System

Abstract

To reproduce a gesture and a conversation of a deceased pet and a deceased spouse, and to maintain emotional connection.SOLUTION: A system includes a first collection part, a first learning part, a first reproduction part, a second collection part, a second learning part, and a second reproduction part. The first collection part collects behavioral data of a pet. The first learning part analyzes the data collected by the first collection part, and learns the behavioral pattern of the pet. The first reproduction part reproduces the gesture and habit of the pet, based on the data learned by the first learning part. The second collection part collects conversational data with a spouse. The second learning part analyzes the data collected by the second collection part, and learns the conversational pattern and preference of the spouse. The second reproduction part reproduces the spouse based on the data learned by the second learning part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has the problem that it is not possible to reproduce the gestures or conversations of a deceased pet or spouse, making it difficult to maintain an emotional connection.

[0005] The system of the embodiment aims to reproduce the gestures and conversations of a deceased pet or spouse, thereby maintaining an emotional connection. [Means for solving the problem]

[0006] The system according to the embodiment includes a first collection unit, a first learning unit, a first reproducing unit, a second collection unit, a second learning unit, and a second reproducing unit. The first collection unit collects behavioral data of the pet. The first learning unit analyzes the data collected by the first collection unit and learns the behavioral patterns of the pet. The first reproducing unit reproduces the gestures and habits of the pet based on the data learned by the first learning unit. The second collection unit collects conversation data with the spouse. The second learning unit analyzes the data collected by the second collection unit and learns the conversation patterns and hobbies and interests of the spouse. The second reproducing unit reproduces the spouse based on the data learned by the second learning unit. Effect of the Invention

[0007] The system of the embodiment can reproduce the gestures and conversations of a deceased pet or spouse, allowing users to maintain an emotional connection. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention is a system that learns the behavior and conversation patterns of a pet or spouse before death and reproduces them with a robot even after death. This system collects behavioral data of a pet and learns the behavioral patterns using AI. Next, a robot that reproduces the gestures, characteristics, and habits of a pet is operated based on the learned data. Similarly, conversation data with a spouse is collected and conversation patterns and hobbies and preferences are learned using AI. Based on the learned data, a robot that reproduces the spouse conducts a conversation. In addition, in the event of the death of a user, it also has a function of contacting related parties. For example, a camera and a microphone are used to collect behavioral data of a pet. This allows the movement and sound of a pet to be recorded in detail. For example, images and sounds of a pet making a specific movement are collected and analyzed by AI. Next, the collected data is analyzed by AI to learn the behavioral patterns of the pet. AI understands the gestures, characteristics, and habits of a pet and generates an operating program to reproduce them. For example, it learns the timing and order of movements when a pet makes a specific movement and creates a program to reproduce them. Based on the learned data, a robot that reproduces the gestures, characteristics, and habits of the pet operates. For example, a robot that reproduces the movements of a pet when it makes a specific movement faithfully reproduces the movement. This allows you to enjoy the gestures and characteristics of the pet even after the death of the pet. Similarly, conversation data with the spouse is collected and analyzed by AI. For example, the content of conversations with the spouse and hobbies and interests are collected and analyzed by AI. The AI ​​learns the spouse's conversation patterns and hobbies and interests and generates a program to reproduce them. Based on the learned data, a robot that reproduces the spouse has a conversation. For example, a robot that reproduces the conversation pattern when the spouse talks about a specific topic faithfully reproduces the conversation. This allows you to enjoy the conversation even after the death of the spouse. In addition, it also has a function to contact related parties in the event of the user's death. For example, when a user dies, a system that automatically contacts related parties registered in advance is activated. This allows the related parties to be appropriately contacted even after the user's death. This allows the behavior and conversation patterns of the pet or spouse before death to be learned and reproduced by the robot even after death.

[0029] The reproduction system according to the embodiment includes a first collection unit, a first learning unit, a first reproduction unit, a second collection unit, a second learning unit, and a second reproduction unit. The first collection unit collects behavioral data of the pet. The behavioral data of the pet includes, for example, movements, cries, and eating patterns, but is not limited to such examples. The first collection unit collects behavioral data of the pet using, for example, a camera and a microphone. The camera captures the movements of the pet with high resolution, and the microphone records the cries of the pet with high sensitivity. For example, the first collection unit collects images and sounds of the pet when it makes a specific movement, which are then analyzed by AI. The first learning unit uses AI to analyze the collected behavioral data of the pet and learn the behavioral patterns of the pet. The AI ​​efficiently learns the behavioral patterns of the pet using, for example, technologies such as deep learning and neural networks. For example, the first learning unit learns the timing and order of actions of the pet when it makes a specific movement, and creates a program to reproduce them. The first reproducing unit executes an operation program that reproduces the gestures, characteristics, and habits of the pet based on the learned data. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. This allows the pet's gestures and characteristics to be enjoyed even after the pet's death. The second collecting unit collects conversation data with the spouse. The conversation data with the spouse includes, for example, daily conversations, conversations on specific topics, and the like, but is not limited to such examples. The second collecting unit collects conversation data with the spouse using, for example, a recording device. The recording device records the spouse's conversation with high sensitivity and saves it as digital data. The second learning unit uses AI to analyze the collected conversation data of the spouse and learns the spouse's conversation patterns and hobbies and interests. The AI ​​efficiently learns the spouse's conversation patterns and hobbies and interests using, for example, technologies such as deep learning and neural networks. For example, the second learning unit learns the conversation patterns of the spouse when talking about a specific topic and creates a program to reproduce them. The second reproducing unit executes an operation program that reproduces the spouse based on the learned data. For example, the second reenactment faithfully reproduces a conversation between spouses on a particular topic, allowing those conversations to be enjoyed even after the spouse's death.As a result, the reproduction system according to the embodiment can learn the behavior and conversation patterns of a pet or spouse while they were alive, and reproduce them using a robot even after their death.

[0030] The first collection unit collects the behavioral data of the pet. The behavioral data of the pet includes, for example, movements, cries, and eating patterns, but is not limited to such examples. The first collection unit collects the behavioral data of the pet using, for example, a camera and a microphone. The camera captures the movements of the pet in high resolution, and the microphone records the cries of the pet with high sensitivity. Specifically, the camera is positioned so that the movements of the pet can be captured from all directions of 360 degrees, and the movements of the pet can be recorded in detail no matter which direction the pet moves. The microphone collects not only the cries of the pet but also the surrounding environmental sounds, and provides data to understand the situation in which the pet is making cries. For example, the first collection unit collects video and audio when the pet makes a specific movement, and the AI ​​analyzes the video and audio. The collected data is transmitted to a cloud server in real time and used for subsequent analysis and learning. In addition, the first collection unit can periodically collect the behavioral data of the pet and track changes in the behavioral patterns over a long period of time. This makes it possible to detect abnormalities in the health condition and behavior of the pet early.

[0031] The first learning unit uses AI to analyze the collected pet behavior data and learn the pet's behavior patterns. The AI ​​efficiently learns the pet's behavior patterns, for example, using technologies such as deep learning and neural networks. Specifically, the AI ​​analyzes the collected video data frame by frame and extracts the characteristics of the pet's movements. For example, it learns the timing and order of movements when the pet makes a specific movement, and creates a program to reproduce it. The AI ​​identifies subtle differences in the pet's movements and understands the circumstances in which a specific movement is performed. In addition, the AI ​​analyzes the patterns of the pet's cries and learns what emotions and requests a specific cry expresses. This allows the first learning unit to grasp the pet's behavior patterns in detail and build a highly accurate model to reproduce them. The learned data is stored in a cloud server and updated and improved as necessary. This allows the first learning unit to always continue to learn the latest behavior patterns.

