system

Abstract

The system according to the embodiment aims to learn and mimic an individual's language patterns and personality. According to an embodiment, the system includes a recording unit, an analysis unit, and an update unit. The recording unit records an individual's conversations. The analysis unit analyzes the data recorded by the recording unit and includes specific algorithms for learning language patterns and personalities. The update unit updates the model based on the results learned by the analysis unit.

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 have had the problem of making it difficult to accurately learn and imitate an individual's language patterns and personality.

[0005] The system according to the embodiment aims to learn and mimic an individual's language patterns and personality. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, an analysis unit, and an update unit. The recording unit records an individual's conversations. The analysis unit analyzes the data recorded by the recording unit and includes specific algorithms for learning language patterns and personalities. The update unit updates the model based on the results learned by the analysis unit. [Effects of the Invention]

[0007] Embodiments of the system can learn and mimic an individual's language patterns and personality. [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 imitation model generation system according to an embodiment of the present invention records an individual's conversations and uses AI to learn the individual's language patterns and personality, thereby creating a model that mimics that individual. This imitation model generation system records the individual's conversations, analyzes the recorded data, and learns the individual's language patterns and personality. Furthermore, the system updates the model based on the learning results to improve accuracy. Even after a person's death, family and friends can relive conversations with the deceased by having the AI ​​respond as if they were the deceased. A more realistic experience can be achieved by using home 3D holograms and virtual graves. For example, the imitation model generation system records an individual's conversations. Detailed data, such as the content, tone, and frequency of the conversations, is collected. For example, everyday conversations and comments made at specific events are recorded. This allows the individual's language patterns and personality to be understood. Next, the imitation model generation system uses AI to analyze the recorded data. The AI ​​analyzes the collected data and learns the individual's language patterns and personality. For example, it analyzes the use of specific words and speaking characteristics. This allows the individual's characteristics to be accurately captured. Furthermore, the imitation model generation system updates the model based on the learning results to improve accuracy. The AI ​​continuously analyzes new data and updates the model, thereby maintaining a model that always reflects the latest information. Even after death, the imitation model generation system allows family and friends to relive conversations with the deceased by having the AI ​​respond as if they were the deceased. For example, an AI that reproduces the deceased's voice and speaking style can converse with family and friends, allowing them to share memories with the deceased. A more realistic experience can be achieved by using home 3D holograms and virtual graves. For example, the deceased's appearance can be recreated in 3D hologram form, allowing family and friends to interact with them. Furthermore, using a virtual grave can provide a place to remember the deceased. This allows the imitation model generation system to automatically record and analyze an individual's conversations and update the model to create a model that imitates that person.

[0029] An imitation model generation system according to an embodiment includes a recording unit, an analysis unit, and an update unit. The recording unit records personal conversations. Personal conversations include, but are not limited to, everyday conversations, business conversations, and online chats. The recording unit records conversations in the form of, for example, audio recording, text recording, or audio recording. The recording unit can also collect detailed data on the content, tone, and frequency of the conversations. For example, the recording unit can evaluate the tone of the conversation based on criteria such as emotional expression, voice pitch, and strength. The analysis unit analyzes the data recorded by the recording unit to learn language patterns and personality traits. The analysis unit can analyze, for example, the usage of specific words and speaking characteristics. For example, the analysis unit can analyze language patterns based on criteria such as frequently used phrases, grammatical structures, and vocabulary frequency. The analysis unit can also evaluate personality traits based on criteria such as personality traits, behavioral patterns, and psychological characteristics. The update unit updates the model based on the results learned by the analysis unit. For example, the update unit can continuously analyze new data and update the model. The update unit can update the model at a frequency or timing such as in real time, periodically, event-driven, etc. As a result, the imitation model generation system according to the embodiment can automatically record and analyze an individual's conversation and update the model to create a model that imitates that person.

[0030] The update unit can continuously analyze new data and update the model. For example, the update unit analyzes new data in real time and updates the model. For example, the update unit collects personal conversation data in real time and updates the model based on that data. The update unit can also periodically analyze new data and update the model. For example, the update unit analyzes data and updates the model on a regular schedule, such as daily, weekly, or monthly. The update unit can also analyze new data and update the model in an event-driven manner. For example, when a specific event occurs, data related to the event is analyzed and the model is updated. In this way, by continuously analyzing new data and updating the model, it is possible to maintain a model that always reflects the latest information. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input data collected in real time to a generation AI, which then analyzes the data and updates the model.

[0031] The analysis unit can analyze the usage of specific words and characteristics of speaking style. The analysis unit, for example, analyzes the usage of specific words. For example, the analysis unit analyzes the usage of specific words based on criteria such as frequency, context, and usage situation. The analysis unit can also analyze speaking style characteristics. For example, the analysis unit analyzes speaking style characteristics based on criteria such as tone of voice, speaking speed, and intonation. In this way, by analyzing the usage of specific words and speaking style characteristics, it is possible to accurately capture the characteristics of an individual. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the usage of specific words and speaking style characteristics into a generation AI, and the generation AI can analyze the data.

[0032] The recording unit can collect detailed data on the content, tone, and frequency of conversations. The recording unit, for example, collects the content of the conversations. For example, the recording unit collects text data of the conversations and records the content. The recording unit can also collect the tone of the conversations. For example, the recording unit evaluates and records the tone of the conversations based on criteria such as emotional expression, pitch, and strength. The recording unit can also collect the frequency of conversations. For example, the recording unit measures and records the frequency of conversations based on criteria such as time units, number of times, and occurrence rate. By collecting detailed data such as the content, tone, and frequency of conversations, it is possible to understand an individual's language patterns and personality. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input data on the content, tone, and frequency of conversations to a generation AI, which then collects the data.

[0033] The imitation model generation system includes a hologram unit that generates a home 3D hologram. The hologram unit generates the home 3D hologram. Home 3D holograms include, for example, technology for displaying a three-dimensional image using a high-resolution display device. The hologram unit generates the 3D hologram based on specifications such as resolution, display device, and generation method. For example, the hologram unit displays a three-dimensional image using a high-resolution projector. The hologram unit can also generate a 3D model using specific software and display the model. This allows for a more realistic experience by generating a home 3D hologram. Some or all of the above-described processing in the hologram unit may be performed using, for example, AI, or may be performed without AI. For example, the hologram unit can input the generation of the 3D model to a generation AI, which then generates the 3D model.

[0034] The imitation model generation system includes a virtual grave unit that provides a virtual grave. The virtual grave unit provides the virtual grave. The virtual grave includes, for example, a virtual space for remembering the deceased. The virtual grave unit provides the virtual grave based on specifications such as display content, access method, and interaction functions. For example, the virtual grave unit provides a virtual space that displays photos and messages of the deceased. The virtual grave unit can also provide an interaction function for family and friends to remember the deceased in the virtual space. In this way, by providing the virtual grave, a place to remember the deceased can be provided. Some or all of the above-mentioned processing in the virtual grave unit may be performed, for example, using AI, or may be performed without using AI. For example, the virtual grave unit can input the generation of the virtual space into a generation AI, and the generation AI can generate the virtual space.

[0035] The recording unit can analyze the user's past conversation history and select an appropriate recording method. The recording unit, for example, prioritizes recording important conversations based on patterns of frequent conversations the user has had in the past. For example, the recording unit can analyze past conversation data and identify frequently occurring topics and phrases. The recording unit can also analyze conversations the user has during a specific time period and concentrate recording on that time period. For example, the recording unit can classify past conversation data by time and identify that many conversations occur during that time period. The recording unit can also prioritize recording conversations related to specific topics from the user's past conversation history. For example, the recording unit can classify past conversation data by topic and prioritize recording conversations related to specific topics. This allows the optimal recording method to be selected by analyzing the user's past conversation history. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without AI. For example, the recording unit can input past conversation data into a generation AI, which analyzes the data and selects an appropriate recording method.

[0036] When recording a conversation, the recording unit can filter the conversation based on the user's current activity status and areas of interest. For example, if the user is at work, the recording unit records only work-related conversations. For example, the recording unit can analyze the user's calendar and task management data to identify the user's current work content. Furthermore, if the user is engaged in a hobby, the recording unit can prioritize recording conversations related to the hobby. For example, the recording unit can analyze the user's social media and search history to identify the user's current areas of interest. Furthermore, if the user is spending time with family, the recording unit can prioritize recording conversations related to the family. For example, the recording unit can analyze the user's location information and communication history to identify the user's current activity status. This allows for filtering based on the user's current activity status and areas of interest to record highly relevant conversations. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input data on the user's activity status and areas of interest into a generation AI, which can analyze the data and perform filtering.

