultural background and religious beliefs. Some or all of the above-described processing by the designation unit may be performed using AI or without AI. For example, the designation unit may input data on the user's cultural background and religious beliefs into the generation AI and cause the generation AI to adjust the expression method.

[0049] The designation unit can propose an optimal expression method by taking into consideration the user's geographical location information at the time of designation. Geographical location information includes, but is not limited to, GPS data, IP address, etc. For example, if the user lives in a specific area, the designation unit can propose an expression method related to that area. Furthermore, if the user is traveling, the designation unit can propose an expression method related to the travel destination. Furthermore, if the user is planning to move, the designation unit can propose an expression method related to the new residence. For example, if the user lives in a specific area, the designation unit proposes an expression method related to that area. This allows the optimal expression method to be proposed by taking into consideration the user's geographical location information. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input the user's geographical location information to the generation AI and cause the generation AI to propose an optimal expression method.

[0050] At the time of designation, the designation unit can analyze the user's social media activity and suggest a relevant expression method. Social media activity includes, but is not limited to, analysis of post content and follower analysis, for example. The designation unit can also analyze the user's social media post content and suggest a relevant expression method. Furthermore, the designation unit can also suggest a relevant expression method by referring to the activity of the user's friends on social media. For example, the designation unit can suggest a relevant expression method based on the information the user shared on social media. In this way, the user's social media activity can be analyzed and a relevant expression method can be suggested. Some or all of the above-described processing in the designation unit may be performed using AI or without AI. For example, the designation unit can input the user's social media activity data into the generation AI and cause the generation AI to suggest a relevant expression method.

[0051] When specifying the expression method, the designation unit can customize the expression method by reflecting the user's past feedback. Examples of feedback include, but are not limited to, survey results and user reviews. The designation unit can improve the expression method based on, for example, feedback previously provided by the user. The designation unit can also customize a specific expression method based on the user's past feedback. Furthermore, the designation unit can analyze the user's past feedback and suggest an optimal expression method. For example, the designation unit can improve the expression method based on the user's past feedback and suggest an expression method that meets the user's needs. This allows the expression method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the expression method.

[0052] The designation unit can adjust the timing of the expression method in consideration of the user's lifestyle rhythm and activity pattern when designating the expression method. Lifestyle rhythm and activity pattern include, but are not limited to, data from a wearable device and self-reported data. For example, if the user is a morning person, the designation unit can suggest an expression method suitable for morning hours. Furthermore, if the user is a night owl, the designation unit can also suggest an expression method suitable for evening hours. Furthermore, the designation unit can adjust the optimal timing of the expression method based on the user's activity pattern. For example, if the user is a morning person, the designation unit can suggest an expression method suitable for morning hours. This allows the timing of the expression method to be adjusted in consideration of the user's lifestyle rhythm and activity pattern. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input data on the user's lifestyle rhythm and activity pattern to the generation AI and cause the generation AI to adjust the timing of the expression method.

[0053] During generation, the generation unit can analyze the user's past generation history and select the optimal generation method. The generation history includes, but is not limited to, past generation data and log data. For example, the generation unit can analyze the appearance and voice of AI robots previously generated by the user and generate an AI robot with similar characteristics. The generation unit can also analyze the user's tendency to generate AI robots during specific time periods based on the user's past generation history and prompt the user to generate an AI robot during those time periods. Furthermore, the generation unit can customize and suggest the optimal generation method based on the user's past generation history. For example, the generation unit can analyze the appearance and voice of AI robots previously generated by the user and generate an AI robot with similar characteristics. This allows the user's past generation history to be analyzed and the optimal generation method selected. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without AI. For example, the generation unit can input the user's past generation history data into the generation AI and have the generation AI select the optimal generation method.

[0054] The generation unit can generate an AI robot by reflecting the opinions of the user's family and relatives. Opinions of the family and relatives include, but are not limited to, survey results and interview results. For example, the generation unit can generate an AI robot with the appearance and voice desired by the user's family. The generation unit can also generate an AI robot with characteristics desired by the user's relatives. Furthermore, the generation unit can generate an optimal AI robot based on the opinions of the user's family and relatives. For example, the generation unit can generate an AI robot with the appearance and voice desired by the user's family. This allows the AI ​​robot to be generated while reflecting the opinions of the user's family and relatives. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input opinion data of the user's family and relatives into the generation AI and cause the generation AI to generate the AI ​​robot.

[0055] The generation unit can adjust the AI ​​robot during generation, taking into account the user's cultural background and religious beliefs. Examples of cultural background and religious beliefs include, but are not limited to, survey results and self-reported data. For example, the generation unit generates an AI robot with an appropriate appearance and voice based on the user's cultural background. The generation unit can also generate an AI robot with appropriate characteristics based on the user's religious beliefs. Furthermore, the generation unit can customize an optimal AI robot by taking into account the user's cultural background and religious beliefs. For example, the generation unit generates an AI robot with an appropriate appearance and voice based on the user's cultural background. This allows the AI ​​robot to be adjusted taking into account the user's cultural background and religious beliefs. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input data on the user's cultural background and religious beliefs into the generation AI and have the generation AI adjust the AI ​​robot.

[0056] The generation unit can generate an optimal AI robot by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user lives in a specific area, the generation unit can generate an AI robot with characteristics related to that area. Furthermore, if the user is traveling, the generation unit can generate an AI robot with characteristics related to the travel destination. Furthermore, if the user is planning to move, the generation unit can generate an AI robot with characteristics related to the new residence. For example, if the user lives in a specific area, the generation unit can generate an AI robot with characteristics related to that area. This allows the generation of an optimal AI robot by taking into account the user's geographical location information. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's geographical location information into the generation AI and cause the generation AI to generate an optimal AI robot.

[0057] During generation, the generation unit can analyze the user's social media activities and generate a related AI robot. Social media activities include, but are not limited to, analysis of posted content and follower analysis. For example, the generation unit can generate an AI robot with related characteristics based on information shared by the user on social media. The generation unit can also analyze the user's social media posts and generate an AI robot with related characteristics. Furthermore, the generation unit can generate an AI robot with related characteristics based on the activities of the user's friends on social media. For example, the generation unit generates an AI robot with related characteristics based on information shared by the user on social media. In this way, the user's social media activities can be analyzed to generate a related AI robot. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's social media activity data into the generation AI and cause the generation AI to generate a related AI robot.

[0058] The generation unit can customize the AI ​​robot by reflecting the user's past feedback during generation. Examples of feedback include, but are not limited to, survey results and user reviews. The generation unit can improve the AI ​​robot based on, for example, feedback previously provided by the user. The generation unit can also customize an AI robot with specific characteristics based on the user's past feedback. Furthermore, the generation unit can analyze the user's past feedback and propose an optimal AI robot. For example, the generation unit can improve the AI ​​robot based on the user's past feedback and propose an AI robot tailored to the user's needs. This allows the AI ​​robot to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's past feedback data into the generation AI and have the generation AI customize the AI ​​robot.

[0059] During generation, the generation unit can adjust the operation timing of the AI ​​robot taking into account the user's lifestyle rhythm and activity pattern. Lifestyle rhythms and activity patterns include, but are not limited to, data from wearable devices and self-reported data. For example, if the user is a morning person, the generation unit can generate an AI robot with operation timings suitable for morning hours. Furthermore, if the user is a night owl, the generation unit can generate an AI robot with operation timings suitable for evening hours. Furthermore, the generation unit can generate an AI robot with optimal operation timings based on the user's activity pattern. For example, if the user is a morning person, the generation unit can generate an AI robot with operation timings suitable for morning hours. This allows the operation timing of the AI ​​robot to be adjusted taking into account the user's lifestyle rhythm and activity pattern. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input data on the user's lifestyle rhythm and activity pattern into the generation AI and cause the generation AI to adjust the operation timing of the AI ​​robot.

[0060] During a dialogue, the dialogue unit can analyze the user's past dialogue history and select an optimal dialogue method. The dialogue history includes, but is not limited to, past dialogue data and log data. For example, the dialogue unit can analyze a dialogue method that the user previously preferred and conduct the dialogue in a similar manner. The dialogue unit can also predict and suggest a dialogue method to be used at a specific time period based on the user's past dialogue history. Furthermore, the dialogue unit can customize and suggest an optimal dialogue method based on the user's past dialogue history. For example, the dialogue unit can analyze a dialogue method that the user previously preferred and conduct the dialogue in a similar manner. This allows the user's past dialogue history to be analyzed and the optimal dialogue method to be selected. Some or all of the above-described processing in the dialogue unit may be performed using AI or without AI. For example, the dialogue unit can input the user's past dialogue history data into a generation AI and cause the generation AI to select an optimal dialogue method.