[0032] The first reproducing unit executes an operation program that reproduces the gestures, characteristics, and habits of the pet based on the learned data. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. Specifically, the robot controls motors and actuators that imitate the movement of the pet to reproduce the movement of the pet. For example, in order to reproduce the body angle, speed, and strength of the pet when it makes a specific movement, the robot adjusts the movement in conjunction with multiple sensors. Furthermore, the first reproducing unit faithfully reproduces the specific cry of the pet using a voice synthesis technology for reproducing the cry of the pet. This allows the behavior and characteristics of the pet to be enjoyed even after the death of the pet. The first reproducing unit fine-tunes the operation program based on the user's feedback to achieve a more natural and realistic reproduction. For example, when the user provides feedback on the pet's movement such as "I want it to move faster" or "The cry is a little different," the first reproducing unit reflects the feedback and improves the operation program. This allows the first reproducing unit to provide a high-quality reproduction that meets the user's expectations.

[0033] The second collection unit collects conversation data with the spouse. The conversation data with the spouse includes, for example, daily conversations, conversations on specific topics, and the like, but is not limited to such examples. The second collection unit collects conversation data with the spouse using, for example, a recording device. The recording device records the spouse's conversation with high sensitivity and saves it as digital data. Specifically, the recording device has a noise canceling function and removes ambient noise to collect clear voice data. Furthermore, the second collection unit can record not only the content of the conversation, but also the speaker's tone of voice and changes in emotion. For example, changes in tone of voice and emotion when the spouse talks about a specific topic are collected and analyzed by AI. The collected data is transmitted to a cloud server and used for subsequent analysis and learning. The second collection unit can periodically collect conversation data with the spouse and track changes in conversation patterns over a long period of time. This makes it possible to grasp changes in the spouse's hobbies and interests and achieve more accurate reproduction.

[0034] The second learning unit uses AI to analyze the collected conversation data of the spouse and learn the spouse's conversation patterns and hobbies and interests. The AI ​​efficiently learns the spouse's conversation patterns and hobbies and interests using technologies such as deep learning and neural networks. Specifically, the AI ​​analyzes the collected voice data and learns the spouse's way of speaking, how to choose words, and how to develop topics. For example, the second learning unit learns the conversation patterns of the spouse when talking about a specific topic and creates a program to reproduce them. The AI ​​analyzes the spouse's tone of voice and changes in emotions to understand in what situations certain emotions are expressed. In addition, the AI ​​learns the spouse's hobbies and interests and deepens its knowledge about specific topics. This allows the second learning unit to grasp the spouse's conversation patterns in detail and build a highly accurate model to reproduce them. The learned data is stored in a cloud server and updated and improved as necessary. This allows the second learning unit to always continue to learn the latest conversation patterns.

[0035] The second reproducing unit executes an operating program that reproduces the spouse based on the learned data. For example, the second reproducing unit faithfully reproduces a conversation when the spouse talks about a specific topic. Specifically, the second reproducing unit uses a voice synthesis technology to reproduce the spouse's voice and generate a conversation about the specific topic. For example, a voice synthesis engine is used to reproduce the tone of voice and changes in emotions when the spouse talks about a specific topic. Furthermore, the second reproducing unit uses a natural language processing technology to reproduce the spouse's way of speaking and choice of words to keep the flow of the conversation natural. This allows the spouse to enjoy the conversation even after the death of the spouse. The second reproducing unit can fine-tune the conversation program based on the user's feedback to achieve a more natural and realistic reproduction. For example, the user can provide feedback on the spouse's conversation such as "I want you to speak with more emotion" or "I want you to talk in more detail about a specific topic," and the second reproducing unit can improve the conversation program by reflecting the feedback. This allows the second reproducing unit to provide a high-quality reproduction that meets the user's expectations.

[0036] The first collection unit can collect the behavioral data of the pet using a camera and a microphone. It is necessary to clarify the specific type and installation method of the camera and microphone. For example, the camera has high resolution and can capture the movements of the pet in detail. The microphone has high sensitivity and can record the cries of the pet in detail. The first collection unit, for example, installs a camera in the pet's living space and monitors the movements of the pet 24 hours a day. Also, a microphone is installed in the pet's living space and records the cries of the pet constantly. This makes it possible to collect the behavioral data of the pet in detail. For example, the first collection unit collects video and audio when the pet makes a specific movement, and the AI ​​analyzes it. This makes it possible to collect the behavioral data of the pet in detail.

[0037] The first learning unit can learn the behavioral patterns of the pet using AI. It is necessary to clarify the specific technology and type of algorithm of AI. For example, technologies such as deep learning and neural network can be used. The first learning unit can efficiently learn the behavioral patterns of the pet using, for example, deep learning. Deep learning learns a large amount of data and has advanced pattern recognition capabilities. A neural network has a multi-layer network structure and can learn complex patterns. This allows the first learning unit to efficiently learn the behavioral patterns of the pet. For example, the first learning unit learns the timing and order of actions when the pet makes a specific movement and creates a program to reproduce it. This allows the pet's behavioral patterns to be efficiently learned.

[0038] The first reproducing unit can execute an operation program that reproduces the gestures, characteristics, and habits of the pet. It is necessary to clarify the specific contents and execution method of the operation program. For example, the structure of the program, the execution environment, etc. are clarified. The first reproducing unit executes, for example, a program that faithfully reproduces the behavior of the pet when it makes a specific movement. The program describes the pet's movements in detail, and the robot executes it. For example, the first reproducing unit executes a program that reproduces the timing and order of movements when the pet makes a specific movement. This allows the gestures, characteristics, and habits of the pet to be faithfully reproduced. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. This allows the gestures and characteristics of the pet to be enjoyed even after the pet's death.

[0039] The second collection unit can collect conversation data with the spouse. It is necessary to clarify the specific collection method and scope of the conversation data. For example, the recording method and the type of conversation to be collected are clarified. The second collection unit, for example, uses a recording device to collect conversation data with the spouse. The recording device records the spouse's conversation with high sensitivity and saves it as digital data. For example, the second collection unit collects daily conversations with the spouse and conversations on specific topics. This allows for detailed collection of conversation data with the spouse. For example, the second collection unit collects the content of conversations with the spouse and hobbies and interests, which are analyzed by AI. This allows for detailed collection of conversation data with the spouse.

[0040] The second learning unit can learn the conversation patterns and hobbies and interests of the spouse using AI. It is necessary to clarify the specific technology and type of algorithm of AI. For example, technologies such as deep learning and neural networks can be used. The second learning unit can efficiently learn the conversation patterns and hobbies and interests of the spouse using, for example, deep learning. Deep learning learns large amounts of data and has advanced pattern recognition capabilities. Neural networks have a multi-layer network structure and can learn complex patterns. This allows the second learning unit to efficiently learn the conversation patterns and hobbies and interests of the spouse. For example, the second learning unit learns the conversation patterns when the spouse talks about a specific topic and creates a program to reproduce them. This allows the conversation patterns and hobbies and interests of the spouse to be efficiently learned.