[0037] When recording a conversation, the recording unit can prioritize recording highly relevant conversations by taking into account the user's geographical location information. For example, when the user is traveling, the recording unit prioritizes recording conversations related to the travel destination. For example, the recording unit analyzes the user's GPS data to identify the user's current location. Furthermore, when the user is at home, the recording unit can prioritize recording conversations related to the home. For example, the recording unit uses the user's location information service to identify the user's current location. Furthermore, when the user is at work, the recording unit can prioritize recording conversations related to work. For example, the recording unit analyzes the user's map data to identify the current location of activities. Thus, by prioritizing recording highly relevant conversations by taking into account the user's geographical location information, important conversations are not missed. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's geographical location information to a generation AI, which analyzes the data and prioritizes recording highly relevant conversations.

[0038] When recording a conversation, the recording unit can analyze the user's social media activity and record related conversations. For example, the recording unit prioritizes recording conversations related to topics the user is talking about on social media. For example, the recording unit can analyze the user's posts and comments to identify current topics of interest. The recording unit can also prioritize recording conversations with people the user follows on social media. For example, the recording unit can analyze the user's follow data to identify important people. The recording unit can also prioritize recording conversations related to groups the user participates in on social media. For example, the recording unit can analyze the user's group participation data to identify related conversations. In this way, related conversations can be recorded by analyzing the user's social media activity. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's social media activity data into a generation AI, which can analyze the data and record related conversations.

[0039] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the conversation. For example, in the case of an important conversation, the analysis unit performs a detailed analysis of language patterns. For example, the analysis unit performs a detailed analysis based on the content of the conversation and the importance of the people involved. The analysis unit can also perform a simplified analysis of language patterns in the case of everyday conversations. For example, the analysis unit performs a simplified analysis based on the frequency of the conversation and general content. The analysis unit can also perform an analysis of language patterns specialized for a conversation related to a specific event. For example, the analysis unit performs a specialized analysis based on the content of the event and related data. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the conversation. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation importance data to a generation AI, which analyzes the data and adjusts the level of detail of the analysis.

[0040] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit applies a business analysis algorithm to business-related conversations. For example, the analysis unit performs business analysis based on business documents and meeting minutes. The analysis unit can also apply a home analysis algorithm to domestic conversations. For example, the analysis unit performs home analysis based on domestic conversation data. The analysis unit can also apply a hobby analysis algorithm to conversations about hobbies. For example, the analysis unit performs hobby analysis based on conversation data related to hobbies. This allows for more appropriate analysis by applying different analysis algorithms depending on the category of the conversation. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation category data to a generation AI, which analyzes the data and applies different analysis algorithms.

[0041] During analysis, the analysis unit can determine the priority of analysis based on the time when the conversation was submitted. For example, the analysis unit prioritizes analysis of recent conversations. For example, the analysis unit prioritizes the latest data based on the date and time when the conversation was submitted. The analysis unit can also prioritize analysis of conversations that occur immediately after a specific event. For example, the analysis unit prioritizes conversations that occur immediately after an event based on the date and time when the event occurred. The analysis unit can also prioritize analysis of conversations that occur immediately after a user expresses a specific emotion. For example, the analysis unit detects a change in emotion and prioritizes conversations that occur immediately after that change. In this way, by determining the priority of analysis based on the time when the conversation was submitted, the latest information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time when the conversation was submitted to a generation AI, which analyzes the data and determines the priority of analysis.

[0042] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversations. For example, the analysis unit prioritizes analysis of conversations related to a specific topic. For example, the analysis unit analyzes conversation topic data to identify highly relevant topics. The analysis unit can also prioritize analysis of conversations related to the user's areas of interest. For example, the analysis unit analyzes the user's social media or search history to identify current areas of interest. The analysis unit can also prioritize analysis of highly relevant conversations based on the user's past conversation history. For example, the analysis unit analyzes past conversation data to identify highly relevant conversations. This allows the analysis order to be adjusted based on the relevance of the conversations, thereby prioritizing analysis of highly relevant conversations. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input conversation relevance data to a generation AI, which analyzes the data and adjusts the order of analysis.

[0043] During updating, the update unit can optimize the model update algorithm by referring to past learning data. The update unit, for example, selects an optimal update algorithm based on past learning data. For example, the update unit analyzes past learning data and identifies an effective update pattern. The update unit can also apply an update algorithm to improve the accuracy of the model from the past learning data. For example, the update unit optimizes parameter adjustment and feedback loops based on past data. This allows the optimal update algorithm to be applied by referring to the past learning data. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input past learning data to a generation AI, which analyzes the data and optimizes the update algorithm.

[0044] The update unit can customize the model update means based on the user's current lifestyle during updating. For example, if the user is busy, the update unit provides a simplified update means. For example, the update unit can analyze the user's schedule data and identify busy time periods. The update unit can also provide a detailed update means if the user is relaxed. For example, the update unit can analyze the user's heart rate data and identify a relaxed state. The update unit can also prioritize updating data related to a specific event if the user is participating in that event. For example, the update unit provides a specialized update means based on the content of the event and related data. This enables more appropriate model updating by customizing the model update means based on the user's current lifestyle. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without AI. For example, the update unit can input the user's lifestyle data into a generation AI, which analyzes the data and customizes the update means.

[0045] During an update, the update unit can weight the update data of the model based on the time the conversation was submitted. For example, the update unit updates the model by prioritizing recent conversation data. For example, the update unit prioritizes the latest data based on the date and time the conversation was submitted. The update unit can also update the model by prioritizing conversation data immediately after a specific event. For example, the update unit prioritizes conversation data immediately after the event based on the date and time the event occurred. The update unit can also update the model by prioritizing conversation data immediately after the user expressed a specific emotion. For example, the update unit detects a change in emotion and prioritizes conversation data immediately thereafter. This enables model updating that prioritizes the latest information by weighting the update data of the model based on the time the conversation was submitted. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without AI. For example, the update unit can input conversation submission time data to a generation AI, which analyzes the data and weights the update data.

[0046] During updating, the update unit can analyze the user's social media activity and suggest a means for updating the model. The update unit, for example, updates the model based on topics the user is talking about on social media. For example, the update unit can analyze the user's posts and comments to identify current topics of interest. The update unit can also update the model by focusing on data influenced by people the user follows on social media. For example, the update unit can analyze the user's follow data to identify important people. The update unit can also update the model by focusing on data related to groups the user participates in on social media. For example, the update unit can analyze the user's group participation data to identify related data. This enables model updating that emphasizes related data by analyzing the user's social media activity. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's social media activity data into a generation AI, which can analyze the data and suggest an update means.

[0047] When displaying a hologram, the hologram unit can select the optimal display method by referring to the user's past hologram usage history. For example, the hologram unit prioritizes the hologram display method that the user has previously preferred. For example, the hologram unit analyzes past usage history data to identify the user's preferences. The hologram unit can also reproduce the hologram display method that the user used at a specific event. For example, the hologram unit reproduces a specific display method based on the content of the event and related data. The hologram unit can also suggest the optimal display method based on the user's past hologram usage history. For example, the hologram unit analyzes past usage data to identify the optimal display method. This allows the optimal hologram display method to be selected by referring to the user's past hologram usage history. Some or all of the above-described processing in the hologram unit may be performed using, for example, AI, or may be performed without AI. For example, the hologram unit can input past usage history data into a generation AI, which analyzes the data and selects the optimal display method.

[0048] When displaying a hologram, the hologram unit can customize the hologram display means based on the user's current lifestyle. For example, if the user is relaxed, the hologram unit displays a hologram with a relaxing effect. For example, the hologram unit analyzes the user's heart rate data to identify the relaxed state. Furthermore, if the user is busy, the hologram unit can display a simple, highly visible hologram. For example, the hologram unit analyzes the user's schedule data to identify busy times. Furthermore, if the user is participating in a specific event, the hologram unit can display a hologram related to that event. For example, the hologram unit provides a specific display method based on the content of the event and related data. This enables more appropriate hologram display by customizing the hologram display means based on the user's current lifestyle. Some or all of the above-described processing in the hologram unit may be performed using, for example, AI, or may be performed without AI. For example, the hologram unit can input the user's lifestyle data into a generation AI, which then analyzes the data and customizes the display means.