[0061] During a dialogue, the dialogue unit can select dialogue content that reflects the opinions of the user's family and relatives. Opinions of the family and relatives include, but are not limited to, survey results, interview results, etc. The dialogue unit, for example, selects dialogue content that reflects the dialogue content desired by the user's family. The dialogue unit can also select dialogue content that reflects the dialogue content desired by the user's relatives. Furthermore, the dialogue unit can select optimal dialogue content based on the opinions of the user's family and relatives. For example, the dialogue unit selects dialogue content that reflects the dialogue content desired by the user's family. This allows the dialogue content to be selected that reflects the opinions of the user's family and relatives. Some or all of the above-described processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input opinion data of the user's family and relatives into the generation AI and cause the generation AI to select the dialogue content.

[0062] During a dialogue, the dialogue unit can adjust the dialogue content taking into account the user's cultural background and religious beliefs. Examples of cultural background and religious beliefs include, but are not limited to, survey results and self-reported data. The dialogue unit, for example, selects appropriate dialogue content based on the user's cultural background. The dialogue unit can also select appropriate dialogue content based on the user's religious beliefs. Furthermore, the dialogue unit can customize optimal dialogue content taking into account the user's cultural background and religious beliefs. For example, the dialogue unit selects appropriate dialogue content based on the user's cultural background. This allows the dialogue content to be adjusted taking into account the user's cultural background and religious beliefs. Some or all of the above-described processing in the dialogue unit may be performed using AI or without AI. For example, the dialogue unit can input data on the user's cultural background and religious beliefs into the generation AI and cause the generation AI to adjust the dialogue content.

[0063] The dialogue unit can provide optimal dialogue content during dialogue by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user lives in a specific area, the dialogue unit can provide dialogue content related to that area. Furthermore, if the user is traveling, the dialogue unit can provide dialogue content related to the user's travel destination. Furthermore, if the user is planning to move, the dialogue unit can provide dialogue content related to the user's new residence. For example, if the user lives in a specific area, the dialogue unit provides dialogue content related to that area. This allows optimal dialogue content to be provided by taking into account the user's geographical location information. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the user's geographical location information into a generation AI and cause the generation AI to provide optimal dialogue content.

[0064] The dialogue unit can analyze the user's social media activity during the dialogue and provide related dialogue content. Social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the dialogue unit can provide related dialogue content based on information shared by the user on social media. The dialogue unit can also analyze the user's social media posts and provide related dialogue content. Furthermore, the dialogue unit can provide related dialogue content by referring to the activities of the user's friends on social media. For example, the dialogue unit can provide related dialogue content based on information shared by the user on social media. In this way, the user's social media activity can be analyzed and related dialogue content can be provided. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or without AI. For example, the dialogue unit can input the user's social media activity data into a generation AI and cause the generation AI to provide related dialogue content.

[0065] The dialogue unit can customize the dialogue method by reflecting the user's past feedback during dialogue. Examples of feedback include, but are not limited to, survey results and user reviews. The dialogue unit can improve the dialogue method based on, for example, feedback provided by the user in the past. The dialogue unit can also customize a specific dialogue method based on the user's past feedback. Furthermore, the dialogue unit can analyze the user's past feedback and suggest an optimal dialogue method. For example, the dialogue unit can improve the dialogue method and suggest a dialogue method tailored to the user's needs based on the user's past feedback. This allows the dialogue method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the user's past feedback data into a generation AI and have the generation AI customize the dialogue method.

[0066] During the dialogue, the dialogue unit can adjust the dialogue timing taking into account the user's lifestyle rhythm and activity pattern. Lifestyle rhythms and activity patterns include, but are not limited to, wearable device data and self-reported data. For example, if the user is a morning person, the dialogue unit can provide a dialogue timing suitable for the morning hours. Furthermore, if the user is a night owl, the dialogue unit can also provide a dialogue timing suitable for the evening hours. Furthermore, the dialogue unit can also suggest an optimal dialogue timing based on the user's activity pattern. For example, if the user is a morning person, the dialogue unit can provide a dialogue timing suitable for the morning hours. This allows the dialogue timing to be adjusted taking into account the user's lifestyle rhythm and activity pattern. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input data on the user's lifestyle rhythm and activity pattern into the generation AI and cause the generation AI to adjust the dialogue timing.

[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 stock unit can analyze a user's preferences and interests based on the information stored by the user and suggest new related information. For example, if a user has a large collection of movies in a particular genre, the stock unit can suggest new movies related to that genre. If a user has a large collection of books by a particular author, the stock unit can suggest new releases by that author or books by related authors. Furthermore, if a user has a large collection of information related to a particular hobby, the stock unit can suggest events and news related to that hobby. This improves the user's experience by suggesting new information based on the user's preferences and interests. Some or all of the above-described processing in the stock unit may be performed using AI, or may be performed without AI. For example, the stock unit can input the user's stock data into a generation AI and have the generation AI suggest new related information.

[0069] The designation unit may have a function for sharing information with other users based on the expression method specified by the user. For example, if a user wants to share specific photos or videos with family or friends, the designation unit may select the information and generate a sharing link. Also, if a user wants to share a specific letter or diary entry, the designation unit may digitize the information and generate a sharing link. Furthermore, if a user wants to share information about a specific hobby or interest, the designation unit may select the information and post it to a related community or forum. This allows information to be shared with other users based on the expression method specified by the user. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without AI. For example, the designation unit may input the user's designated data into a generation AI and cause the generation AI to generate a sharing link.

[0070] The stock unit can analyze the user's past stock history and select the optimal stock method. For example, it analyzes the types of information the user frequently stocked in the past and prioritizes stocking similar information. It can also analyze the format of information the user previously stocked (text, images, videos, etc.) and stock it in the optimal format. Furthermore, it can analyze the user's tendency to stock at specific time periods based on the user's past stock history and encourage stocking at those time periods. For example, it can analyze the information the user previously stocked at specific time periods and send a notification encouraging stocking at those time periods. In this way, the optimal stock method can be selected by analyzing the user's past stock history. Some or all of the above-mentioned processing in the stock unit may be performed using AI, or may be performed without AI. For example, the stock unit can input the user's past stock history data into a generation AI and have the generation AI select the optimal stock method.

[0071] The designation unit can analyze the user's past designation history and suggest the optimal expression method. For example, it can analyze the expression methods selected by the user in the past and suggest similar expression methods. It can also predict and suggest the expression method to be used during a specific time period from the user's past designation history. It can also customize and suggest the optimal expression method based on the user's past designation history. For example, it can analyze the expression methods selected by the user in the past and suggest similar expression methods. In this way, it is possible to analyze the user's past designation history and suggest the optimal expression method. Some or all of the above-mentioned processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input the user's past designation history data into a generation AI and have the generation AI suggest the optimal expression method.

[0072] The generation unit can analyze the user's past generation history and select the optimal generation method. For example, it can analyze the appearance and voice of AI robots generated by the user in the past and generate an AI robot with similar characteristics. It can also analyze the user's past generation history to determine a tendency to generate AI robots at specific times of the day and encourage generation at those times. It can also customize and suggest the optimal generation method based on the user's past generation history. For example, it can analyze the appearance and voice of AI robots generated by the user in the past and generate an AI robot with similar characteristics. This allows the user's past generation history to be analyzed and the optimal generation method to be selected. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's past generation history data into the generation AI and have the generation AI select the optimal generation method.

[0073] The dialogue unit can analyze the user's past dialogue history and select the optimal dialogue method. For example, it analyzes the dialogue methods that the user has previously preferred and conducts dialogue in a similar manner. It can also predict and suggest a dialogue method to be used at a specific time period from the user's past dialogue history. It can also customize and suggest an optimal dialogue method based on the user's past dialogue history. For example, it analyzes the dialogue methods that the user has previously preferred and conducts dialogue in a similar manner. In this way, it is possible to analyze the user's past dialogue history and select the optimal dialogue method. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the user's past dialogue history data into a generation AI and have the generation AI select the optimal dialogue method.

[0074] The processing flow of the first embodiment will be briefly explained below.