[0041] The second reproducing unit can execute an operating program that reproduces the spouse. It is necessary to clarify the specific contents and execution method of the operating program. For example, the program structure, execution environment, etc. are clarified. The second reproducing unit executes, for example, a program that faithfully reproduces a conversation when the spouse speaks about a specific topic. The program describes the spouse's conversation in detail, and the robot executes it. For example, the second reproducing unit executes a program that reproduces the conversation pattern when the spouse speaks about a specific topic. This makes it possible to faithfully reproduce the spouse's conversation and behavior. For example, the second reproducing unit faithfully reproduces a conversation when the spouse speaks about a specific topic. This makes it possible to enjoy the conversation even after the spouse's death.

[0042] The first collection unit can estimate the pet's emotion and adjust the timing of collecting behavioral data based on the estimated pet's emotion. For example, the first collection unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first collection unit calculates an emotion score based on the change in facial expression. The first collection unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first collection unit analyzes the tone and speed of the voice and calculates the emotion score. The first collection unit can also collect the pet's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first collection unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to collect behavioral data at an optimal timing according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the first collection unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0043] The first collection unit can analyze the past behavior history of the pet and select the optimal collection method. For example, the first collection unit acquires the past behavior history of the pet from a database and analyzes it using AI. For example, the first collection unit determines the priority of data to be collected based on the behavior that the pet frequently performed in the past. The first collection unit can also analyze the past behavior pattern of the pet and select the optimal method for collecting a specific behavior. For example, the first collection unit selects data to be collected in a specific time period from the past behavior history of the pet. This makes it possible to select the optimal collection method based on the past behavior history of the pet. A part or all of the above-mentioned processing in the first collection unit may be performed using AI, for example, or may be performed without using AI. For example, the first collection unit can input the past behavior history data of the pet to the generation AI and cause the generation AI to select the optimal collection method.

[0044] The first collection unit can perform filtering based on the pet's current health condition and environment when collecting behavioral data. For example, the first collection unit monitors the pet's health condition with a sensor and collects behavioral data when the pet's health condition is good. For example, the first collection unit measures the pet's body temperature and heart rate with a sensor and evaluates the health condition. The first collection unit can also monitor the pet's environment with a sensor and collect behavioral data when the environment is stable. For example, the first collection unit measures the temperature and humidity of the pet's living space with a sensor and evaluates the stability of the environment. This makes it possible to collect only important data based on the pet's health condition and environment. A part or all of the above-mentioned processing in the first collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the first collection unit can input the pet's health condition and environmental data to the generation AI and cause the generation AI to perform filtering.

[0045] The first collection unit can estimate the pet's emotion and determine the priority of the behavioral data to be collected based on the estimated pet's emotion. For example, the first collection unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first collection unit calculates an emotion score based on the change in facial expression. The first collection unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first collection unit analyzes the tone and speed of the voice and calculates the emotion score. The first collection unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first collection unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the behavioral data to be collected according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the first collection unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0046] The first collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the pet when collecting behavioral data. For example, the first collection unit acquires the geographical location information of the pet by a GPS device, and preferentially collects highly relevant data. For example, when the pet is in a specific location, the first collection unit preferentially collects behavioral data at the location. In addition, when the pet is moving, the first collection unit can also preferentially collect behavioral data during movement. For example, when the pet is in a specific location, the first collection unit preferentially collects behavioral data at the location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the pet. A part or all of the above-mentioned processing in the first collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the first collection unit can input the geographical location information data of the pet to the generation AI, and cause the generation AI to execute the priority order of highly relevant data.

[0047] The first collection unit can analyze the social media activity of the pet owner when collecting the behavioral data, and collect related data. For example, the first collection unit analyzes photos and videos of the pet posted by the pet owner on social media, and collects related behavioral data. For example, the first collection unit analyzes comments on the pet's behavior posted by the owner on social media, and collects related behavioral data. The first collection unit can also analyze information on the pet's behavior posted by the owner on social media, and collect related behavioral data. For example, the first collection unit analyzes information on the pet's behavior posted by the owner on social media, and collects related behavioral data. This makes it possible to collect related data based on the owner's social media activity. A part or all of the above-mentioned processing in the first collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the first collection unit can input the owner's social media activity data to the generation AI, and cause the generation AI to execute collection of related data.

[0048] The first learning unit can estimate the pet's emotion and adjust the behavior pattern learning method based on the estimated pet's emotion. For example, the first learning unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first learning unit calculates an emotion score based on the change in facial expression. The first learning unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first learning unit analyzes the tone and speed of the voice and calculates the emotion score. The first learning unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first learning unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to adjust the behavior pattern learning method according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0049] The first learning unit can adjust the level of detail of the learning based on the importance of the pet's behavior during learning. The first learning unit, for example, evaluates the importance of the pet's behavior and learns important behavior patterns in detail. For example, the first learning unit evaluates the importance of the behavior based on the frequency and impact of the pet's behavior. The first learning unit can also simply learn behavior patterns with low importance. For example, the first learning unit adjusts the level of detail of the learning based on the importance of the pet's behavior. This makes it possible to adjust the level of detail of the learning based on the importance of the pet's behavior. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit can input the pet's behavior data to the generation AI and cause the generation AI to evaluate the importance of the behavior and adjust the level of detail of the learning.

[0050] The first learning unit can apply different learning algorithms depending on the type and age of the pet during learning. The first learning unit applies different learning algorithms depending on, for example, the type of pet. For example, the first learning unit applies optimal learning algorithms to different types of pets such as dogs and cats. The first learning unit can also apply different learning algorithms depending on the age of the pet. For example, the first learning unit applies optimal learning algorithms to young pets and old pets. This makes it possible to apply optimal learning algorithms depending on the type and age of the pet. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit can input data on the type and age of the pet to the generation AI and cause the generation AI to apply the optimal learning algorithm.

[0051] The first learning unit can estimate the pet's emotion and determine the learning priority based on the estimated pet's emotion. For example, the first learning unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first learning unit calculates an emotion score based on the change in facial expression. The first learning unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first learning unit analyzes the tone and speed of the voice and calculates the emotion score. The first learning unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first learning unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the learning priority according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0052] The first learning unit can weight the learning based on the collection time of the pet's behavior data during learning. The first learning unit, for example, acquires the collection time of the pet's behavior data from a database and analyzes it using AI. For example, the first learning unit weights the learning based on the collection time of the pet's behavior data. For example, the first learning unit weights the learning based on the collection time of the pet's behavior data. This allows the learning to be weighted based on the collection time of the pet's behavior data. A part or all of the above-mentioned processing in the first learning unit may be performed using AI, for example, or may be performed without using AI. For example, the first learning unit can input collection time data of the pet's behavior data to the generation AI and cause the generation AI to perform the weighting of the learning.

[0053] The first learning unit can improve the accuracy of learning by referring to pet-related literature during learning. The first learning unit, for example, acquires pet-related literature from a database and analyzes it using AI. For example, the first learning unit improves the accuracy of learning by referring to pet-related literature. For example, the first learning unit improves the accuracy of learning by referring to pet-related literature. As a result, the accuracy of learning can be improved by referring to pet-related literature. A part or all of the above-mentioned processing in the first learning unit may be performed using AI, for example, or may be performed without using AI. For example, the first learning unit can input pet-related literature data to the generation AI and cause the generation AI to execute improvement of the accuracy of learning.