[0049] When displaying a hologram, the hologram unit can select the optimal display method by taking into account the user's geographical location information. For example, when the user is at home, the hologram unit displays a hologram suitable for the home. For example, the hologram unit analyzes the user's GPS data to identify the user's current location. Furthermore, when the user is traveling, the hologram unit can display a hologram related to the user's travel destination. For example, the hologram unit uses the user's location information service to identify the user's current location. Furthermore, when the user is at work, the hologram unit can display a hologram related to work. For example, the hologram unit analyzes the user's map data to identify the user's current location. This allows for more appropriate hologram display by selecting the optimal hologram display method by taking into account the user's geographical location information. Some or all of the above-described processing in the hologram unit may be performed using, or without, AI. For example, the hologram unit can input the user's geographical location information into a generation AI, which then analyzes the data and selects the optimal display method.

[0050] When displaying a hologram, the hologram unit can analyze the user's social media activity and suggest a means for displaying the hologram. For example, the hologram unit displays a hologram related to a topic the user is discussing on social media. For example, the hologram unit analyzes the user's posts and comments to identify current topics of interest. The hologram unit can also display a hologram related to a person the user follows on social media. For example, the hologram unit analyzes the user's follow data to identify important people. The hologram unit can also display a hologram related to a group the user joins on social media. For example, the hologram unit analyzes the user's group participation data to identify related holograms. This allows related holograms to be displayed by analyzing the user's social media activity. Some or all of the above-described processing in the hologram unit may be performed using, or without, AI. For example, the hologram unit can input the user's social media activity data into a generation AI, which analyzes the data and suggests a means for displaying the hologram.

[0051] When displaying a virtual grave, the virtual grave unit can select the optimal display method by referring to the user's past virtual grave usage history. For example, the virtual grave unit prioritizes the virtual grave display method that the user has previously preferred. For example, the virtual grave unit analyzes past usage history data to identify the user's preferences. The virtual grave unit can also reproduce the virtual grave display method that the user used for a specific event. For example, the virtual grave unit reproduces a specific display method based on the content of the event and related data. The virtual grave unit can also suggest the optimal display method based on the user's past virtual grave usage history. For example, the virtual grave unit analyzes past usage data to identify the optimal display method. This allows the optimal virtual grave display method to be selected by referring to the user's past virtual grave usage history. Some or all of the above-described processing in the virtual grave unit may be performed using, for example, AI, or may be performed without AI. For example, the virtual grave unit can input past usage history data into a generation AI, which analyzes the data and selects the optimal display method.

[0052] When displaying the virtual grave, the virtual grave unit can customize the display means of the virtual grave based on the user's current living situation. For example, if the user is relaxed, the virtual grave unit displays a virtual grave with a relaxing effect. For example, the virtual grave unit analyzes the user's heart rate data to identify the user's relaxed state. Furthermore, if the user is busy, the virtual grave unit can display a simple, highly visible virtual grave. For example, the virtual grave unit analyzes the user's schedule data to identify busy times. Furthermore, if the user is participating in a specific event, the virtual grave unit can display a virtual grave related to that event. For example, the virtual grave unit provides a specific display method based on the content of the event and related data. This allows for customizing the display means of the virtual grave based on the user's current living situation, enabling a more appropriate virtual grave display. Some or all of the above-described processing in the virtual grave unit may be performed using, for example, AI, or may be performed without AI. For example, the virtual grave unit can input the user's living situation data into a generation AI, which analyzes the data and customizes the display means.

[0053] When displaying a virtual grave, the virtual grave unit can select the optimal display method by taking into account the user's geographical location information. For example, if the user is at home, the virtual grave unit displays a virtual grave appropriate for the home. For example, the virtual grave unit analyzes the user's GPS data to identify the user's current location. Also, if the user is traveling, the virtual grave unit can display a virtual grave related to the user's travel destination. For example, the virtual grave unit can use the user's location information service to identify the user's current location. Also, if the user is at work, the virtual grave unit can display a virtual grave related to the user's work. For example, the virtual grave unit analyzes the user's map data to identify the user's current location. This allows for a more appropriate virtual grave display by selecting the optimal virtual grave display method by taking into account the user's geographical location information. Some or all of the above-described processing in the virtual grave unit may be performed using, or without, AI. For example, the virtual grave unit can input the user's geographical location information into a generation AI, which then analyzes the data and selects the optimal display method.

[0054] When displaying a virtual grave, the virtual grave unit can analyze the user's social media activity and suggest a display method for the virtual grave. For example, the virtual grave unit displays a virtual grave related to a topic the user is talking about on social media. For example, the virtual grave unit analyzes the user's posts and comments to identify current topics of interest. The virtual grave unit can also display a virtual grave related to a person the user follows on social media. For example, the virtual grave unit analyzes the user's follow data to identify important people. The virtual grave unit can also display a virtual grave related to a group the user joins on social media. For example, the virtual grave unit analyzes the user's group participation data to identify a related virtual grave. This allows the related virtual grave to be displayed by analyzing the user's social media activity. Some or all of the above-described processing in the virtual grave unit may be performed using, for example, AI, or may be performed without AI. For example, the virtual grave unit can input the user's social media activity data into a generation AI, which analyzes the data and suggests a display method for the virtual grave.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The imitation model generation system can analyze a user's past conversation history and prioritize recording conversations related to specific topics. For example, it can identify topics that a user frequently talks about and prioritize recording conversations related to those topics. By analyzing past conversation data and identifying frequently occurring topics and phrases, it is possible to record important conversations without missing any. It can also analyze conversations that a user has during specific time periods and concentrate recording on those time periods. By classifying past conversation data by time and identifying that many conversations occur during specific time periods, efficient recording becomes possible. Furthermore, it can also prioritize recording conversations related to specific topics from a user's past conversation history. By classifying past conversation data by topic and prioritizing recording conversations related to specific topics, it becomes possible to record according to the user's interests.

[0057] The imitation model generation system can adjust the conversation recording method based on the user's current activity status and areas of interest. For example, if the user is at work, only work-related conversations are recorded. By analyzing the user's calendar and task management data and identifying the current work content, highly relevant conversations can be recorded. Also, if the user is engaged in a hobby, conversations related to that hobby can be recorded with priority. By analyzing the user's social media and search history and identifying the current areas of interest, highly relevant conversations can be recorded. Furthermore, if the user is spending time with family, conversations related to the family can be recorded with priority. By analyzing the user's location information and communication history and identifying the current activity status, highly relevant conversations can be recorded.

[0058] The imitation model generation system can adjust the conversation recording method by taking into account the user's geographical location information. For example, if the user is traveling, conversations related to the travel destination can be recorded with priority. By analyzing the user's GPS data and identifying the user's current location, highly relevant conversations can be recorded. Also, if the user is at home, conversations related to the home can be recorded with priority. By using the user's location information service and identifying the user's current location, highly relevant conversations can be recorded. Furthermore, if the user is at work, conversations related to work can be recorded with priority. By analyzing the user's map data and identifying the current activity location, highly relevant conversations can be recorded. In this way, by recording highly relevant conversations by taking the user's geographical location information into account, important conversations will not be missed.

[0059] The imitation model generation system can analyze a user's social media activity and prioritize recording relevant conversations. For example, conversations related to topics that the user is talking about on social media can be prioritized and recorded. By analyzing the user's posts and comments and identifying current topics of interest, highly relevant conversations can be recorded. In addition, the imitation model generation system can prioritize recording conversations with people the user follows on social media. By analyzing the user's follow data and identifying important people, highly relevant conversations can be recorded. Furthermore, the imitation model generation system can prioritize recording conversations related to groups the user participates in on social media. By analyzing the user's group participation data and identifying relevant conversations, highly relevant conversations can be recorded. In this way, relevant conversations can be recorded by analyzing the user's social media activity.