[0075] Step 1: The Stock section stores information such as photos, videos, favorite TV shows, books, magazines, movies, hobbies, favorite things, favorite sayings, letters, diaries, maternal and child health handbooks, medicine records, children's artwork, words of gratitude, and insider stories. For example, the Stock section has a function that allows users to upload photos and videos of family memories. The Stock section can also digitize and store letters and diaries. Step 2: The specification unit specifies how the information stored by the storage unit is to be expressed. For example, if the specification unit is to play only audio, it can record the user's voice. If the specification unit is to play only text, it can save letters or diaries written by the user as text data. If the specification unit is to play with background music, it can play the user's favorite music in the background. Step 3: The generator generates an AI robot based on the expression method specified by the specification unit. For example, the generator can generate the user's appearance and voice using AI to resemble the user. The generator generates the user's appearance and voice using text generation AI (e.g., LLM) or multimodal generation AI. Step 4: The dialogue unit engages in dialogue using the AI ​​robot generated by the generation unit. For example, the dialogue unit can converse with an AI robot that reproduces the voice and appearance of the deceased. The dialogue unit can also converse in text chat format while reading letters or diaries written by the deceased.

[0076] (Example 2) An information storage system according to an embodiment of the present invention executes information stored by a user in advance using a specified expression method, allowing for simulated interactive communication with the deceased. The information storage system allows users to store information such as photos, videos, favorite TV programs, books, magazines, movies, hobbies, favorite things, favorite words, letters, diaries, maternal and child health handbooks, medicine records, children's artwork, words of gratitude, and secret stories. The system then generates an AI robot based on the specified expression method and engages in dialogue. For example, the information storage system allows users to store memorable photos and videos of family memories and create lists of favorite movies and books. It is also possible to digitize and store letters and diaries. Next, the information storage system allows users to specify the expression method for the stored information. For example, when playing audio only, the user's voice can be recorded. When playing text only, letters and diaries written by the user are saved as text data. When playing with background music, the user's favorite music can be played in the background. Furthermore, the information storage system can use AI to generate a user's appearance and voice, making them resemble the user. Finally, the information storage system allows surviving relatives to engage in simulated interactive communication with the deceased. For example, through a conversational AI robot, users can converse with a robot that replicates the voice and appearance of the deceased. It is also possible to have a text chat while reading letters and diaries written by the deceased. This allows the information storage system to preserve the user's memories and messages, and surviving relatives can find peace of mind through conversations with the deceased. This allows the information storage system to preserve the user's memories and messages, and surviving relatives can find peace of mind through conversations with the deceased. For example, by having the AI ​​robot talk about a user's favorite movie, family members can share the deceased's hobbies and preferences and feel a connection with the deceased. It is also possible to receive memories and words of gratitude from the deceased through letters and diaries.

[0077] An information storage system according to an embodiment includes a storage unit, a designation unit, a generation unit, and a dialogue unit. The storage unit stores information such as photos, videos, favorite TV programs, books, magazines, movies, hobbies, favorite things, favorite words, letters, diaries, maternal and child health handbooks, medicine handbooks, children's artwork, words of gratitude, and insider stories. For example, the storage unit has a function that allows the user to upload photos and videos of family memories. The storage unit can also digitize and store letters and diaries. The designation unit specifies how to express the information stored by the storage unit. For example, the designation unit can record the user's voice when playing audio only. When playing text only, the designation unit saves letters and diaries written by the user as text data. When playing with background music, the user's favorite music can be played in the background. The generation unit generates an AI robot based on the expression method specified by the designation unit. For example, the generation unit can generate the user's appearance and voice using AI to resemble the user. The generation unit can generate the user's appearance and voice using text generation AI (e.g., LLM) or multimodal generation AI. The dialogue unit engages in dialogue using the AI ​​robot generated by the generation unit. For example, the dialogue unit can converse with an AI robot that reproduces the voice and appearance of the deceased in a conversational format. The dialogue unit can also converse in a text chat format while reading letters or diaries written by the deceased. In this way, the information storage system according to the embodiment allows the user's memories and messages to be preserved, and surviving relatives can find peace of mind through dialogue with the deceased.

[0078] The stock unit may have a function that allows users to upload images and videos. Examples of image and video formats include, but are not limited to, JPEG, PNG, and MP4. The stock unit may have a function that allows users to upload images and videos from their own devices. For example, the stock unit may upload images and videos directly from a smartphone or PC. The stock unit may also store images and videos using cloud storage. For example, the stock unit may link with a cloud storage service to securely store images and videos uploaded by users. This allows users to easily store photos and videos. Some or all of the above-described processing in the stock unit may be performed using, or without, AI. For example, the stock unit may input images and videos uploaded by users into AI and have the AI ​​classify and tag the images and videos.

[0079] The designation unit may have a function for inputting an expression method designated by the user. Examples of input include, but are not limited to, keyboard input and voice input. For example, the designation unit may allow the user to input the expression method using a keyboard. The designation unit may also allow the designation unit to input the expression method using voice input. For example, the designation unit may allow the user to give a voice instruction and analyze the voice to set the expression method. Furthermore, the designation unit may also allow the designation unit to input the expression method using a touchscreen. For example, the designation unit may allow the user to set the expression method by tapping an option on the touchscreen. This allows the user to easily set the expression method designated by the user. Some or all of the above-described processing in the designation unit may be performed using, for example, AI, or may be performed without AI. For example, the designation unit may input the user's voice input to AI and have the AI ​​set the expression method from the voice data.

[0080] The generation unit can create an AI robot based on a specified expression method. Examples of the creation include, but are not limited to, training an AI model and using data. The generation unit can generate the user's appearance and voice using, for example, a text generation AI (e.g., LLM). The generation unit can also generate the user's appearance and voice using a multimodal generation AI. For example, the generation unit inputs a user's photo and voice data, and the AI ​​generates an appearance and voice that resembles the user. The generation unit can also customize the appearance and voice of the AI ​​robot to suit the user's preferences. For example, the generation unit generates an AI robot based on characteristics specified by the user (e.g., hairstyle, clothing, tone of voice, etc.). This allows the AI ​​robot to be generated based on the specified expression method. Some or all of the above-described processing in the generation unit is performed using AI. For example, the generation unit inputs a user's photo and voice data into the AI, and the AI ​​generates an appearance and voice that resembles the user.

[0081] The dialogue unit can conduct a dialogue using the created AI robot. Dialogue can include, but is not limited to, the use of natural language processing technology and dialogue scenarios. For example, the dialogue unit can converse with a robot that reproduces the voice and appearance of the deceased in a conversational format with the AI ​​robot. The dialogue unit can also converse with the AI ​​robot in a text chat format, reading letters or diaries written by the deceased. For example, the dialogue unit can use natural language processing technology to generate an appropriate response to a user's input. Furthermore, the dialogue unit can set a dialogue scenario and progress the dialogue by the user selecting options. For example, the dialogue unit determines the content and direction of the dialogue by the user selecting options. This allows a dialogue to be conducted using the created AI robot. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without AI. For example, the dialogue unit inputs a user's input to AI, which then generates an appropriate response.

[0082] The stock unit may include a storage unit that stores the stored information. Examples of storage include, but are not limited to, storing in a database or using cloud storage. For example, the storage unit stores information stored by the user in a database. The storage unit can also store information using cloud storage. For example, the storage unit works in conjunction with a cloud storage service to safely store the information stored by the user. Furthermore, the storage unit has a function to periodically back up information. For example, the storage unit periodically creates backups of data to prevent data loss. This allows the stored information to be safely stored. Some or all of the above-mentioned processing in the storage unit may be performed using AI, or may be performed without using AI. For example, the storage unit inputs the information stored by the user into AI, which then classifies and tags the data.

[0083] The designation unit may include a unit that manages the designated expression methods. Examples of management include, but are not limited to, using a database management system and setting access permissions. For example, the management unit stores and manages the expression methods designated by the user in a database. The management unit can also set access permissions so that only specific users can change the expression methods. For example, the management unit stores the expression methods designated by the user in a database so that only specific users can access them. Furthermore, the management unit has a function for saving a history of changes to the expression methods and allowing past settings to be referenced. For example, the management unit saves the history of changes to the expression methods in a database so that users can reference past settings. This allows for efficient management of the designated expression methods. Some or all of the above-described processing in the management unit may be performed using AI, or may be performed without AI. For example, the management unit inputs the expression methods designated by the user into AI, which then manages the data and sets access permissions.