[0054] The first reproducing unit can estimate the emotion of the pet and adjust the timing of the action to be reproduced based on the estimated emotion of the pet. For example, the first reproducing unit captures the facial expression of the pet with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first reproducing unit can calculate an emotion score based on the change in facial expression. The first reproducing unit can also record the voice of the pet and estimate the emotion using a voice analysis technology. For example, the first reproducing unit analyzes the tone and speed of the voice and calculates an emotion score. The first reproducing unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first reproducing unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to reproduce the action at an optimal timing according to the emotion of the pet. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the first reproducing unit may input image data of a pet taken by a camera to the generating AI and cause the generating AI to estimate the pet's emotions.

[0055] The first reproducing unit can select the optimal reproduction method by referring to the past behavioral patterns of the pet at the time of reproduction. For example, the first reproducing unit acquires the past behavioral patterns of the pet from a database and analyzes them using AI. For example, the first reproducing unit selects the optimal reproduction method by referring to the past behavioral patterns of the pet. For example, the first reproducing unit selects the optimal reproduction method by referring to the past behavioral patterns of the pet. This makes it possible to select the optimal reproduction method based on the past behavioral patterns of the pet. A part or all of the above-mentioned processing in the first reproducing unit may be performed, for example, using AI, or may be performed without using AI. For example, the first reproducing unit can input the past behavioral pattern data of the pet to the generating AI and cause the generating AI to select the optimal reproduction method.

[0056] The first reproducing unit can customize the operation program based on the pet's current environment at the time of reproduction. The first reproducing unit, for example, monitors the pet's current environment with a sensor and customizes the operation program based on the environmental data. For example, the first reproducing unit measures the temperature and humidity of the pet's living space with a sensor and evaluates the stability of the environment. The first reproducing unit can also monitor the situation around the pet with a sensor and customize the operation program. For example, the first reproducing unit customizes the operation program based on the situation of the pet's living space. This makes it possible to customize the operation program based on the pet's current environment. A part or all of the above-mentioned processing in the first reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the first reproducing unit can input the pet's environmental data to the generating AI and cause the generating AI to execute customization of the operation program.

[0057] The first reproducing unit can estimate the emotion of the pet and determine the priority of the actions to be reproduced based on the estimated emotion of the pet. For example, the first reproducing unit captures the facial expression of the pet with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first reproducing unit calculates an emotion score based on the change in the facial expression. The first reproducing unit can also record the voice of the pet and estimate the emotion using a voice analysis technology. For example, the first reproducing unit analyzes the tone and speed of the voice and calculates the emotion score. The first reproducing unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first reproducing unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the actions to be reproduced according to the emotion of the pet. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the first reproducing unit may input image data of a pet taken by a camera to the generating AI and cause the generating AI to estimate the pet's emotions.

[0058] The first reproducing unit can select an optimal reproduction method in consideration of the geographical location information of the pet at the time of reproduction. For example, the first reproducing unit acquires the geographical location information of the pet by a GPS device and preferentially collects highly relevant data. For example, when the pet is in a specific location, the first reproducing unit preferentially collects behavioral data at that location. Also, when the pet is moving, the first reproducing unit can preferentially collect behavioral data during the movement. For example, when the pet is in a specific location, the first reproducing unit preferentially collects behavioral data at that location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the pet. A part or all of the above-mentioned processing in the first reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the first reproducing unit can input the geographical location information data of the pet to the generating AI and cause the generating AI to execute the priority order of highly relevant data.

[0059] At the time of reproduction, the first reproduction unit can analyze the social media activity of the pet owner and suggest a means of reproduction. For example, the first reproduction unit analyzes photos and videos of the pet posted by the pet owner on social media and collects related behavioral data. For example, the first reproduction unit analyzes comments on the pet's behavior posted by the owner on social media and collects related behavioral data. The first reproduction unit can also analyze information on the pet's behavior posted by the owner on social media and collect related behavioral data. For example, the first reproduction unit analyzes information on the pet's behavior posted by the owner on social media and collects related behavioral data. This makes it possible to collect related data based on the owner's social media activity. A part or all of the above-mentioned processing in the first reproduction unit may be performed, for example, using AI or may be performed without using AI. For example, the first reproduction unit can input the owner's social media activity data to the generation AI and cause the generation AI to collect related data.

[0060] The second collection unit can estimate the spouse's emotion and adjust the timing of collecting conversation data based on the estimated spouse's emotion. For example, the second collection unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second collection unit calculates an emotion score based on the change in facial expression. The second collection unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second collection unit analyzes the tone and speed of the voice and calculates an emotion score. The second collection unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second collection unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to collect conversation data at an optimal timing according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the second collection unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's emotions.

[0061] The second collection unit can analyze the spouse's past conversation history and select the optimal collection method. For example, the second collection unit acquires the spouse's past conversation history from a database and analyzes it using AI. For example, the second collection unit determines the priority of data to be collected based on conversations that the spouse frequently had in the past. The second collection unit can also analyze the spouse's past conversation patterns and select the optimal method for collecting a specific conversation. For example, the second collection unit selects data to be collected in a specific time period from the spouse's past conversation history. This makes it possible to select the optimal collection method based on the spouse's past conversation history. A part or all of the above-mentioned processing in the second collection unit may be performed using AI, for example, or may be performed without using AI. For example, the second collection unit can input the spouse's past conversation history data to the generation AI and cause the generation AI to select the optimal collection method.

[0062] The second collection unit can perform filtering based on the spouse's current living situation and areas of interest when collecting conversation data. For example, the second collection unit monitors the spouse's living situation with a sensor and collects conversation data when the living situation is stable. For example, the second collection unit evaluates the living situation based on the spouse's occupation and daily activities. The second collection unit can also obtain the spouse's areas of interest from a database and filter the conversation data to be collected based on the areas of interest. For example, the second collection unit filters the conversation data to be collected based on the spouse's hobbies and interests. This makes it possible to collect only important data based on the spouse's living situation and areas of interest. A part or all of the above-mentioned processing in the second collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the second collection unit can input the spouse's living situation and areas of interest data to the generation AI and cause the generation AI to perform filtering.

[0063] The second collection unit can estimate the spouse's emotion and determine the priority of the conversation data to be collected based on the estimated spouse's emotion. For example, the second collection unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second collection unit calculates an emotion score based on the change in facial expression. The second collection unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second collection unit analyzes the tone and speed of the voice and calculates the emotion score. The second collection unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second collection unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the conversation data to be collected according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the second collection unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's emotions.

[0064] When collecting conversation data, the second collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the spouse. For example, the second collection unit acquires the geographical location information of the spouse by a GPS device, and preferentially collects highly relevant data. For example, when the spouse is in a specific location, the second collection unit preferentially collects conversation data at that location. In addition, when the spouse is moving, the second collection unit can also preferentially collect conversation data during the movement. For example, when the spouse is in a specific location, the second collection unit preferentially collects conversation data at that location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the spouse. A part or all of the above-mentioned processing in the second collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the second collection unit can input the geographical location information data of the spouse to the generation AI, and cause the generation AI to execute the priority order of highly relevant data.