[0060] The imitation model generation system can optimize the model update method by referencing the user's past conversation history. For example, it can select the optimal update algorithm based on past training data. By analyzing past training data and identifying effective update patterns, it can improve the accuracy of the model. It can also apply an update algorithm to improve the model accuracy from past training data. It can improve the model accuracy by optimizing parameter adjustments and feedback loops based on past data. Furthermore, by referencing past conversation history, it can prioritize model updates related to specific topics. By classifying past conversation data by topic and updating the model with an emphasis on data related to specific topics, it is possible to update the model according to the user's interests.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The recording unit records personal conversations. Personal conversations include everyday conversations, business conversations, online chats, etc. The recording unit records the conversations using audio recordings, text recordings, audio recordings, etc., and collects detailed data such as the content, tone, and frequency of the conversations. For example, the tone of the conversation can be evaluated based on criteria such as emotional expression, pitch, and strength of voice. Step 2: The analyzer analyzes the data recorded by the recorder and learns language patterns and personality. The analyzer analyzes the usage of specific words and speaking characteristics, and analyzes language patterns based on criteria such as frequent phrases, grammatical structures, and vocabulary frequency. It can also evaluate personality based on criteria such as character traits, behavioral patterns, and psychological characteristics. Step 3: The updater updates the model based on the results learned by the analyzer. The updater continuously analyzes new data and can update the model at any frequency or timing, such as in real time, periodically, or event-driven.

[0063] (Example 2) An imitation model generation system according to an embodiment of the present invention records an individual's conversations and uses AI to learn the individual's language patterns and personality, thereby creating a model that mimics that individual. This imitation model generation system records the individual's conversations, analyzes the recorded data, and learns the individual's language patterns and personality. Furthermore, the system updates the model based on the learning results to improve accuracy. Even after a person's death, family and friends can relive conversations with the deceased by having the AI ​​respond as if they were the deceased. A more realistic experience can be achieved by using home 3D holograms and virtual graves. For example, the imitation model generation system records an individual's conversations. Detailed data, such as the content, tone, and frequency of the conversations, is collected. For example, everyday conversations and comments made at specific events are recorded. This allows the individual's language patterns and personality to be understood. Next, the imitation model generation system uses AI to analyze the recorded data. The AI ​​analyzes the collected data and learns the individual's language patterns and personality. For example, it analyzes the use of specific words and speaking characteristics. This allows the individual's characteristics to be accurately captured. Furthermore, the imitation model generation system updates the model based on the learning results to improve accuracy. The AI ​​continuously analyzes new data and updates the model, thereby maintaining a model that always reflects the latest information. Even after death, the imitation model generation system allows family and friends to relive conversations with the deceased by having the AI ​​respond as if they were the deceased. For example, an AI that reproduces the deceased's voice and speaking style can converse with family and friends, allowing them to share memories with the deceased. A more realistic experience can be achieved by using home 3D holograms and virtual graves. For example, the deceased's appearance can be recreated in 3D hologram form, allowing family and friends to interact with them. Furthermore, using a virtual grave can provide a place to remember the deceased. This allows the imitation model generation system to automatically record and analyze an individual's conversations and update the model to create a model that imitates that person.

[0064] An imitation model generation system according to an embodiment includes a recording unit, an analysis unit, and an update unit. The recording unit records personal conversations. Personal conversations include, but are not limited to, everyday conversations, business conversations, and online chats. The recording unit records conversations in the form of, for example, audio recording, text recording, or audio recording. The recording unit can also collect detailed data on the content, tone, and frequency of the conversations. For example, the recording unit can evaluate the tone of the conversation based on criteria such as emotional expression, voice pitch, and strength. The analysis unit analyzes the data recorded by the recording unit to learn language patterns and personality traits. The analysis unit can analyze, for example, the usage of specific words and speaking characteristics. For example, the analysis unit can analyze language patterns based on criteria such as frequently used phrases, grammatical structures, and vocabulary frequency. The analysis unit can also evaluate personality traits based on criteria such as personality traits, behavioral patterns, and psychological characteristics. The update unit updates the model based on the results learned by the analysis unit. For example, the update unit can continuously analyze new data and update the model. The update unit can update the model at a frequency or timing such as in real time, periodically, event-driven, etc. As a result, the imitation model generation system according to the embodiment can automatically record and analyze an individual's conversation and update the model to create a model that imitates that person.

[0065] The update unit can continuously analyze new data and update the model. For example, the update unit analyzes new data in real time and updates the model. For example, the update unit collects personal conversation data in real time and updates the model based on that data. The update unit can also periodically analyze new data and update the model. For example, the update unit analyzes data and updates the model on a regular schedule, such as daily, weekly, or monthly. The update unit can also analyze new data and update the model in an event-driven manner. For example, when a specific event occurs, data related to the event is analyzed and the model is updated. In this way, by continuously analyzing new data and updating the model, it is possible to maintain a model that always reflects the latest information. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input data collected in real time to a generation AI, which then analyzes the data and updates the model.

[0066] The analysis unit can analyze the usage of specific words and characteristics of speaking style. The analysis unit, for example, analyzes the usage of specific words. For example, the analysis unit analyzes the usage of specific words based on criteria such as frequency, context, and usage situation. The analysis unit can also analyze speaking style characteristics. For example, the analysis unit analyzes speaking style characteristics based on criteria such as tone of voice, speaking speed, and intonation. In this way, by analyzing the usage of specific words and speaking style characteristics, it is possible to accurately capture the characteristics of an individual. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the usage of specific words and speaking style characteristics into a generation AI, and the generation AI can analyze the data.

[0067] The recording unit can collect detailed data on the content, tone, and frequency of conversations. The recording unit, for example, collects the content of the conversations. For example, the recording unit collects text data of the conversations and records the content. The recording unit can also collect the tone of the conversations. For example, the recording unit evaluates and records the tone of the conversations based on criteria such as emotional expression, pitch, and strength. The recording unit can also collect the frequency of conversations. For example, the recording unit measures and records the frequency of conversations based on criteria such as time units, number of times, and occurrence rate. By collecting detailed data such as the content, tone, and frequency of conversations, it is possible to understand an individual's language patterns and personality. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input data on the content, tone, and frequency of conversations to a generation AI, which then collects the data.

[0068] The imitation model generation system includes a hologram unit that generates a home 3D hologram. The hologram unit generates the home 3D hologram. Home 3D holograms include, for example, technology for displaying a three-dimensional image using a high-resolution display device. The hologram unit generates the 3D hologram based on specifications such as resolution, display device, and generation method. For example, the hologram unit displays a three-dimensional image using a high-resolution projector. The hologram unit can also generate a 3D model using specific software and display the model. This allows for a more realistic experience by generating a home 3D hologram. Some or all of the above-described processing in the hologram unit may be performed using, for example, AI, or may be performed without AI. For example, the hologram unit can input the generation of the 3D model to a generation AI, which then generates the 3D model.

[0069] The imitation model generation system includes a virtual grave unit that provides a virtual grave. The virtual grave unit provides the virtual grave. The virtual grave includes, for example, a virtual space for remembering the deceased. The virtual grave unit provides the virtual grave based on specifications such as display content, access method, and interaction functions. For example, the virtual grave unit provides a virtual space that displays photos and messages of the deceased. The virtual grave unit can also provide an interaction function for family and friends to remember the deceased in the virtual space. In this way, by providing the virtual grave, a place to remember the deceased can be provided. Some or all of the above-mentioned processing in the virtual grave unit may be performed, for example, using AI, or may be performed without using AI. For example, the virtual grave unit can input the generation of the virtual space into a generation AI, and the generation AI can generate the virtual space.

[0070] The recording unit can estimate the user's emotions and adjust the timing of recording the conversation based on the estimated user's emotions. For example, if the user is feeling stressed, the recording unit pauses recording the conversation and resumes it when the user is relaxed. For example, the recording unit can analyze the user's voice data to detect signs of stress. Furthermore, if the user is excited, the recording unit can increase the recording frequency so as not to miss important conversations. For example, the recording unit can analyze the user's facial expression data to detect signs of excitement. Furthermore, if the user is calm, the recording unit can record the conversation at a normal recording timing. For example, the recording unit can analyze the user's heart rate data to detect a calm state. This allows the conversation to be recorded at a more appropriate timing by adjusting the timing of recording the conversation according to the user's emotions. Emotion estimation is realized 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 recording unit can be performed using, for example, an AI, or without an AI. For example, the recording unit can input the user's emotional data into the generation AI, which can then estimate the emotion and adjust the recording timing.