[0084] The generation unit may include a unit for managing the created AI robot. Examples of management include, but are not limited to, using a database management system and setting access permissions. For example, the management unit stores and manages data of the generated AI robot in a database. The management unit can also set access permissions so that only specific users can access the AI ​​robot's data. For example, the management unit stores data of the generated AI robot in a database so that only specific users can access it. Furthermore, the management unit has a function for saving the AI ​​robot's update history and allowing users to refer to past versions. For example, the management unit saves the AI ​​robot's update history in a database so that users can refer to past versions. This allows for efficient management of the generated AI robot. Some or all of the above-described processing in the management unit may be performed using AI, or may be performed without AI. For example, the management unit inputs data of the generated AI robot into AI, which then manages the data and sets access permissions.

[0085] The dialogue unit may include a unit for storing a dialogue history. Examples of history storage include, but are not limited to, storing the history in a database or using cloud storage. For example, the history storage unit stores the dialogue history between the user and the AI ​​robot in a database. The history storage unit can also store the dialogue history using cloud storage. For example, the history storage unit works with a cloud storage service to securely store the dialogue history between the user and the AI ​​robot. Furthermore, the history storage unit includes a dialogue history search function. For example, the history storage unit allows the user to search past dialogue history and refer to specific dialogue content. By storing the dialogue history, the past dialogue content can be referenced. Some or all of the above-described processing in the history storage unit may be performed using AI, or may be performed without AI. For example, the history storage unit inputs the dialogue history between the user and the AI ​​robot into AI, which then classifies and tags the data.

[0086] The storage unit can estimate the user's emotions and prioritize the information to be saved based on the estimated user emotions. Estimating emotions can be achieved, for example, by using an emotion recognition algorithm or by using a data type, but is not limited to these examples. The storage unit can, for example, analyze the user's facial expressions or voice data to estimate emotions. The storage unit can also analyze the user's text data to estimate emotions. For example, the storage unit can analyze text data entered by the user and calculate an emotion score. Furthermore, the storage unit can prioritize the information to be saved based on the estimated emotions. For example, if the user is emotionally calm, important information (e.g., letters or diaries) can be prioritized for storage. Also, if the user is emotionally excited, light content (e.g., favorite TV shows or movies) can be prioritized for storage. Furthermore, if the user is emotionally unstable, words of gratitude or encouraging messages can be prioritized for storage. Thus, by prioritizing information based on the user's emotions, more appropriate information can be saved. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using AI, or may be performed without using AI. For example, the storage unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0087] When stocking, the stocking unit can analyze the user's past stocking history and select the optimal stocking method. Examples of stocking methods include, but are not limited to, storing information in a database or using cloud storage. For example, the stocking unit can analyze the types of information the user frequently stocked in the past and prioritize stocking similar information. The stocking unit can also analyze the format (text, image, video, etc.) of the information the user previously stocked and stock it in the optimal format. Furthermore, the stocking unit can analyze the user's tendency to stock at specific time periods based on the user's past stocking history and encourage stocking at those time periods. For example, the stocking unit can analyze the information the user previously stocked at specific time periods and send a notification encouraging stocking at those time periods. In this way, the optimal stocking method can be selected by analyzing the user's past stocking history. Some or all of the above-described processing in the stocking unit may be performed using AI or without AI. For example, the stocking unit can input the user's past stocking history data into a generation AI and have the generation AI select the optimal stocking method.

[0088] The stock unit can filter information based on the user's current lifestyle and areas of interest when storing the information. Examples of filtering include, but are not limited to, keyword filtering and category filtering. For example, the stock unit prioritizes storing information related to the user's current areas of interest (e.g., hobbies and favorite things). The stock unit can also filter related information based on the user's current lifestyle (e.g., raising children, working). Furthermore, the stock unit can filter information based on topics in which the user has recently shown interest (e.g., new hobbies and interests). For example, the stock unit filters related information based on keywords recently searched by the user or information on websites visited by the user. This allows information to be filtered based on the user's current lifestyle and areas of interest. Some or all of the above-described processing in the stock unit may be performed using AI or without AI. For example, the stock unit can input data on the user's current lifestyle and areas of interest into the generation AI and have the generation AI perform the filtering.

[0089] The stock unit can select the optimal stocking method depending on the user's input method when stocking. Input methods include, but are not limited to, voice input, text input, and image input. For example, when a user uses voice input, the stock unit automatically converts the voice data into text and stores it. Furthermore, when a user uploads an image, the stock unit can analyze the content using image recognition technology and store related information. Furthermore, when a user uses text input, the stock unit can automatically classify and store the input text. For example, when a user uses voice input, the stock unit inputs the voice data into an AI, which then converts the voice data into text and stores it. This allows the optimal stocking method to be selected depending on the user's input method. Some or all of the above-described processing in the stock unit may be performed using AI, or may be performed without AI. For example, the stock unit can input the user's input data into a generation AI and have the generation AI select the optimal stocking method.

[0090] The stock unit can classify information taking into account the user's family structure and relationships when storing the information. Examples of family structure and relationships include, but are not limited to, survey results and family trees. For example, when a user stores messages addressed to family members, the stock unit classifies the messages into appropriate categories based on the family structure. Furthermore, when a user stores messages addressed to friends, the stock unit can classify the messages into appropriate categories based on the relationship with the friends. Furthermore, when a user stores messages addressed to relatives, the stock unit can classify the messages into appropriate categories based on the relationship with the relatives. For example, when a user stores messages addressed to family members, the stock unit classifies the messages based on the family structure and prioritizes displaying information related to specific family members. This allows information to be classified taking into account the user's family structure and relationships. Some or all of the above-described processing in the stock unit may be performed using AI or without AI. For example, the stock unit can input data on the user's family structure and relationships into a generation AI and have the generation AI classify the information.

[0091] The storage unit can estimate the user's emotions and adjust the expression method of the stored information based on the estimated user emotions. Estimating emotions can be achieved, for example, by using an emotion recognition algorithm or by using a data type, but is not limited to these examples. The storage unit can, for example, analyze the user's facial expressions or voice data to estimate emotions. The storage unit can also analyze the user's text data to estimate emotions. For example, the storage unit can analyze text data entered by the user and calculate an emotion score. Furthermore, the storage unit can adjust the expression method of the stored information based on the estimated emotions. For example, if the user is emotionally calm, the storage unit can store information using a formal expression method. Furthermore, if the user is emotionally excited, the storage unit can store information using a casual expression method. Furthermore, if the user is emotionally unstable, the storage unit can store information expressed in a gentle tone. This allows the expression method of information to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the storage unit may be performed using AI, or may be performed without using AI. For example, the storage unit may input the user's facial expression data into the generation AI and have the generation AI estimate the emotion.

[0092] When storing information, the stock unit can prioritize stocking highly relevant information by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user lives in a specific area, the stock unit can prioritize stocking information related to that area. Furthermore, if the user is traveling, the stock unit can prioritize stocking information related to the user's travel destination. Furthermore, if the user is planning to move, the stock unit can prioritize stocking information related to the user's new residence. For example, if the user lives in a specific area, the stock unit can stock events and news related to that area. This allows highly relevant information to be prioritized by taking into account the user's geographical location information. Some or all of the above-described processing in the stock unit may be performed using AI, or may be performed without using AI. For example, the stock unit can input the user's geographical location information into the generation AI and cause the generation AI to select highly relevant information.

[0093] The stock unit can analyze the user's social media activity and store related information during storage. Social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the stock unit automatically stores photos and videos shared by the user on social media. The stock unit can also analyze the user's social media posts and store related information. Furthermore, the stock unit can store related information based on the activities of the user's friends on social media. For example, the stock unit automatically stores photos and videos shared by the user on social media and adds related tags. This allows the user's social media activity to be analyzed and related information to be stored. Some or all of the above-described processing in the stock unit may be performed using AI or without AI. For example, the stock unit can input the user's social media activity data into a generation AI and have the generation AI select related information.

[0094] The stocking unit can customize the stocking method by reflecting the user's past feedback during stocking. Examples of feedback include, but are not limited to, survey results and user reviews. The stocking unit can improve the stocking method based on, for example, feedback provided by the user in the past. The stocking unit can also customize the stocking method for specific information based on the user's past feedback. Furthermore, the stocking unit can analyze the user's past feedback and propose an optimal stocking method. For example, the stocking unit can improve the stocking method based on the user's past feedback and propose a stocking method tailored to the user's needs. This allows the stocking method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the stocking unit may be performed using AI, or may be performed without AI. For example, the stocking unit can input the user's past feedback data into a generation AI and have the generation AI customize the stocking method.