[0065] The second collection unit can analyze the social media activity of the spouse when collecting the conversation data and collect related data. For example, the second collection unit analyzes the content of the conversation posted by the spouse on social media and collects related conversation data. For example, the second collection unit analyzes comments on hobbies and interests posted by the spouse on social media and collects related conversation data. The second collection unit can also analyze information on the conversation posted by the spouse on social media and collect related conversation data. For example, the second collection unit analyzes information on the conversation posted by the spouse on social media and collects related conversation data. This makes it possible to collect related data based on the social media activity of the spouse. A part or all of the above-mentioned processing in the second collection unit may be performed, for example, using AI or may be performed without using AI. For example, the second collection unit can input the social media activity data of the spouse to the generation AI and cause the generation AI to execute collection of related data.

[0066] The second learning unit can estimate the spouse's emotion and adjust the learning method of the conversation pattern based on the estimated spouse's emotion. For example, the second learning unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second learning unit calculates an emotion score based on the change in facial expression. The second learning unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second learning unit analyzes the tone and speed of the voice and calculates the emotion score. The second learning unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second learning unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to adjust the learning method of the conversation pattern according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the second learning unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's emotions.

[0067] The second learning unit can adjust the level of detail of the learning based on the importance of the spouse's conversation during learning. The second learning unit, for example, evaluates the importance of the spouse's conversation and learns important conversation patterns in detail. For example, the second learning unit evaluates the importance of the conversation based on the frequency of the spouse's conversation and the importance of the content. The second learning unit can also simply learn conversation patterns with low importance. For example, the second learning unit adjusts the level of detail of the learning based on the importance of the spouse's conversation. This makes it possible to adjust the level of detail of the learning based on the importance of the spouse's conversation. A part or all of the above-mentioned processing in the second learning unit may be performed, for example, using AI or may be performed without using AI. For example, the second learning unit can input spouse's conversation data to the generation AI and cause the generation AI to evaluate the importance of the conversation and adjust the level of detail of the learning.

[0068] The second learning unit can apply different learning algorithms depending on the hobbies and interests of the spouse during learning. The second learning unit applies different learning algorithms depending on, for example, the hobbies of the spouse. For example, the second learning unit applies an optimal learning algorithm depending on the hobbies and interests of the spouse. This makes it possible to apply an optimal learning algorithm depending on the hobbies and interests of the spouse. A part or all of the above-mentioned processing in the second learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the second learning unit can input the hobby and interest data of the spouse to the generation AI and cause the generation AI to apply the optimal learning algorithm.

[0069] The second learning unit can estimate the spouse's emotion and determine the learning priority based on the spouse's estimated emotion. For example, the second learning unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second learning unit calculates an emotion score based on the change in facial expression. The second learning unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second learning unit analyzes the tone and speed of the voice and calculates the emotion score. The second learning unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second learning unit calculates the emotion score based on the heart rate fluctuation. This makes it possible to determine the learning priority according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the second learning unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's emotions.

[0070] The second learning unit can weight the learning based on the collection time of the spouse's conversation data during learning. The second learning unit, for example, acquires the collection time of the spouse's conversation data from a database and analyzes it using AI. For example, the second learning unit weights the learning based on the collection time of the spouse's conversation data. For example, the second learning unit weights the learning based on the collection time of the spouse's conversation data. This makes it possible to weight the learning based on the collection time of the spouse's conversation data. A part or all of the above-mentioned processing in the second learning unit may be performed using AI, for example, or may be performed without using AI. For example, the second learning unit can input collection time data of the spouse's conversation data to the generation AI and cause the generation AI to perform the weighting of the learning.

[0071] The second learning unit can improve the accuracy of the learning by referring to the spouse's related literature during learning. The second learning unit, for example, acquires the spouse's related literature from a database and analyzes it using AI. For example, the second learning unit improves the accuracy of the learning by referring to the spouse's related literature. For example, the second learning unit improves the accuracy of the learning by referring to the spouse's related literature. As a result, the accuracy of the learning can be improved by referring to the spouse's related literature. A part or all of the above-mentioned processing in the second learning unit may be performed using AI, for example, or may be performed without using AI. For example, the second learning unit can input the spouse's related literature data to the generation AI and cause the generation AI to execute the improvement of the learning accuracy.

[0072] The second reproducing unit can estimate the emotion of the spouse and adjust the timing of the conversation to be reproduced based on the estimated emotion of the spouse. For example, the second reproducing unit captures the facial expression of the spouse with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second reproducing unit calculates an emotion score based on the change in the facial expression. The second reproducing unit can also record the voice of the spouse and estimate the emotion using a voice analysis technique. For example, the second reproducing unit analyzes the tone and speed of the voice and calculates an emotion score. The second reproducing unit can also collect the biological data of the spouse (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second reproducing unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to reproduce the conversation at an optimal timing according to the emotion of the spouse. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the second reproducing unit may input image data of the spouse taken by a camera to the generating AI, and cause the generating AI to estimate the spouse's emotions.

[0073] The second reproducing unit can select the optimal reproduction method by referring to the spouse's past conversation patterns at the time of reproduction. The second reproducing unit, for example, acquires the spouse's past conversation patterns from a database and analyzes them using AI. For example, the second reproducing unit selects the optimal reproduction method by referring to the spouse's past conversation patterns. For example, the second reproducing unit selects the optimal reproduction method by referring to the spouse's past conversation patterns. This makes it possible to select the optimal reproduction method based on the spouse's past conversation patterns. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI, or may be performed without using AI. For example, the second reproducing unit can input the spouse's past conversation pattern data to the generating AI and cause the generating AI to select the optimal reproduction method.

[0074] The second reproducing unit can customize the conversation program based on the spouse's current living situation at the time of reproduction. The second reproducing unit, for example, monitors the spouse's current living situation with a sensor and customizes the conversation program based on the living situation data. For example, the second reproducing unit evaluates the living situation based on the spouse's occupation and daily activities. The second reproducing unit can also monitor the spouse's surroundings with a sensor and customize the conversation program. For example, the second reproducing unit customizes the conversation program based on the situation of the spouse's living space. This makes it possible to customize the conversation program based on the spouse's current living situation. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the second reproducing unit can input the spouse's living situation data to the generating AI and cause the generating AI to customize the conversation program.

[0075] The second reproducing unit can estimate the emotion of the spouse and determine the priority of the conversation to be reproduced based on the estimated emotion of the spouse. For example, the second reproducing unit captures the facial expression of the spouse with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second reproducing unit can calculate an emotion score based on the change in the facial expression. The second reproducing unit can also record the voice of the spouse and estimate the emotion using a voice analysis technique. For example, the second reproducing unit analyzes the tone and speed of the voice and calculates an emotion score. The second reproducing unit can also collect the biological data of the spouse (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second reproducing unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the conversation to be reproduced according to the emotion of the spouse. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the second reproducing unit may input image data of the spouse taken by a camera to the generating AI, and cause the generating AI to estimate the spouse's emotions.

[0076] The second reproducing unit can select an optimal reproduction method in consideration of the geographical location information of the spouse at the time of reproduction. For example, the second reproducing unit acquires the geographical location information of the spouse by a GPS device and preferentially collects highly relevant data. For example, when the spouse is in a specific location, the second reproducing unit preferentially collects conversation data at that location. In addition, when the spouse is moving, the second reproducing unit can also preferentially collect conversation data during the movement. For example, when the spouse is in a specific location, the second reproducing unit preferentially collects conversation data at that location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the spouse. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the second reproducing unit can input the geographical location information data of the spouse to the generating AI and cause the generating AI to execute the priority order of highly relevant data.