[0071] The recording unit can analyze the user's past conversation history and select an appropriate recording method. The recording unit, for example, prioritizes recording important conversations based on patterns of frequent conversations the user has had in the past. For example, the recording unit can analyze past conversation data and identify frequently occurring topics and phrases. The recording unit can also analyze conversations the user has during a specific time period and concentrate recording on that time period. For example, the recording unit can classify past conversation data by time and identify that many conversations occur during that time period. The recording unit can also prioritize recording conversations related to specific topics from the user's past conversation history. For example, the recording unit can classify past conversation data by topic and prioritize recording conversations related to specific topics. This allows the optimal recording method to be selected by analyzing the user's past conversation history. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without AI. For example, the recording unit can input past conversation data into a generation AI, which analyzes the data and selects an appropriate recording method.

[0072] When recording a conversation, the recording unit can filter the conversation based on the user's current activity status and areas of interest. For example, if the user is at work, the recording unit records only work-related conversations. For example, the recording unit can analyze the user's calendar and task management data to identify the user's current work content. Furthermore, if the user is engaged in a hobby, the recording unit can prioritize recording conversations related to the hobby. For example, the recording unit can analyze the user's social media and search history to identify the user's current areas of interest. Furthermore, if the user is spending time with family, the recording unit can prioritize recording conversations related to the family. For example, the recording unit can analyze the user's location information and communication history to identify the user's current activity status. This allows for filtering based on the user's current activity status and areas of interest to record highly relevant conversations. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input data on the user's activity status and areas of interest into a generation AI, which can analyze the data and perform filtering.

[0073] The recording unit can estimate the user's emotions and determine the priority of conversations to be recorded based on the estimated user emotions. For example, if the user is sad, the recording unit prioritizes recording emotional conversations. For example, the recording unit analyzes the user's voice data to detect signs of sadness. Furthermore, if the user is happy, the recording unit can also prioritize recording positive conversations. For example, the recording unit analyzes the user's facial expression data to detect signs of joy. Furthermore, if the user is angry, the recording unit can also prioritize recording calm conversations. For example, the recording unit analyzes the user's heart rate data to detect signs of anger. Thus, by determining the priority of conversations to be recorded based on the user's emotions, important conversations can be prioritized and recorded. The emotion estimation is realized using an emotion estimation function, for example, 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 recording unit can be performed using, for example, AI, or without AI. For example, the recording unit can input the user's emotional data into the generation AI, which can then estimate the emotions and determine the priority of the conversations to be recorded.

[0074] When recording a conversation, the recording unit can prioritize recording highly relevant conversations by taking into account the user's geographical location information. For example, when the user is traveling, the recording unit prioritizes recording conversations related to the travel destination. For example, the recording unit analyzes the user's GPS data to identify the user's current location. Furthermore, when the user is at home, the recording unit can prioritize recording conversations related to the home. For example, the recording unit uses the user's location information service to identify the user's current location. Furthermore, when the user is at work, the recording unit can prioritize recording conversations related to work. For example, the recording unit analyzes the user's map data to identify the current location of activities. Thus, by prioritizing recording highly relevant conversations by taking into account the user's geographical location information, important conversations are not missed. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's geographical location information to a generation AI, which analyzes the data and prioritizes recording highly relevant conversations.

[0075] When recording a conversation, the recording unit can analyze the user's social media activity and record related conversations. For example, the recording unit prioritizes recording conversations related to topics the user is talking about on social media. For example, the recording unit can analyze the user's posts and comments to identify current topics of interest. The recording unit can also prioritize recording conversations with people the user follows on social media. For example, the recording unit can analyze the user's follow data to identify important people. The recording unit can also prioritize recording conversations related to groups the user participates in on social media. For example, the recording unit can analyze the user's group participation data to identify related conversations. In this way, related conversations can be recorded by analyzing the user's social media activity. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's social media activity data into a generation AI, which can analyze the data and record related conversations.

[0076] The analysis unit can estimate the user's emotions and adjust the language pattern analysis method based on the estimated user emotions. For example, if the user is sad, the analysis unit can emphasize the frequency of use of emotional words in the analysis. For example, the analysis unit can analyze the user's voice data and detect signs of sadness. Also, if the user is happy, the analysis unit can emphasize the frequency of use of positive words in the analysis. For example, the analysis unit can analyze the user's facial expression data and detect signs of joy. Also, if the user is angry, the analysis unit can emphasize the frequency of use of aggressive words in the analysis. For example, the analysis unit can analyze the user's heart rate data and detect signs of anger. This enables more accurate analysis by adjusting the language pattern analysis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative 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 analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input user emotion data into the generation AI, which can then analyze the data and adjust how it analyzes language patterns.

[0077] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the conversation. For example, in the case of an important conversation, the analysis unit performs a detailed analysis of language patterns. For example, the analysis unit performs a detailed analysis based on the content of the conversation and the importance of the people involved. The analysis unit can also perform a simplified analysis of language patterns in the case of everyday conversations. For example, the analysis unit performs a simplified analysis based on the frequency of the conversation and general content. The analysis unit can also perform an analysis of language patterns specialized for a conversation related to a specific event. For example, the analysis unit performs a specialized analysis based on the content of the event and related data. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the conversation. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation importance data to a generation AI, which analyzes the data and adjusts the level of detail of the analysis.

[0078] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit applies a business analysis algorithm to business-related conversations. For example, the analysis unit performs business analysis based on business documents and meeting minutes. The analysis unit can also apply a home analysis algorithm to domestic conversations. For example, the analysis unit performs home analysis based on domestic conversation data. The analysis unit can also apply a hobby analysis algorithm to conversations about hobbies. For example, the analysis unit performs hobby analysis based on conversation data related to hobbies. This allows for more appropriate analysis by applying different analysis algorithms depending on the category of the conversation. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation category data to a generation AI, which analyzes the data and applies different analysis algorithms.

[0079] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user emotions. For example, if the user is sad, the analysis unit prioritizes the analysis of emotional conversations. For example, the analysis unit analyzes the user's voice data to detect signs of sadness. Also, if the user is happy, the analysis unit can prioritize the analysis of positive conversations. For example, the analysis unit analyzes the user's facial expression data to detect signs of joy. Also, if the user is angry, the analysis unit can prioritize the analysis of aggressive conversations. For example, the analysis unit analyzes the user's heart rate data to detect signs of anger. Thus, by determining the analysis priority based on the user's emotions, important conversations can be prioritized for analysis. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative 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 analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input user emotion data into the generation AI, which can then analyze the data and determine analysis priorities.

[0080] During analysis, the analysis unit can determine the priority of analysis based on the time when the conversation was submitted. For example, the analysis unit prioritizes analysis of recent conversations. For example, the analysis unit prioritizes the latest data based on the date and time when the conversation was submitted. The analysis unit can also prioritize analysis of conversations that occur immediately after a specific event. For example, the analysis unit prioritizes conversations that occur immediately after an event based on the date and time when the event occurred. The analysis unit can also prioritize analysis of conversations that occur immediately after a user expresses a specific emotion. For example, the analysis unit detects a change in emotion and prioritizes conversations that occur immediately after that change. In this way, by determining the priority of analysis based on the time when the conversation was submitted, the latest information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time when the conversation was submitted to a generation AI, which analyzes the data and determines the priority of analysis.

[0081] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversations. For example, the analysis unit prioritizes analysis of conversations related to a specific topic. For example, the analysis unit analyzes conversation topic data to identify highly relevant topics. The analysis unit can also prioritize analysis of conversations related to the user's areas of interest. For example, the analysis unit analyzes the user's social media or search history to identify current areas of interest. The analysis unit can also prioritize analysis of highly relevant conversations based on the user's past conversation history. For example, the analysis unit analyzes past conversation data to identify highly relevant conversations. This allows the analysis order to be adjusted based on the relevance of the conversations, thereby prioritizing analysis of highly relevant conversations. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input conversation relevance data to a generation AI, which analyzes the data and adjusts the order of analysis.