[0095] The storage unit can adjust the timing of information acquisition during storage, taking into account the user's health condition and lifestyle. Examples of health condition and lifestyle include, but are not limited to, data from a wearable device and self-reported data. For example, the storage unit can set a periodic timing for storing information when the user's health condition is good. Furthermore, the storage unit can flexibly adjust the timing for acquiring the stored information when the user's health condition is deteriorating. Furthermore, the storage unit can suggest the optimal timing for acquiring information in accordance with the user's lifestyle. For example, when the user's health condition is good, the storage unit can set a periodic timing for storing information and send a notification. This allows the timing for acquiring information to be adjusted taking into account the user's health condition and lifestyle. Some or all of the above-described processing in the storage unit may be performed using AI, or may be performed without AI. For example, the storage unit can input data on the user's health condition and lifestyle into the generation AI and cause the generation AI to adjust the timing for acquiring information.

[0096] The designation unit can estimate the user's emotion and present options for expression based on the estimated user emotion. Estimating the emotion can be achieved, for example, by using an emotion recognition algorithm or by using a type of data, but is not limited to these examples. The designation unit can, for example, analyze the user's facial expressions or voice data to estimate the emotion. The designation unit can also analyze the user's text data to estimate the emotion. For example, the designation unit can analyze text data entered by the user and calculate an emotion score. The designation unit then presents options for expression based on the estimated emotion. For example, if the user is emotionally calm, formal expressions can be presented as options. If the user is emotionally excited, casual expressions can be presented as options. Furthermore, if the user is emotionally unstable, options expressed in a gentle tone can be presented. This allows options for expression to be presented based on the user's emotion. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit may input the user's facial expression data to the generation AI and cause the generation AI to estimate the emotion.

[0097] At the time of designation, the designation unit can analyze the user's past designation history and suggest the optimal expression method. The designation history includes, for example, past setting data, log data, etc., but is not limited to such examples. For example, the designation unit can analyze the user's past designation history and suggest a similar expression method. The designation unit can also predict and suggest an expression method to be used during a specific time period based on the user's past designation history. Furthermore, the designation unit can customize and suggest the optimal expression method based on the user's past designation history. For example, the designation unit can analyze the user's past designation history and suggest a similar expression method. This allows the user's past designation history to be analyzed and the optimal expression method to be suggested. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without AI. For example, the designation unit can input the user's past designation history data into a generation AI and have the generation AI suggest the optimal expression method.

[0098] The designation unit can customize the expression method based on the user's current mood and situation at the time of designation. The mood and situation include, but are not limited to, survey results, sensor data, and the like. For example, if the user is emotionally calm, the designation unit can customize and suggest a formal expression method. Furthermore, if the user is emotionally excited, the designation unit can customize and suggest a casual expression method. Furthermore, if the user is emotionally unstable, the designation unit can customize and suggest a gentler expression method. For example, if the user is emotionally calm, the designation unit customizes and suggests a formal expression method. This allows the expression method to be customized based on the user's current mood and situation. Some or all of the above-described processing in the designation unit may be performed using AI or without AI. For example, the designation unit can input data on the user's mood and situation into the generation AI and cause the generation AI to customize the expression method.

[0099] When designating a method of expression, the designation unit can select the method of expression reflecting the opinions of the user's family and relatives. Opinions of the family and relatives include, but are not limited to, survey results, interview results, etc. For example, the designation unit selects the method of expression reflecting the preference of the user's family. The designation unit can also select the method of expression reflecting the preference of the user's relatives. Furthermore, the designation unit can select the optimal method of expression based on the opinions of the user's family and relatives. For example, the designation unit selects the method of expression reflecting the preference of the user's family. This allows the selection of the method of expression to reflect the opinions of the user's family and relatives. Some or all of the above-described processing in the designation unit may be performed using AI or may be performed without using AI. For example, the designation unit can input opinion data of the user's family and relatives into the generation AI and cause the generation AI to select the method of expression.

[0100] The designation unit may adjust the expression method by taking into consideration the user's cultural background and religious beliefs. Examples of the cultural background and religious beliefs include, but are not limited to, survey results and self-reported data. The designation unit may select an appropriate expression method based on the user's cultural background. The designation unit may also select an appropriate expression method based on the user's religious beliefs. Furthermore, the designation unit may customize the optimal expression method by taking into consideration the user's cultural background and religious beliefs. For example, the designation unit may select an appropriate expression method based on the user's cultural background. This allows the expression method to be adjusted by taking into consideration the user's cultural background and religious beliefs. Some or all of the above-described processing by the designation unit may be performed using AI or without AI. For example, the designation unit may input data on the user's cultural background and religious beliefs into the generation AI and cause the generation AI to adjust the expression method.

[0101] The designation unit can estimate the user's emotion and set detailed settings for the expression method based on the estimated user's emotion. Estimating the emotion can be achieved, for example, by using an emotion recognition algorithm or by using a type of data, but is not limited to these examples. The designation unit can, for example, analyze the user's facial expression or voice data to estimate the emotion. The designation unit can also analyze the user's text data to estimate the emotion. For example, the designation unit can analyze text data entered by the user and calculate an emotion score. The designation unit then sets detailed settings for the expression method based on the estimated emotion. For example, if the user is emotionally calm, a formal detailed setting can be set. If the user is emotionally excited, a casual detailed setting can be set. Furthermore, if the user is emotionally unstable, a gentle detailed setting can be set. This allows detailed settings for the expression method to be set based on the user's emotion. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit may input the user's facial expression data to the generation AI and cause the generation AI to estimate the emotion.

[0102] The designation unit can propose an optimal expression method by taking into consideration the user's geographical location information at the time of designation. Geographical location information includes, but is not limited to, GPS data, IP address, etc. For example, if the user lives in a specific area, the designation unit can propose an expression method related to that area. Furthermore, if the user is traveling, the designation unit can propose an expression method related to the travel destination. Furthermore, if the user is planning to move, the designation unit can propose an expression method related to the new residence. For example, if the user lives in a specific area, the designation unit proposes an expression method related to that area. This allows the optimal expression method to be proposed by taking into consideration the user's geographical location information. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input the user's geographical location information to the generation AI and cause the generation AI to propose an optimal expression method.

[0103] At the time of designation, the designation unit can analyze the user's social media activity and suggest a relevant expression method. Social media activity includes, but is not limited to, analysis of post content and follower analysis, for example. The designation unit can also analyze the user's social media post content and suggest a relevant expression method. Furthermore, the designation unit can also suggest a relevant expression method by referring to the activity of the user's friends on social media. For example, the designation unit can suggest a relevant expression method based on the information the user shared on social media. In this way, the user's social media activity can be analyzed and a relevant expression method can be suggested. Some or all of the above-described processing in the designation unit may be performed using AI or without AI. For example, the designation unit can input the user's social media activity data into the generation AI and cause the generation AI to suggest a relevant expression method.

[0104] When specifying the expression method, the designation unit can customize the expression method by reflecting the user's past feedback. Examples of feedback include, but are not limited to, survey results and user reviews. The designation unit can improve the expression method based on, for example, feedback previously provided by the user. The designation unit can also customize a specific expression method based on the user's past feedback. Furthermore, the designation unit can analyze the user's past feedback and suggest an optimal expression method. For example, the designation unit can improve the expression method based on the user's past feedback and suggest an expression method that meets the user's needs. This allows the expression method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the expression method.

[0105] The designation unit can adjust the timing of the expression method in consideration of the user's lifestyle rhythm and activity pattern when designating the expression method. Lifestyle rhythm and activity pattern include, but are not limited to, data from a wearable device and self-reported data. For example, if the user is a morning person, the designation unit can suggest an expression method suitable for morning hours. Furthermore, if the user is a night owl, the designation unit can also suggest an expression method suitable for evening hours. Furthermore, the designation unit can adjust the optimal timing of the expression method based on the user's activity pattern. For example, if the user is a morning person, the designation unit can suggest an expression method suitable for morning hours. This allows the timing of the expression method to be adjusted in consideration of the user's lifestyle rhythm and activity pattern. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input data on the user's lifestyle rhythm and activity pattern to the generation AI and cause the generation AI to adjust the timing of the expression method.