[0077] The second reproducing unit can analyze the spouse's social media activity at the time of reproduction and suggest a means of reproduction. The second reproducing unit, for example, analyzes the content of the conversation posted by the spouse on social media and collects related conversation data. For example, the second reproducing unit analyzes comments on hobbies and interests posted by the spouse on social media and collects related conversation data. The second reproducing unit can also analyze information on the conversation posted by the spouse on social media and collect related conversation data. For example, the second reproducing unit analyzes information on the conversation posted by the spouse on social media and collects related conversation data. This makes it possible to collect related data based on the spouse's social media activity. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the second reproducing unit can input the spouse's social media activity data to the generating AI and cause the generating AI to collect related data.

[0078] The communication unit can estimate the user's emotion and adjust the timing of contact based on the estimated user's emotion. The communication unit, for example, captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the communication unit calculates an emotion score based on the change in facial expression. The communication unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the communication unit analyzes the tone and speed of the voice and calculates the emotion score. The communication unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the communication unit calculates the emotion score based on the fluctuation of the heart rate. This allows the user to contact the user at the optimal timing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0079] The contact unit can select the optimal contact method by referring to the user's past contact history at the time of contact. The contact unit, for example, acquires the user's past contact history from a database and analyzes it using AI. For example, the contact unit selects the optimal contact method by referring to the user's past contact history. For example, the contact unit selects a specific contact method based on the user's past contact history. This makes it possible to select the optimal contact method based on the user's past contact history. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI, or may be performed without using AI. For example, the contact unit can input the user's past contact history data to the generation AI and cause the generation AI to select the optimal contact method.

[0080] The communication unit can estimate the user's emotion and determine the priority of the contact based on the estimated user's emotion. The communication unit, for example, captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the communication unit calculates an emotion score based on the change in the facial expression. The communication unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the communication unit analyzes the tone and speed of the voice and calculates the emotion score. The communication unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the communication unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the contact according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0081] The contact unit can select the optimal contact method in consideration of the geographical location information of the user at the time of contact. For example, the contact unit acquires the geographical location information of the user using a GPS device, and preferentially collects highly relevant data. For example, when the user is in a specific location, the contact unit preferentially selects a contact method at that location. In addition, when the user is moving, the contact unit can also preferentially select a contact method during movement. For example, when the user is in a specific location, the contact unit preferentially selects a contact method at that location. This makes it possible to select a highly relevant contact method based on the geographical location information of the user. Part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI, or may be performed without using AI. For example, the contact unit can input the geographical location information data of the user to the generation AI, and cause the generation AI to select a highly relevant contact method.

[0082] The contact unit can select the optimal contact method by analyzing the user's social media activity at the time of contact. The contact unit, for example, analyzes the content posted by the user on social media and selects a related contact method. For example, the contact unit analyzes comments on hobbies and interests posted by the user on social media and selects a related contact method. The contact unit can also analyze information posted by the user on social media and select a related contact method. For example, the contact unit analyzes information posted by the user on social media and selects a related contact method. This makes it possible to select a related contact method based on the user's social media activity. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI or may be performed without using AI. For example, the contact unit can input the user's social media activity data to the generation AI and cause the generation AI to select a related contact method.

[0083] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0084] When collecting the behavioral data of the pet, the first collection unit can monitor the health condition of the pet and collect data when the health condition is good. For example, the pet's body temperature and heart rate are measured by a sensor to evaluate the health condition. The pet's environment can also be monitored by a sensor and behavioral data can be collected when the environment is stable. This makes it possible to collect only important data based on the pet's health condition and environment. Furthermore, the first collection unit can also preferentially collect highly relevant data in consideration of the geographical location information of the pet. For example, when the pet is in a specific location, behavioral data at that location can be preferentially collected. Also, when the pet is moving, behavioral data during the movement can be preferentially collected. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the pet.

[0085] When learning the behavioral patterns of a pet, the first learning unit can apply different learning algorithms depending on the type and age of the pet. For example, the optimal learning algorithm is applied to different types of pets such as dogs and cats. Also, the optimal learning algorithm can be applied to young pets and old pets. This makes it possible to apply the optimal learning algorithm depending on the type and age of the pet. Furthermore, the first learning unit can adjust the level of detail of the learning based on the importance of the pet's behavior. For example, the importance of the behavior is evaluated based on the frequency and impact of the pet's behavior, and important behavioral patterns are learned in detail. Also, it is possible to simply learn behavioral patterns with low importance. This makes it possible to adjust the level of detail of the learning based on the importance of the pet's behavior.

[0086] The first reproducing unit can customize the operation program based on the pet's current environment when reproducing the pet's gestures, characteristics, and habits. For example, the temperature and humidity of the pet's living space are measured by a sensor to evaluate the stability of the environment. The operation program can also be customized by monitoring the pet's surroundings with a sensor. This allows the operation program to be customized based on the pet's current environment. Furthermore, the first reproducing unit can also select the optimal reproduction method by referring to the pet's past behavioral patterns. For example, the pet's past behavioral patterns are obtained from a database and analyzed using AI. This allows the optimal reproduction method to be selected based on the pet's past behavioral patterns.

[0087] When collecting conversation data with a spouse, the second collection unit can filter the conversation data based on the spouse's living situation and areas of interest. For example, the living situation is evaluated based on the spouse's occupation and daily activities, and conversation data is collected when the living situation is stable. The conversation data to be collected can also be filtered based on the spouse's hobbies and interests. This makes it possible to collect only important data based on the spouse's living situation and areas of interest. Furthermore, the second collection unit can preferentially collect highly relevant data in consideration of the spouse's geographical location information. For example, when the spouse is in a specific location, conversation data at that location can be preferentially collected. Also, when the spouse is on the move, conversation data during the move can be preferentially collected. This makes it possible to preferentially collect highly relevant data based on the spouse's geographical location information.

[0088] The process flow of the first embodiment will be briefly described below.

[0089] Step 1: The first collection unit collects behavioral data of the pet. The behavioral data of the pet includes, but is not limited to, movements, cries, and eating patterns. The first collection unit collects the behavioral data of the pet using, for example, a camera and a microphone. The camera captures the movements of the pet with high resolution, and the microphone records the cries of the pet with high sensitivity. Step 2: The first learning unit uses AI to analyze the collected pet behavior data and learn the pet's behavior patterns. The AI ​​efficiently learns the pet's behavior patterns using technologies such as deep learning and neural networks. For example, the first learning unit learns the timing and sequence of actions when the pet makes a specific movement and creates a program to reproduce it. Step 3: The first reproducing unit executes an action program that reproduces the pet's gestures, characteristics, and habits based on the learned data. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. This allows you to enjoy the gestures and characteristics of your pet even after it has died. Step 4: The second collection unit collects conversation data with the spouse. The conversation data with the spouse includes, but is not limited to, for example, daily conversations and conversations on specific topics. The second collection unit collects conversation data with the spouse using, for example, a recording device. The recording device records the spouse's conversation with high sensitivity and stores it as digital data. Step 5: The second learning unit uses AI to analyze the collected conversation data of the spouse and learn the spouse's conversation patterns and hobbies and interests. The AI ​​efficiently learns the spouse's conversation patterns and hobbies and interests using technologies such as deep learning and neural networks. For example, the second learning unit learns the conversation patterns of the spouse when talking about a specific topic and creates a program to reproduce them. Step 6: The second reproducing unit executes an operation program for reproducing the spouse based on the learned data. For example, the second reproducing unit faithfully reproduces the conversation of the spouse when talking about a specific topic. This allows the spouse to enjoy the conversation even after the death of the spouse.