[0082] The update unit can estimate the user's emotions and adjust the model update method based on the estimated user emotions. For example, if the user is sad, the update unit updates the model by emphasizing emotional data. For example, the update unit analyzes the user's voice data and detects signs of sadness. Furthermore, if the user is happy, the update unit can also update the model by emphasizing positive data. For example, the update unit analyzes the user's facial expression data and detects signs of joy. Furthermore, if the user is angry, the update unit can also update the model by emphasizing aggressive data. For example, the update unit analyzes the user's heart rate data and detects signs of anger. This enables more appropriate model update by adjusting the model update method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative 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 update unit can be performed using, for example, an AI, or without an AI. For example, the update unit can input user emotion data into the generation AI, which can then analyze the data and adjust how the model is updated.

[0083] During updating, the update unit can optimize the model update algorithm by referring to past learning data. The update unit, for example, selects an optimal update algorithm based on past learning data. For example, the update unit analyzes past learning data and identifies an effective update pattern. The update unit can also apply an update algorithm to improve the accuracy of the model from the past learning data. For example, the update unit optimizes parameter adjustment and feedback loops based on past data. This allows the optimal update algorithm to be applied by referring to the past learning data. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input past learning data to a generation AI, which analyzes the data and optimizes the update algorithm.

[0084] The update unit can customize the model update means based on the user's current lifestyle during updating. For example, if the user is busy, the update unit provides a simplified update means. For example, the update unit can analyze the user's schedule data and identify busy time periods. The update unit can also provide a detailed update means if the user is relaxed. For example, the update unit can analyze the user's heart rate data and identify a relaxed state. The update unit can also prioritize updating data related to a specific event if the user is participating in that event. For example, the update unit provides a specialized update means based on the content of the event and related data. This enables more appropriate model updating by customizing the model update means based on the user's current lifestyle. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without AI. For example, the update unit can input the user's lifestyle data into a generation AI, which analyzes the data and customizes the update means.

[0085] The update unit can estimate the user's emotions and adjust the model update frequency based on the estimated user emotions. For example, if the user is sad, the update unit frequently updates the emotional data. For example, the update unit can analyze the user's voice data to detect signs of sadness. Also, if the user is happy, the update unit can frequently update the positive data. For example, the update unit can analyze the user's facial expression data to detect signs of joy. Also, if the user is angry, the update unit can frequently update the aggressive data. For example, the update unit can analyze the user's heart rate data to detect signs of anger. This allows the model to be updated at a more appropriate frequency by adjusting the model update frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative 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 update unit can be performed using, for example, an AI, or without an AI. For example, the update unit can input user emotion data into the generation AI, which can then analyze the data and adjust the model update frequency.

[0086] During an update, the update unit can weight the update data of the model based on the time the conversation was submitted. For example, the update unit updates the model by prioritizing recent conversation data. For example, the update unit prioritizes the latest data based on the date and time the conversation was submitted. The update unit can also update the model by prioritizing conversation data immediately after a specific event. For example, the update unit prioritizes conversation data immediately after the event based on the date and time the event occurred. The update unit can also update the model by prioritizing conversation data immediately after the user expressed a specific emotion. For example, the update unit detects a change in emotion and prioritizes conversation data immediately thereafter. This enables model updating that prioritizes the latest information by weighting the update data of the model based on the time the conversation was submitted. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without AI. For example, the update unit can input conversation submission time data to a generation AI, which analyzes the data and weights the update data.

[0087] During updating, the update unit can analyze the user's social media activity and suggest a means for updating the model. The update unit, for example, updates the model based on topics the user is talking about on social media. For example, the update unit can analyze the user's posts and comments to identify current topics of interest. The update unit can also update the model by focusing on data influenced by people the user follows on social media. For example, the update unit can analyze the user's follow data to identify important people. The update unit can also update the model by focusing on data related to groups the user participates in on social media. For example, the update unit can analyze the user's group participation data to identify related data. This enables model updating that emphasizes related data by analyzing the user's social media activity. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's social media activity data into a generation AI, which can analyze the data and suggest an update means.

[0088] The hologram unit can estimate the user's emotions and adjust the hologram display method based on the estimated user's emotions. For example, if the user is sad, the hologram unit displays a hologram with subdued colors. For example, the hologram unit analyzes the user's voice data and detects signs of sadness. Also, if the user is happy, the hologram unit can display a hologram with bright colors. For example, the hologram unit analyzes the user's facial expression data and detects signs of joy. Also, if the user is angry, the hologram unit can display a hologram with calm colors. For example, the hologram unit analyzes the user's heart rate data and detects signs of anger. This allows for more appropriate hologram display by adjusting the hologram display method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or 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 hologram unit may be performed using AI, or without AI. For example, the hologram unit can input the user's emotional data into the generation AI, which can then analyze the data and adjust how the hologram is displayed.

[0089] When displaying a hologram, the hologram unit can select the optimal display method by referring to the user's past hologram usage history. For example, the hologram unit prioritizes the hologram display method that the user has previously preferred. For example, the hologram unit analyzes past usage history data to identify the user's preferences. The hologram unit can also reproduce the hologram display method that the user used at a specific event. For example, the hologram unit reproduces a specific display method based on the content of the event and related data. The hologram unit can also suggest the optimal display method based on the user's past hologram usage history. For example, the hologram unit analyzes past usage data to identify the optimal display method. This allows the optimal hologram display method to be selected by referring to the user's past hologram usage history. Some or all of the above-described processing in the hologram unit may be performed using, for example, AI, or may be performed without AI. For example, the hologram unit can input past usage history data into a generation AI, which analyzes the data and selects the optimal display method.

[0090] When displaying a hologram, the hologram unit can customize the hologram display means based on the user's current lifestyle. For example, if the user is relaxed, the hologram unit displays a hologram with a relaxing effect. For example, the hologram unit analyzes the user's heart rate data to identify the relaxed state. Furthermore, if the user is busy, the hologram unit can display a simple, highly visible hologram. For example, the hologram unit analyzes the user's schedule data to identify busy times. Furthermore, if the user is participating in a specific event, the hologram unit can display a hologram related to that event. For example, the hologram unit provides a specific display method based on the content of the event and related data. This enables more appropriate hologram display by customizing the hologram display means based on the user's current lifestyle. Some or all of the above-described processing in the hologram unit may be performed using, for example, AI, or may be performed without AI. For example, the hologram unit can input the user's lifestyle data into a generation AI, which then analyzes the data and customizes the display means.

[0091] The hologram unit can estimate the user's emotions and determine the display priority of holograms based on the estimated user emotions. For example, if the user is sad, the hologram unit can prioritize displaying emotional holograms. For example, the hologram unit can analyze the user's voice data and detect signs of sadness. Also, if the user is happy, the hologram unit can prioritize displaying positive holograms. For example, the hologram unit can analyze the user's facial expression data and detect signs of joy. Also, if the user is angry, the hologram unit can prioritize displaying calm holograms. For example, the hologram unit can analyze the user's heart rate data and detect signs of anger. This allows important holograms to be prioritized by determining the display priority of holograms based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or 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 hologram unit may be performed using, for example, AI, or may be performed without using AI. For example, the hologram unit may input user emotion data into a generation AI, which may analyze the data and determine the display priority of the holograms.

[0092] When displaying a hologram, the hologram unit can select the optimal display method by taking into account the user's geographical location information. For example, when the user is at home, the hologram unit displays a hologram suitable for the home. For example, the hologram unit analyzes the user's GPS data to identify the user's current location. Furthermore, when the user is traveling, the hologram unit can display a hologram related to the user's travel destination. For example, the hologram unit uses the user's location information service to identify the user's current location. Furthermore, when the user is at work, the hologram unit can display a hologram related to work. For example, the hologram unit analyzes the user's map data to identify the user's current location. This allows for more appropriate hologram display by selecting the optimal hologram display method by taking into account the user's geographical location information. Some or all of the above-described processing in the hologram unit may be performed using, or without, AI. For example, the hologram unit can input the user's geographical location information into a generation AI, which then analyzes the data and selects the optimal display method.

[0093] When displaying a hologram, the hologram unit can analyze the user's social media activity and suggest a means for displaying the hologram. For example, the hologram unit displays a hologram related to a topic the user is discussing on social media. For example, the hologram unit analyzes the user's posts and comments to identify current topics of interest. The hologram unit can also display a hologram related to a person the user follows on social media. For example, the hologram unit analyzes the user's follow data to identify important people. The hologram unit can also display a hologram related to a group the user joins on social media. For example, the hologram unit analyzes the user's group participation data to identify related holograms. This allows related holograms to be displayed by analyzing the user's social media activity. Some or all of the above-described processing in the hologram unit may be performed using, or without, AI. For example, the hologram unit can input the user's social media activity data into a generation AI, which analyzes the data and suggests a means for displaying the hologram.