[0106] The generation unit can estimate the user's emotions and adjust the appearance and voice of the AI ​​robot based on the estimated user emotions. Estimating emotions can be achieved, for example, by using an emotion recognition algorithm and by using different types of data, but is not limited to these examples. The generation unit can, for example, analyze the user's facial expressions and voice data to estimate emotions. The generation unit can also analyze the user's text data to estimate emotions. For example, the generation unit can analyze text data entered by the user and calculate an emotion score. The generation unit can then adjust the appearance and voice of the AI ​​robot based on the estimated emotions. For example, if the user is emotionally calm, the generation unit can generate an AI robot with a formal appearance and voice. If the user is emotionally excited, the generation unit can generate an AI robot with a casual appearance and voice. Furthermore, if the user is emotionally unstable, the generation unit can generate an AI robot with an appearance and voice expressed in a gentle tone. This allows the appearance and voice of the AI ​​robot to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0107] During generation, the generation unit can analyze the user's past generation history and select the optimal generation method. The generation history includes, but is not limited to, past generation data and log data. For example, the generation unit can analyze the appearance and voice of AI robots previously generated by the user and generate an AI robot with similar characteristics. The generation unit can also analyze the user's tendency to generate AI robots during specific time periods based on the user's past generation history and prompt the user to generate an AI robot during those time periods. Furthermore, the generation unit can customize and suggest the optimal generation method based on the user's past generation history. For example, the generation unit can analyze the appearance and voice of AI robots previously generated by the user and generate an AI robot with similar characteristics. This allows the user's past generation history to be analyzed and the optimal generation method selected. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without AI. For example, the generation unit can input the user's past generation history data into the generation AI and have the generation AI select the optimal generation method.

[0108] The generation unit can customize the characteristics of the AI ​​robot based on the user's current mood and situation at the time of generation. Moods and situations include, but are not limited to, survey results, sensor data, etc. For example, if the user is emotionally calm, the generation unit can generate an AI robot with formal characteristics. Furthermore, if the user is emotionally excited, the generation unit can generate an AI robot with casual characteristics. Furthermore, if the user is emotionally unstable, the generation unit can generate an AI robot with characteristics expressed in a gentle tone. For example, if the user is emotionally calm, the generation unit can generate an AI robot with formal characteristics. This allows the characteristics of the AI ​​robot to be customized based on the user's current mood and situation. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input data on the user's mood and situation into the generation AI and cause the generation AI to customize the characteristics of the AI ​​robot.

[0109] The generation unit can generate an AI robot by reflecting the opinions of the user's family and relatives. Opinions of the family and relatives include, but are not limited to, survey results and interview results. For example, the generation unit can generate an AI robot with the appearance and voice desired by the user's family. The generation unit can also generate an AI robot with characteristics desired by the user's relatives. Furthermore, the generation unit can generate an optimal AI robot based on the opinions of the user's family and relatives. For example, the generation unit can generate an AI robot with the appearance and voice desired by the user's family. This allows the AI ​​robot to be generated while reflecting the opinions of the user's family and relatives. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input opinion data of the user's family and relatives into the generation AI and cause the generation AI to generate the AI ​​robot.

[0110] The generation unit can adjust the AI ​​robot during generation, taking into account the user's cultural background and religious beliefs. Examples of cultural background and religious beliefs include, but are not limited to, survey results and self-reported data. For example, the generation unit generates an AI robot with an appropriate appearance and voice based on the user's cultural background. The generation unit can also generate an AI robot with appropriate characteristics based on the user's religious beliefs. Furthermore, the generation unit can customize an optimal AI robot by taking into account the user's cultural background and religious beliefs. For example, the generation unit generates an AI robot with an appropriate appearance and voice based on the user's cultural background. This allows the AI ​​robot to be adjusted taking into account the user's cultural background and religious beliefs. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input data on the user's cultural background and religious beliefs into the generation AI and have the generation AI adjust the AI ​​robot.

[0111] The generation unit can estimate the user's emotions and adjust the behavior and expression of the AI ​​robot based on the estimated user emotions. Estimating emotions can be achieved, for example, by using an emotion recognition algorithm and the type of data, but is not limited to these examples. The generation unit can, for example, analyze the user's facial expressions and voice data to estimate emotions. The generation unit can also analyze the user's text data to estimate emotions. For example, the generation unit can analyze text data entered by the user and calculate an emotion score. The generation unit can then adjust the AI ​​robot's behavior and expression based on the estimated emotions. For example, if the user is emotionally calm, the generation unit can generate an AI robot with formal behavior and expression. If the user is emotionally excited, the generation unit can generate an AI robot with casual behavior and expression. Furthermore, if the user is emotionally unstable, the generation unit can generate an AI robot with behavior and expression expressed in a gentle tone. This allows the AI ​​robot's behavior and expression to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0112] The generation unit can generate an optimal AI robot by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user lives in a specific area, the generation unit can generate an AI robot with characteristics related to that area. Furthermore, if the user is traveling, the generation unit can generate an AI robot with characteristics related to the travel destination. Furthermore, if the user is planning to move, the generation unit can generate an AI robot with characteristics related to the new residence. For example, if the user lives in a specific area, the generation unit can generate an AI robot with characteristics related to that area. This allows the generation of an optimal AI robot by taking into account the user's geographical location information. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's geographical location information into the generation AI and cause the generation AI to generate an optimal AI robot.

[0113] During generation, the generation unit can analyze the user's social media activities and generate a related AI robot. Social media activities include, but are not limited to, analysis of posted content and follower analysis. For example, the generation unit can generate an AI robot with related characteristics based on information shared by the user on social media. The generation unit can also analyze the user's social media posts and generate an AI robot with related characteristics. Furthermore, the generation unit can generate an AI robot with related characteristics based on the activities of the user's friends on social media. For example, the generation unit generates an AI robot with related characteristics based on information shared by the user on social media. In this way, the user's social media activities can be analyzed to generate a related AI robot. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's social media activity data into the generation AI and cause the generation AI to generate a related AI robot.

[0114] The generation unit can customize the AI ​​robot by reflecting the user's past feedback during generation. Examples of feedback include, but are not limited to, survey results and user reviews. The generation unit can improve the AI ​​robot based on, for example, feedback previously provided by the user. The generation unit can also customize an AI robot with specific characteristics based on the user's past feedback. Furthermore, the generation unit can analyze the user's past feedback and propose an optimal AI robot. For example, the generation unit can improve the AI ​​robot based on the user's past feedback and propose an AI robot tailored to the user's needs. This allows the AI ​​robot to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's past feedback data into the generation AI and have the generation AI customize the AI ​​robot.

[0115] During generation, the generation unit can adjust the operation timing of the AI ​​robot taking into account the user's lifestyle rhythm and activity pattern. Lifestyle rhythms and activity patterns include, but are not limited to, data from wearable devices and self-reported data. For example, if the user is a morning person, the generation unit can generate an AI robot with operation timings suitable for morning hours. Furthermore, if the user is a night owl, the generation unit can generate an AI robot with operation timings suitable for evening hours. Furthermore, the generation unit can generate an AI robot with optimal operation timings based on the user's activity pattern. For example, if the user is a morning person, the generation unit can generate an AI robot with operation timings suitable for morning hours. This allows the operation timing of the AI ​​robot to be adjusted taking into account the user's lifestyle rhythm and activity pattern. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input data on the user's lifestyle rhythm and activity pattern into the generation AI and cause the generation AI to adjust the operation timing of the AI ​​robot.

[0116] The dialogue unit can estimate the user's emotions and adjust the content and tone of the dialogue based on the estimated user emotions. Estimating emotions can be achieved, for example, by using an emotion recognition algorithm or by using a type of data, but is not limited to these examples. The dialogue unit can, for example, analyze the user's facial expressions or voice data to estimate emotions. The dialogue unit can also analyze the user's text data to estimate emotions. For example, the dialogue unit can analyze text data entered by the user and calculate an emotion score. Furthermore, the dialogue unit can adjust the content and tone of the dialogue based on the estimated emotions. For example, if the user is emotionally calm, the dialogue can be conducted in a formal tone. Also, if the user is emotionally excited, the dialogue can be conducted in a casual tone. Furthermore, if the user is emotionally unstable, the dialogue can be conducted in a gentle tone. This allows the content and tone of the dialogue to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processes in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit may input the user's facial expression data to the generation AI and have the generation AI estimate the user's emotions.

[0117] During a dialogue, the dialogue unit can analyze the user's past dialogue history and select an optimal dialogue method. The dialogue history includes, but is not limited to, past dialogue data and log data. For example, the dialogue unit can analyze a dialogue method that the user previously preferred and conduct the dialogue in a similar manner. The dialogue unit can also predict and suggest a dialogue method to be used at a specific time period based on the user's past dialogue history. Furthermore, the dialogue unit can customize and suggest an optimal dialogue method based on the user's past dialogue history. For example, the dialogue unit can analyze a dialogue method that the user previously preferred and conduct the dialogue in a similar manner. This allows the user's past dialogue history to be analyzed and the optimal dialogue method to be selected. Some or all of the above-described processing in the dialogue unit may be performed using AI or without AI. For example, the dialogue unit can input the user's past dialogue history data into a generation AI and cause the generation AI to select an optimal dialogue method.