[0090] (Example 2) The system according to the embodiment of the present invention is a system that learns the behavior and conversation patterns of a pet or spouse before death and reproduces them with a robot even after death. This system collects behavioral data of a pet and learns the behavioral patterns using AI. Next, a robot that reproduces the gestures, characteristics, and habits of a pet is operated based on the learned data. Similarly, conversation data with a spouse is collected and conversation patterns and hobbies and preferences are learned using AI. Based on the learned data, a robot that reproduces the spouse conducts a conversation. In addition, in the event of the death of a user, it also has a function of contacting related parties. For example, a camera and a microphone are used to collect behavioral data of a pet. This allows the movement and sound of a pet to be recorded in detail. For example, images and sounds of a pet making a specific movement are collected and analyzed by AI. Next, the collected data is analyzed by AI to learn the behavioral patterns of the pet. AI understands the gestures, characteristics, and habits of a pet and generates an operating program to reproduce them. For example, it learns the timing and order of movements when a pet makes a specific movement and creates a program to reproduce them. Based on the learned data, a robot that reproduces the gestures, characteristics, and habits of the pet operates. For example, a robot that reproduces the movements of a pet when it makes a specific movement faithfully reproduces the movement. This allows you to enjoy the gestures and characteristics of the pet even after the death of the pet. Similarly, conversation data with the spouse is collected and analyzed by AI. For example, the content of conversations with the spouse and hobbies and interests are collected and analyzed by AI. The AI ​​learns the spouse's conversation patterns and hobbies and interests and generates a program to reproduce them. Based on the learned data, a robot that reproduces the spouse has a conversation. For example, a robot that reproduces the conversation pattern when the spouse talks about a specific topic faithfully reproduces the conversation. This allows you to enjoy the conversation even after the death of the spouse. In addition, it also has a function to contact related parties in the event of the user's death. For example, when a user dies, a system that automatically contacts related parties registered in advance is activated. This allows the related parties to be appropriately contacted even after the user's death. This allows the behavior and conversation patterns of the pet or spouse before death to be learned and reproduced by the robot even after death.

[0091] The reproduction system according to the embodiment includes a first collection unit, a first learning unit, a first reproduction unit, a second collection unit, a second learning unit, and a second reproduction unit. The first collection unit collects behavioral data of the pet. The behavioral data of the pet includes, for example, movements, cries, and eating patterns, but is not limited to such examples. The first collection unit collects behavioral data of the pet using, for example, a camera and a microphone. The camera captures the movements of the pet with high resolution, and the microphone records the cries of the pet with high sensitivity. For example, the first collection unit collects images and sounds of the pet when it makes a specific movement, which are then analyzed by AI. The first learning unit uses AI to analyze the collected behavioral data of the pet and learn the behavioral patterns of the pet. The AI ​​efficiently learns the behavioral patterns of the pet using, for example, technologies such as deep learning and neural networks. For example, the first learning unit learns the timing and order of actions of the pet when it makes a specific movement, and creates a program to reproduce them. The first reproducing unit executes an operation program that reproduces the gestures, characteristics, and habits of the pet based on the learned data. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. This allows the pet's gestures and characteristics to be enjoyed even after the pet's death. The second collecting unit collects conversation data with the spouse. The conversation data with the spouse includes, for example, daily conversations, conversations on specific topics, and the like, but is not limited to such examples. The second collecting unit collects conversation data with the spouse using, for example, a recording device. The recording device records the spouse's conversation with high sensitivity and saves it as digital data. The second learning unit uses AI to analyze the collected conversation data of the spouse and learns the spouse's conversation patterns and hobbies and interests. The AI ​​efficiently learns the spouse's conversation patterns and hobbies and interests using, for example, technologies such as deep learning and neural networks. For example, the second learning unit learns the conversation patterns of the spouse when talking about a specific topic and creates a program to reproduce them. The second reproducing unit executes an operation program that reproduces the spouse based on the learned data. For example, the second reenactment faithfully reproduces a conversation between spouses on a particular topic, allowing those conversations to be enjoyed even after the spouse's death.As a result, the reproduction system according to the embodiment can learn the behavior and conversation patterns of a pet or spouse while they were alive, and reproduce them using a robot even after their death.

[0092] The first collection unit collects the behavioral data of the pet. The behavioral data of the pet includes, for example, movements, cries, and eating patterns, but is not limited to such examples. The first collection unit collects the behavioral data of the pet using, for example, a camera and a microphone. The camera captures the movements of the pet in high resolution, and the microphone records the cries of the pet with high sensitivity. Specifically, the camera is positioned so that the movements of the pet can be captured from all directions of 360 degrees, and the movements of the pet can be recorded in detail no matter which direction the pet moves. The microphone collects not only the cries of the pet but also the surrounding environmental sounds, and provides data to understand the situation in which the pet is making cries. For example, the first collection unit collects video and audio when the pet makes a specific movement, and the AI ​​analyzes the video and audio. The collected data is transmitted to a cloud server in real time and used for subsequent analysis and learning. In addition, the first collection unit can periodically collect the behavioral data of the pet and track changes in the behavioral patterns over a long period of time. This makes it possible to detect abnormalities in the health condition and behavior of the pet early.

[0093] The first learning unit uses AI to analyze the collected pet behavior data and learn the pet's behavior patterns. The AI ​​efficiently learns the pet's behavior patterns, for example, using technologies such as deep learning and neural networks. Specifically, the AI ​​analyzes the collected video data frame by frame and extracts the characteristics of the pet's movements. For example, it learns the timing and order of movements when the pet makes a specific movement, and creates a program to reproduce it. The AI ​​identifies subtle differences in the pet's movements and understands the circumstances in which a specific movement is performed. In addition, the AI ​​analyzes the patterns of the pet's cries and learns what emotions and requests a specific cry expresses. This allows the first learning unit to grasp the pet's behavior patterns in detail and build a highly accurate model to reproduce them. The learned data is stored in a cloud server and updated and improved as necessary. This allows the first learning unit to always continue to learn the latest behavior patterns.

[0094] The first reproducing unit executes an operation program that reproduces the gestures, characteristics, and habits of the pet based on the learned data. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. Specifically, the robot controls motors and actuators that imitate the movement of the pet to reproduce the movement of the pet. For example, in order to reproduce the body angle, speed, and strength of the pet when it makes a specific movement, the robot adjusts the movement in conjunction with multiple sensors. Furthermore, the first reproducing unit faithfully reproduces the specific cry of the pet using a voice synthesis technology for reproducing the cry of the pet. This allows the behavior and characteristics of the pet to be enjoyed even after the death of the pet. The first reproducing unit fine-tunes the operation program based on the user's feedback to achieve a more natural and realistic reproduction. For example, when the user provides feedback on the pet's movement such as "I want it to move faster" or "The cry is a little different," the first reproducing unit reflects the feedback and improves the operation program. This allows the first reproducing unit to provide a high-quality reproduction that meets the user's expectations.