[0094] The virtual grave unit can estimate the user's emotions and adjust the display method of the virtual grave based on the estimated user's emotions. For example, if the user is sad, the virtual grave unit displays the virtual grave in subdued colors. For example, the virtual grave unit analyzes the user's voice data to detect signs of sadness. Also, if the user is happy, the virtual grave unit can display the virtual grave in bright colors. For example, the virtual grave unit analyzes the user's facial expression data to detect signs of joy. Also, if the user is angry, the virtual grave unit can display the virtual grave in subdued colors. For example, the virtual grave unit analyzes the user's heart rate data to detect signs of anger. This allows for a more appropriate virtual grave display by adjusting the display method of the virtual grave based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or 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 virtual grave unit may be performed using, for example, AI, or may be performed without using AI. For example, the virtual grave unit may input user emotional data into a generation AI, which may analyze the data and adjust the display method of the virtual grave.

[0095] When displaying a virtual grave, the virtual grave unit can select the optimal display method by referring to the user's past virtual grave usage history. For example, the virtual grave unit prioritizes the virtual grave display method that the user has previously preferred. For example, the virtual grave unit analyzes past usage history data to identify the user's preferences. The virtual grave unit can also reproduce the virtual grave display method that the user used for a specific event. For example, the virtual grave unit reproduces a specific display method based on the content of the event and related data. The virtual grave unit can also suggest the optimal display method based on the user's past virtual grave usage history. For example, the virtual grave unit analyzes past usage data to identify the optimal display method. This allows the optimal virtual grave display method to be selected by referring to the user's past virtual grave usage history. Some or all of the above-described processing in the virtual grave unit may be performed using, for example, AI, or may be performed without AI. For example, the virtual grave unit can input past usage history data into a generation AI, which analyzes the data and selects the optimal display method.

[0096] When displaying the virtual grave, the virtual grave unit can customize the display means of the virtual grave based on the user's current living situation. For example, if the user is relaxed, the virtual grave unit displays a virtual grave with a relaxing effect. For example, the virtual grave unit analyzes the user's heart rate data to identify the user's relaxed state. Furthermore, if the user is busy, the virtual grave unit can display a simple, highly visible virtual grave. For example, the virtual grave unit analyzes the user's schedule data to identify busy times. Furthermore, if the user is participating in a specific event, the virtual grave unit can display a virtual grave related to that event. For example, the virtual grave unit provides a specific display method based on the content of the event and related data. This allows for customizing the display means of the virtual grave based on the user's current living situation, enabling a more appropriate virtual grave display. Some or all of the above-described processing in the virtual grave unit may be performed using, for example, AI, or may be performed without AI. For example, the virtual grave unit can input the user's living situation data into a generation AI, which analyzes the data and customizes the display means.

[0097] The virtual grave unit can estimate the user's emotions and determine the display priority of virtual graves based on the estimated user emotions. For example, if the user is sad, the virtual grave unit can prioritize displaying emotional virtual graves. For example, the virtual grave unit can analyze the user's voice data to detect signs of sadness. Also, if the user is happy, the virtual grave unit can prioritize displaying positive virtual graves. For example, the virtual grave unit can analyze the user's facial expression data to detect signs of joy. Also, if the user is angry, the virtual grave unit can prioritize displaying calm virtual graves. For example, the virtual grave unit can analyze the user's heart rate data to detect signs of anger. Thus, by determining the display priority of virtual graves based on the user's emotions, important virtual graves can be prioritized for display. Emotion estimation is realized using an emotion estimation function, for example, 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 virtual grave unit may be performed using, for example, AI, or may be performed without using AI. For example, the virtual grave unit may input user emotion data into a generation AI, which then analyzes the data and determines the display priority of the virtual grave.

[0098] When displaying a virtual grave, the virtual grave unit can select the optimal display method by taking into account the user's geographical location information. For example, if the user is at home, the virtual grave unit displays a virtual grave appropriate for the home. For example, the virtual grave unit analyzes the user's GPS data to identify the user's current location. Also, if the user is traveling, the virtual grave unit can display a virtual grave related to the user's travel destination. For example, the virtual grave unit can use the user's location information service to identify the user's current location. Also, if the user is at work, the virtual grave unit can display a virtual grave related to the user's work. For example, the virtual grave unit analyzes the user's map data to identify the user's current location. This allows for a more appropriate virtual grave display by selecting the optimal virtual grave display method by taking into account the user's geographical location information. Some or all of the above-described processing in the virtual grave unit may be performed using, or without, AI. For example, the virtual grave unit can input the user's geographical location information into a generation AI, which then analyzes the data and selects the optimal display method.

[0099] When displaying a virtual grave, the virtual grave unit can analyze the user's social media activity and suggest a display method for the virtual grave. For example, the virtual grave unit displays a virtual grave related to a topic the user is talking about on social media. For example, the virtual grave unit analyzes the user's posts and comments to identify current topics of interest. The virtual grave unit can also display a virtual grave related to a person the user follows on social media. For example, the virtual grave unit analyzes the user's follow data to identify important people. The virtual grave unit can also display a virtual grave related to a group the user joins on social media. For example, the virtual grave unit analyzes the user's group participation data to identify a related virtual grave. This allows the related virtual grave to be displayed by analyzing the user's social media activity. Some or all of the above-described processing in the virtual grave unit may be performed using, for example, AI, or may be performed without AI. For example, the virtual grave unit can input the user's social media activity data into a generation AI, which analyzes the data and suggests a display method for the virtual grave. === Hard Collateral 1-1 === Each of the multiple elements, including the recording unit, analysis unit, update unit, hologram unit, and virtual grave unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the recording unit records an individual's conversation using the microphone 38B or camera 42 of the smart device 14. The analysis unit analyzes the recorded data by the specific processing unit 290 of the data processing device 12 to learn language patterns and personality. The update unit updates the model by the specific processing unit 290 of the data processing device 12. The hologram unit generates a 3D hologram using the output device 40 of the smart device 14. The virtual grave unit provides a virtual space by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the recording unit, analysis unit, update unit, hologram unit, and virtual grave unit, described above, is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the recording unit records an individual's conversation using the microphone 238 or camera 42 of the smart glasses 214. The analysis unit analyzes the recorded data by the specific processing unit 290 of the data processing device 12 to learn language patterns and personality. The update unit updates the model by the specific processing unit 290 of the data processing device 12. The hologram unit generates a 3D hologram using the display of the smart glasses 214. The virtual grave unit provides a virtual space by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the recording unit, analysis unit, update unit, hologram unit, and virtual grave unit, described above, is realized, for example, in at least one of the headset terminal 314 and the data processing device 12. For example, the recording unit records an individual's conversation using the microphone 238 or camera 42 of the headset terminal 314. The analysis unit analyzes the recorded data using the specific processing unit 290 of the data processing device 12 to learn language patterns and personality. The update unit updates the model using the specific processing unit 290 of the data processing device 12. The hologram unit generates a 3D hologram using the display 343 of the headset terminal 314. The virtual grave unit provides a virtual space using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the recording unit, analysis unit, update unit, hologram unit, and virtual grave unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the recording unit records an individual's conversation using the microphone 238 or camera 42 of the robot 414. The analysis unit analyzes the recorded data by the specific processing unit 290 of the data processing device 12 to learn language patterns and personality. The update unit updates the model by the specific processing unit 290 of the data processing device 12. The hologram unit generates a 3D hologram using the display device of the robot 414. The virtual grave unit provides a virtual space by the specific processing unit 290 of the data processing device 12.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The imitation model generation system can estimate a user's emotions and adjust the tone of the conversation based on the estimated emotions. For example, if the user is sad, the system can respond in a gentle tone. By analyzing the user's voice data and detecting signs of sadness, the system can select an appropriate tone. Alternatively, if the user is happy, the system can respond in a bright tone. By analyzing the user's facial expression data and detecting signs of joy, the system can select an appropriate tone. Furthermore, if the user is angry, the system can respond in a calm tone. By analyzing the user's heart rate data and detecting signs of anger, the system can select an appropriate tone. This allows for more natural communication by using a tone that corresponds to the user's emotions.