[0118] The dialogue unit can customize the dialogue content based on the user's current mood and situation during the dialogue. Mood and situation include, but are not limited to, survey results, sensor data, and the like. For example, if the user is emotionally calm, the dialogue unit can conduct the dialogue in a formal manner. Furthermore, if the user is emotionally excited, the dialogue unit can conduct the dialogue in a casual manner. Furthermore, if the user is emotionally unstable, the dialogue unit can conduct the dialogue in a gentler tone. For example, if the user is emotionally calm, the dialogue unit can conduct the dialogue in a formal manner. This allows the dialogue content to be customized based on the user's current mood and situation. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input data on the user's mood and situation into the generation AI and have the generation AI customize the dialogue content.

[0119] During a dialogue, the dialogue unit can select dialogue content that reflects the opinions of the user's family and relatives. Opinions of the family and relatives include, but are not limited to, survey results, interview results, etc. The dialogue unit, for example, selects dialogue content that reflects the dialogue content desired by the user's family. The dialogue unit can also select dialogue content that reflects the dialogue content desired by the user's relatives. Furthermore, the dialogue unit can select optimal dialogue content based on the opinions of the user's family and relatives. For example, the dialogue unit selects dialogue content that reflects the dialogue content desired by the user's family. This allows the dialogue content to be selected that reflects the opinions of the user's family and relatives. Some or all of the above-described processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input opinion data of the user's family and relatives into the generation AI and cause the generation AI to select the dialogue content.

[0120] During a dialogue, the dialogue unit can adjust the dialogue content taking into account the user's cultural background and religious beliefs. Examples of cultural background and religious beliefs include, but are not limited to, survey results and self-reported data. The dialogue unit, for example, selects appropriate dialogue content based on the user's cultural background. The dialogue unit can also select appropriate dialogue content based on the user's religious beliefs. Furthermore, the dialogue unit can customize optimal dialogue content taking into account the user's cultural background and religious beliefs. For example, the dialogue unit selects appropriate dialogue content based on the user's cultural background. This allows the dialogue content to be adjusted taking into account the user's cultural background and religious beliefs. Some or all of the above-described processing in the dialogue unit may be performed using AI or without AI. For example, the dialogue unit can input data on the user's cultural background and religious beliefs into the generation AI and cause the generation AI to adjust the dialogue content.

[0121] The dialogue unit can estimate the user's emotions and adjust the dialogue progression method based on the estimated user emotions. Estimating emotions can be achieved, for example, by using an emotion recognition algorithm or by using a type of data, but is not limited to these examples. The dialogue unit can, for example, analyze the user's facial expressions or voice data to estimate emotions. The dialogue unit can also analyze the user's text data to estimate emotions. For example, the dialogue unit can analyze text data entered by the user and calculate an emotion score. Furthermore, the dialogue unit can adjust the dialogue progression method based on the estimated emotions. For example, if the user is emotionally calm, the dialogue can be conducted in a formal progression method. On the other hand, if the user is emotionally excited, the dialogue can be conducted in a casual progression method. Furthermore, if the user is emotionally unstable, the dialogue can be conducted in a gentler tone. This allows the dialogue progression method to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processes in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit may input the user's facial expression data to the generation AI and have the generation AI estimate the user's emotions.

[0122] The dialogue unit can provide optimal dialogue content during dialogue by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user lives in a specific area, the dialogue unit can provide dialogue content related to that area. Furthermore, if the user is traveling, the dialogue unit can provide dialogue content related to the user's travel destination. Furthermore, if the user is planning to move, the dialogue unit can provide dialogue content related to the user's new residence. For example, if the user lives in a specific area, the dialogue unit provides dialogue content related to that area. This allows optimal dialogue content to be provided by taking into account the user's geographical location information. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the user's geographical location information into a generation AI and cause the generation AI to provide optimal dialogue content.

[0123] The dialogue unit can analyze the user's social media activity during the dialogue and provide related dialogue content. Social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the dialogue unit can provide related dialogue content based on information shared by the user on social media. The dialogue unit can also analyze the user's social media posts and provide related dialogue content. Furthermore, the dialogue unit can provide related dialogue content by referring to the activities of the user's friends on social media. For example, the dialogue unit can provide related dialogue content based on information shared by the user on social media. In this way, the user's social media activity can be analyzed and related dialogue content can be provided. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or without AI. For example, the dialogue unit can input the user's social media activity data into a generation AI and cause the generation AI to provide related dialogue content.

[0124] The dialogue unit can customize the dialogue method by reflecting the user's past feedback during dialogue. Examples of feedback include, but are not limited to, survey results and user reviews. The dialogue unit can improve the dialogue method based on, for example, feedback provided by the user in the past. The dialogue unit can also customize a specific dialogue method based on the user's past feedback. Furthermore, the dialogue unit can analyze the user's past feedback and suggest an optimal dialogue method. For example, the dialogue unit can improve the dialogue method and suggest a dialogue method tailored to the user's needs based on the user's past feedback. This allows the dialogue method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the user's past feedback data into a generation AI and have the generation AI customize the dialogue method.

[0125] During the dialogue, the dialogue unit can adjust the dialogue timing taking into account the user's lifestyle rhythm and activity pattern. Lifestyle rhythms and activity patterns include, but are not limited to, wearable device data and self-reported data. For example, if the user is a morning person, the dialogue unit can provide a dialogue timing suitable for the morning hours. Furthermore, if the user is a night owl, the dialogue unit can also provide a dialogue timing suitable for the evening hours. Furthermore, the dialogue unit can also suggest an optimal dialogue timing based on the user's activity pattern. For example, if the user is a morning person, the dialogue unit can provide a dialogue timing suitable for the morning hours. This allows the dialogue timing to be adjusted taking into account the user's lifestyle rhythm and activity pattern. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input data on the user's lifestyle rhythm and activity pattern into the generation AI and cause the generation AI to adjust the dialogue timing. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned stock unit, designation unit, generation unit, and dialogue unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the stock unit can save information in the storage 50 of the smart device 14 and back up the information in the database 24 of the data processing device 12. The designation unit accepts a user's designation via the control unit 46A of the smart device 14 and determines the expression method via the specific processing unit 290 of the data processing device 12. The generation unit generates an AI robot via the specific processing unit 290 of the data processing device 12 and generates an appearance and voice that resembles the user via the processor 46 of the smart device 14. The dialogue unit conducts a dialogue via the control unit 46A of the smart device 14 and adjusts the content of the dialogue via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned stock unit, designation unit, generation unit, and dialogue unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the stock unit can store information in the storage 50 of the smart glasses 214 and back up the information in the database 24 of the data processing device 12. The designation unit accepts a user's designation via the control unit 46A of the smart glasses 214 and determines the expression method via the specific processing unit 290 of the data processing device 12. The generation unit generates an AI robot via the specific processing unit 290 of the data processing device 12 and generates an appearance and voice that resembles the user via the processor 46 of the smart glasses 214. The dialogue unit conducts a dialogue via the control unit 46A of the smart glasses 214 and adjusts the content of the dialogue via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned stock unit, designation unit, generation unit, and dialogue unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the stock unit can save information in the storage 50 of the headset type terminal 314 and back up the information in the database 24 of the data processing device 12. The designation unit receives a user's designation via the control unit 46A of the headset type terminal 314, and determines the expression method via the specific processing unit 290 of the data processing device 12. The generation unit generates an AI robot via the specific processing unit 290 of the data processing device 12, and generates an appearance and voice that resembles the user via the processor 46 of the headset type terminal 314. The dialogue unit conducts a dialogue via the control unit 46A of the headset type terminal 314, and adjusts the content of the dialogue via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned stock unit, designation unit, generation unit, and dialogue unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the stock unit can save information in the storage 50 of the robot 414 and back up the information in the database 24 of the data processing device 12. The designation unit receives a user's designation via the control unit 46A of the robot 414, and determines the expression method via the specific processing unit 290 of the data processing device 12. The generation unit generates an AI robot via the specific processing unit 290 of the data processing device 12, and generates an appearance and voice that resembles the user via the processor 46 of the robot 414. The dialogue unit conducts a dialogue via the control unit 46A of the robot 414, and adjusts the content of the dialogue via the specific processing unit 290 of the data processing device 12.