[0102] The imitation model generation system can analyze a user's past conversation history and prioritize recording conversations related to specific topics. For example, it can identify topics that a user frequently talks about and prioritize recording conversations related to those topics. By analyzing past conversation data and identifying frequently occurring topics and phrases, it is possible to record important conversations without missing any. It can also analyze conversations that a user has during specific time periods and concentrate recording on those time periods. By classifying past conversation data by time and identifying that many conversations occur during specific time periods, efficient recording becomes possible. Furthermore, it can also prioritize recording conversations related to specific topics from a user's past conversation history. By classifying past conversation data by topic and prioritizing recording conversations related to specific topics, it becomes possible to record according to the user's interests.

[0103] The imitation model generation system can adjust the conversation recording method based on the user's current activity status and areas of interest. For example, if the user is at work, only work-related conversations are recorded. By analyzing the user's calendar and task management data and identifying the current work content, highly relevant conversations can be recorded. Also, if the user is engaged in a hobby, conversations related to that hobby can be recorded with priority. By analyzing the user's social media and search history and identifying the current areas of interest, highly relevant conversations can be recorded. Furthermore, if the user is spending time with family, conversations related to the family can be recorded with priority. By analyzing the user's location information and communication history and identifying the current activity status, highly relevant conversations can be recorded.

[0104] The imitation model generation system can estimate a user's emotions and adjust the timing of conversation recording based on the estimated emotions. For example, if the user is feeling stressed, the system pauses the conversation recording and resumes it in a relaxed state. By analyzing the user's voice data and detecting signs of stress, the system can record at an appropriate time. Furthermore, if the user is excited, the system can increase the recording frequency so as not to miss important conversations. By analyzing the user's facial expression data and detecting signs of excitement, the system can record at an appropriate time. Furthermore, if the user is calm, the system can record the conversation at the normal recording timing. By analyzing the user's heart rate data and detecting a calm state, the system can record at an appropriate time. This allows the system to adjust the timing of conversation recording according to the user's emotions and record the conversation at a more appropriate time.

[0105] The imitation model generation system can adjust the conversation recording method by taking into account the user's geographical location information. For example, if the user is traveling, conversations related to the travel destination can be recorded with priority. By analyzing the user's GPS data and identifying the user's current location, highly relevant conversations can be recorded. Also, if the user is at home, conversations related to the home can be recorded with priority. By using the user's location information service and identifying the user's current location, highly relevant conversations can be recorded. Furthermore, if the user is at work, conversations related to work can be recorded with priority. By analyzing the user's map data and identifying the current activity location, highly relevant conversations can be recorded. In this way, by recording highly relevant conversations by taking the user's geographical location information into account, important conversations will not be missed.

[0106] The imitation model generation system can estimate the user's emotions and determine the priority of conversations based on the estimated emotions. For example, if the user is sad, emotional conversations can be recorded with priority. By analyzing the user's voice data and detecting signs of sadness, important conversations can be recorded with priority. Also, if the user is happy, positive conversations can be recorded with priority. By analyzing the user's facial expression data and detecting signs of joy, important conversations can be recorded with priority. Furthermore, if the user is angry, calm conversations can be recorded with priority. By analyzing the user's heart rate data and detecting signs of anger, important conversations can be recorded with priority. Thus, by determining the priority of conversations based on the user's emotions, important conversations can be recorded without missing any.

[0107] The imitation model generation system can analyze a user's social media activity and prioritize recording relevant conversations. For example, conversations related to topics that the user is talking about on social media can be prioritized and recorded. By analyzing the user's posts and comments and identifying current topics of interest, highly relevant conversations can be recorded. In addition, the imitation model generation system can prioritize recording conversations with people the user follows on social media. By analyzing the user's follow data and identifying important people, highly relevant conversations can be recorded. Furthermore, the imitation model generation system can prioritize recording conversations related to groups the user participates in on social media. By analyzing the user's group participation data and identifying relevant conversations, highly relevant conversations can be recorded. In this way, relevant conversations can be recorded by analyzing the user's social media activity.

[0108] The imitation model generation system can estimate a user's emotions and adjust the conversation analysis method based on the estimated emotions. For example, if a user is sad, the analysis can be focused on the frequency of use of emotional words. By analyzing the user's voice data and detecting signs of sadness, an appropriate analysis method can be selected. Also, if a user is happy, the analysis can be focused on the frequency of use of positive words. By analyzing the user's facial expression data and detecting signs of joy, an appropriate analysis method can be selected. Furthermore, if a user is angry, the analysis can be focused on the frequency of use of aggressive words. By analyzing the user's heart rate data and detecting signs of anger, an appropriate analysis method can be selected. This allows for more accurate analysis by adjusting the language pattern analysis method based on the user's emotions.

[0109] The imitation model generation system can optimize the model update method by referencing the user's past conversation history. For example, it can select the optimal update algorithm based on past training data. By analyzing past training data and identifying effective update patterns, it can improve the accuracy of the model. It can also apply an update algorithm to improve the model accuracy from past training data. It can improve the model accuracy by optimizing parameter adjustments and feedback loops based on past data. Furthermore, by referencing past conversation history, it can prioritize model updates related to specific topics. By classifying past conversation data by topic and updating the model with an emphasis on data related to specific topics, it is possible to update the model according to the user's interests.

[0110] The imitation model generation system can estimate the user's emotions and adjust the model update frequency based on the estimated emotions. For example, if the user is sad, the emotional data is updated frequently. An appropriate update frequency can be selected by analyzing the user's voice data and detecting signs of sadness. Also, if the user is happy, the positive data can be updated frequently. An appropriate update frequency can be selected by analyzing the user's facial expression data and detecting signs of joy. Furthermore, if the user is angry, the aggressive data can be updated frequently. An appropriate update frequency can be selected by analyzing the user's heart rate data and detecting signs of anger. This allows the model update frequency to be adjusted based on the user's emotions, thereby updating the model at a more appropriate frequency.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The recording unit records personal conversations. Personal conversations include everyday conversations, business conversations, online chats, etc. The recording unit records the conversations using audio recordings, text recordings, audio recordings, etc., and collects detailed data such as the content, tone, and frequency of the conversations. For example, the tone of the conversation can be evaluated based on criteria such as emotional expression, pitch, and strength of voice. Step 2: The analyzer analyzes the data recorded by the recorder and learns language patterns and personality. The analyzer analyzes the usage of specific words and speaking characteristics, and analyzes language patterns based on criteria such as frequent phrases, grammatical structures, and vocabulary frequency. It can also evaluate personality based on criteria such as character traits, behavioral patterns, and psychological characteristics. Step 3: The updater updates the model based on the results learned by the analyzer. The updater continuously analyzes new data and can update the model at any frequency or timing, such as in real time, periodically, or event-driven.

[0113] 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.

[0114] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0115] 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.

[0116] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0131] 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.

[0132] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0147] 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.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0164] 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.

[0165] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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).

[0170] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0171] 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."

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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, in order to avoid confusion and to 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.

[0183] 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.

[0184] [Explanation of symbols]

[0185] 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 recording unit for recording individual conversations; an analysis unit that analyzes the data recorded by the recording unit and includes specific algorithms for learning language patterns and personalities; an update unit that updates the model based on the results learned by the analysis unit; A system characterized by:

2. The update unit Continually analyze new data and update the model 2. The system of claim 1.

3. The analysis unit Analyze specific word usage and speaking characteristics 2. The system of claim 1.

4. The recording unit Collect detailed data on the content, tone, and frequency of conversations 2. The system of claim 1.

5. Equipped with a hologram unit that generates 3D holograms for home use 2. The system of claim 1.

6. Equipped with a virtual grave section that provides virtual graves 2. The system of claim 1.

7. The recording unit Estimate the user's emotions and adjust the timing of recording conversations based on the estimated user emotions using a specific algorithm 2. The system of claim 1.

8. The recording unit Analyze the user's past conversation history and select the appropriate recording method 2. The system of claim 1.

9. The recording unit Filter conversations based on the user's current activity and interests when recording them 2. The system of claim 1.

10. The recording unit Estimate the user's emotions and prioritize the conversations to record based on the estimated user emotions.

2. The system of claim 1.

Images