[0126] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0127] The stock unit can analyze a user's preferences and interests based on the information stored by the user and suggest new related information. For example, if a user has a large collection of movies in a particular genre, the stock unit can suggest new movies related to that genre. If a user has a large collection of books by a particular author, the stock unit can suggest new releases by that author or books by related authors. Furthermore, if a user has a large collection of information related to a particular hobby, the stock unit can suggest events and news related to that hobby. This improves the user's experience by suggesting new information based on the user's preferences and interests. Some or all of the above-described processing in the stock unit may be performed using AI, or may be performed without AI. For example, the stock unit can input the user's stock data into a generation AI and have the generation AI suggest new related information.

[0128] The designation unit may have a function for sharing information with other users based on the expression method specified by the user. For example, if a user wants to share specific photos or videos with family or friends, the designation unit may select the information and generate a sharing link. Also, if a user wants to share a specific letter or diary entry, the designation unit may digitize the information and generate a sharing link. Furthermore, if a user wants to share information about a specific hobby or interest, the designation unit may select the information and post it to a related community or forum. This allows information to be shared with other users based on the expression method specified by the user. Some or all of the above-described processing in the designation unit may be performed using AI, or may be performed without AI. For example, the designation unit may input the user's designated data into a generation AI and cause the generation AI to generate a sharing link.

[0129] The generation unit can estimate the user's emotions and adjust the dialogue scenario of the AI ​​robot based on the estimated user's emotions. For example, if the user is emotionally calm, the generation unit can set a formal dialogue scenario. Furthermore, if the user is emotionally excited, the generation unit can set a casual dialogue scenario. Furthermore, if the user is emotionally unstable, the generation unit can set a dialogue scenario expressed in a gentle tone. By adjusting the dialogue scenario of the AI ​​robot based on the user's emotions, more appropriate dialogue can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without AI. For example, the generation unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0130] The dialogue unit can estimate the user's emotions and adjust the content and tone of the dialogue based on the estimated user's emotions. For example, if the user is emotionally calm, the dialogue unit can use a formal tone. If the user is emotionally excited, the dialogue unit can use a casual tone. Furthermore, if the user is emotionally unstable, the dialogue unit can use a gentle tone. By adjusting the content and tone of the dialogue based on the user's emotions, a more appropriate dialogue can be provided. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without AI. For example, the dialogue unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0131] The storage unit can estimate the user's emotions and prioritize the information to be saved based on the estimated user emotions. For example, if the user is emotionally calm, important information (e.g., letters and diaries) can be prioritized for storage. Also, if the user is emotionally excited, light content (e.g., favorite TV shows and movies) can be prioritized for storage. Furthermore, if the user is emotionally unstable, words of gratitude and encouraging messages can be prioritized for storage. By prioritizing information based on the user's emotions, more appropriate information can be saved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit can be performed using AI, or without AI. For example, the storage unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0132] The stock unit can analyze the user's past stock history and select the optimal stock method. For example, it analyzes the types of information the user frequently stocked in the past and prioritizes stocking similar information. It can also analyze the format of information the user previously stocked (text, images, videos, etc.) and stock it in the optimal format. Furthermore, it can analyze the user's tendency to stock at specific time periods based on the user's past stock history and encourage stocking at those time periods. For example, it can analyze the information the user previously stocked at specific time periods and send a notification encouraging stocking at those time periods. In this way, the optimal stock method can be selected by analyzing the user's past stock history. Some or all of the above-mentioned processing in the stock unit may be performed using AI, or may be performed without AI. For example, the stock unit can input the user's past stock history data into a generation AI and have the generation AI select the optimal stock method.

[0133] The designation unit can analyze the user's past designation history and suggest the optimal expression method. For example, it can analyze the expression methods selected by the user in the past and suggest similar expression methods. It can also predict and suggest the expression method to be used during a specific time period from the user's past designation history. It can also customize and suggest the optimal expression method based on the user's past designation history. For example, it can analyze the expression methods selected by the user in the past and suggest similar expression methods. In this way, it is possible to analyze the user's past designation history and suggest the optimal expression method. Some or all of the above-mentioned processing in the designation unit may be performed using AI, or may be performed without using AI. For example, the designation unit can input the user's past designation history data into a generation AI and have the generation AI suggest the optimal expression method.

[0134] The generation unit can analyze the user's past generation history and select the optimal generation method. For example, it can analyze the appearance and voice of AI robots generated by the user in the past and generate an AI robot with similar characteristics. It can also analyze the user's past generation history to determine a tendency to generate AI robots at specific times of the day and encourage generation at those times. It can also customize and suggest the optimal generation method based on the user's past generation history. For example, it can analyze the appearance and voice of AI robots generated by the user in the past and generate an AI robot with similar characteristics. This allows the user's past generation history to be analyzed and the optimal generation method to be selected. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the user's past generation history data into the generation AI and have the generation AI select the optimal generation method.

[0135] The dialogue unit can analyze the user's past dialogue history and select the optimal dialogue method. For example, it analyzes the dialogue methods that the user has previously preferred and conducts dialogue in a similar manner. It can also predict and suggest a dialogue method to be used at a specific time period from the user's past dialogue history. It can also customize and suggest an optimal dialogue method based on the user's past dialogue history. For example, it analyzes the dialogue methods that the user has previously preferred and conducts dialogue in a similar manner. In this way, it is possible to analyze the user's past dialogue history and select the optimal dialogue method. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the user's past dialogue history data into a generation AI and have the generation AI select the optimal dialogue method.

[0136] The dialogue unit can estimate the user's emotions and adjust the dialogue progression method based on the estimated user emotions. For example, if the user is emotionally calm, the dialogue can be conducted in a formal manner. Furthermore, if the user is emotionally excited, the dialogue can be conducted in a casual manner. Furthermore, if the user is emotionally unstable, the dialogue can be conducted in a gentler tone. By adjusting the dialogue progression method based on the user's emotions, a more appropriate dialogue can be provided. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the dialogue unit may be performed using AI, or may be performed without AI. For example, the dialogue unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0137] The processing flow of the second embodiment will be briefly explained below.

[0138] Step 1: The Stock section stores information such as photos, videos, favorite TV shows, books, magazines, movies, hobbies, favorite things, favorite sayings, letters, diaries, maternal and child health handbooks, medicine records, children's artwork, words of gratitude, and insider stories. For example, the Stock section has a function that allows users to upload photos and videos of family memories. The Stock section can also digitize and store letters and diaries. Step 2: The specification unit specifies how the information stored by the storage unit is to be expressed. For example, if the specification unit is to play only audio, it can record the user's voice. If the specification unit is to play only text, it can save letters or diaries written by the user as text data. If the specification unit is to play with background music, it can play the user's favorite music in the background. Step 3: The generator generates an AI robot based on the expression method specified by the specification unit. For example, the generator can generate the user's appearance and voice using AI to resemble the user. The generator generates the user's appearance and voice using text generation AI (e.g., LLM) or multimodal generation AI. Step 4: The dialogue unit engages in dialogue using the AI ​​robot generated by the generation unit. For example, the dialogue unit can converse with an AI robot that reproduces the voice and appearance of the deceased. The dialogue unit can also converse in text chat format while reading letters or diaries written by the deceased.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0143] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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 identification processing unit 290 using these models.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0175] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification 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 the same process as the identification processing unit 290 using these models.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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).

[0196] 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.

[0197] 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."

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Explanation of symbols]

[0211] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A stock department that stores information, a designation unit that designates a representation method of the information stored by the storage unit; a generation unit that generates an AI robot based on the expression method designated by the designation unit; a dialogue unit that conducts dialogue using the AI ​​robot generated by the generation unit; Equipped with A system characterized by:

2. The stock unit includes: Users have the ability to upload images and videos 2. The system of claim 1.

3. The designation unit Has the ability to input user-specified expressions 2. The system of claim 1.

4. The generation unit Create an AI robot based on a specified expression method 2. The system of claim 1.

5. The dialogue unit Conduct conversations using the created AI robot 2. The system of claim 1.

6. The stock unit includes: A storage unit for storing stored information is provided.

2. The system of claim 1.

7. The designation unit Equipped with a section for managing the specified expression method 2. The system of claim 1.

8. The generation unit It will have a department to manage the created AI robots.

2. The system of claim 1.

Images