[0095] The second collection unit collects conversation data with the spouse. The conversation data with the spouse includes, for example, daily conversations, conversations on specific topics, and the like, but is not limited to such examples. The second collection unit collects conversation data with the spouse using, for example, a recording device. The recording device records the spouse's conversation with high sensitivity and saves it as digital data. Specifically, the recording device has a noise canceling function and removes ambient noise to collect clear voice data. Furthermore, the second collection unit can record not only the content of the conversation, but also the speaker's tone of voice and changes in emotion. For example, changes in tone of voice and emotion when the spouse talks about a specific topic are collected and analyzed by AI. The collected data is transmitted to a cloud server and used for subsequent analysis and learning. The second collection unit can periodically collect conversation data with the spouse and track changes in conversation patterns over a long period of time. This makes it possible to grasp changes in the spouse's hobbies and interests and achieve more accurate reproduction.

[0096] The second learning unit uses AI to analyze the collected conversation data of the spouse and learn the spouse's conversation patterns and hobbies and interests. The AI ​​efficiently learns the spouse's conversation patterns and hobbies and interests using technologies such as deep learning and neural networks. Specifically, the AI ​​analyzes the collected voice data and learns the spouse's way of speaking, how to choose words, and how to develop topics. For example, the second learning unit learns the conversation patterns of the spouse when talking about a specific topic and creates a program to reproduce them. The AI ​​analyzes the spouse's tone of voice and changes in emotions to understand in what situations certain emotions are expressed. In addition, the AI ​​learns the spouse's hobbies and interests and deepens its knowledge about specific topics. This allows the second learning unit to grasp the spouse's conversation patterns in detail and build a highly accurate model to reproduce them. The learned data is stored in a cloud server and updated and improved as necessary. This allows the second learning unit to always continue to learn the latest conversation patterns.

[0097] The second reproducing unit executes an operating program that reproduces the spouse based on the learned data. For example, the second reproducing unit faithfully reproduces a conversation when the spouse talks about a specific topic. Specifically, the second reproducing unit uses a voice synthesis technology to reproduce the spouse's voice and generate a conversation about the specific topic. For example, a voice synthesis engine is used to reproduce the tone of voice and changes in emotions when the spouse talks about a specific topic. Furthermore, the second reproducing unit uses a natural language processing technology to reproduce the spouse's way of speaking and choice of words to keep the flow of the conversation natural. This allows the spouse to enjoy the conversation even after the death of the spouse. The second reproducing unit can fine-tune the conversation program based on the user's feedback to achieve a more natural and realistic reproduction. For example, the user can provide feedback on the spouse's conversation such as "I want you to speak with more emotion" or "I want you to talk in more detail about a specific topic," and the second reproducing unit can improve the conversation program by reflecting the feedback. This allows the second reproducing unit to provide a high-quality reproduction that meets the user's expectations.

[0098] The first collection unit can collect the behavioral data of the pet using a camera and a microphone. It is necessary to clarify the specific type and installation method of the camera and microphone. For example, the camera has high resolution and can capture the movements of the pet in detail. The microphone has high sensitivity and can record the cries of the pet in detail. The first collection unit, for example, installs a camera in the pet's living space and monitors the movements of the pet 24 hours a day. Also, a microphone is installed in the pet's living space and records the cries of the pet constantly. This makes it possible to collect the behavioral data of the pet in detail. For example, the first collection unit collects video and audio when the pet makes a specific movement, and the AI ​​analyzes it. This makes it possible to collect the behavioral data of the pet in detail.

[0099] The first learning unit can learn the behavioral patterns of the pet using AI. It is necessary to clarify the specific technology and type of algorithm of AI. For example, technologies such as deep learning and neural network can be used. The first learning unit can efficiently learn the behavioral patterns of the pet using, for example, deep learning. Deep learning learns a large amount of data and has advanced pattern recognition capabilities. A neural network has a multi-layer network structure and can learn complex patterns. This allows the first learning unit to efficiently learn the behavioral patterns of the pet. For example, the first learning unit learns the timing and order of actions when the pet makes a specific movement and creates a program to reproduce it. This allows the pet's behavioral patterns to be efficiently learned.

[0100] The first reproducing unit can execute an operation program that reproduces the gestures, characteristics, and habits of the pet. It is necessary to clarify the specific contents and execution method of the operation program. For example, the structure of the program, the execution environment, etc. are clarified. The first reproducing unit executes, for example, a program that faithfully reproduces the behavior of the pet when it makes a specific movement. The program describes the pet's movements in detail, and the robot executes it. For example, the first reproducing unit executes a program that reproduces the timing and order of movements when the pet makes a specific movement. This allows the gestures, characteristics, and habits of the pet to be faithfully reproduced. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. This allows the gestures and characteristics of the pet to be enjoyed even after the pet's death.

[0101] The second collection unit can collect conversation data with the spouse. It is necessary to clarify the specific collection method and scope of the conversation data. For example, the recording method and the type of conversation to be collected are clarified. The second collection unit, for example, uses a recording device to collect conversation data with the spouse. The recording device records the spouse's conversation with high sensitivity and saves it as digital data. For example, the second collection unit collects daily conversations with the spouse and conversations on specific topics. This allows for detailed collection of conversation data with the spouse. For example, the second collection unit collects the content of conversations with the spouse and hobbies and interests, which are analyzed by AI. This allows for detailed collection of conversation data with the spouse.

[0102] The second learning unit can learn the conversation patterns and hobbies and interests of the spouse using AI. It is necessary to clarify the specific technology and type of algorithm of AI. For example, technologies such as deep learning and neural networks can be used. The second learning unit can efficiently learn the conversation patterns and hobbies and interests of the spouse using, for example, deep learning. Deep learning learns large amounts of data and has advanced pattern recognition capabilities. Neural networks have a multi-layer network structure and can learn complex patterns. This allows the second learning unit to efficiently learn the conversation patterns and hobbies and interests of the spouse. For example, the second learning unit learns the conversation patterns when the spouse talks about a specific topic and creates a program to reproduce them. This allows the conversation patterns and hobbies and interests of the spouse to be efficiently learned.

[0103] The second reproducing unit can execute an operating program that reproduces the spouse. It is necessary to clarify the specific contents and execution method of the operating program. For example, the program structure, execution environment, etc. are clarified. The second reproducing unit executes, for example, a program that faithfully reproduces a conversation when the spouse speaks about a specific topic. The program describes the spouse's conversation in detail, and the robot executes it. For example, the second reproducing unit executes a program that reproduces the conversation pattern when the spouse speaks about a specific topic. This makes it possible to faithfully reproduce the spouse's conversation and behavior. For example, the second reproducing unit faithfully reproduces a conversation when the spouse speaks about a specific topic. This makes it possible to enjoy the conversation even after the spouse's death.

[0104] The first collection unit can estimate the pet's emotion and adjust the timing of collecting behavioral data based on the estimated pet's emotion. For example, the first collection unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first collection unit calculates an emotion score based on the change in facial expression. The first collection unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first collection unit analyzes the tone and speed of the voice and calculates the emotion score. The first collection unit can also collect the pet's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first collection unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to collect behavioral data at an optimal timing according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the first collection unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0105] The first collection unit can analyze the past behavior history of the pet and select the optimal collection method. For example, the first collection unit acquires the past behavior history of the pet from a database and analyzes it using AI. For example, the first collection unit determines the priority of data to be collected based on the behavior that the pet frequently performed in the past. The first collection unit can also analyze the past behavior pattern of the pet and select the optimal method for collecting a specific behavior. For example, the first collection unit selects data to be collected in a specific time period from the past behavior history of the pet. This makes it possible to select the optimal collection method based on the past behavior history of the pet. A part or all of the above-mentioned processing in the first collection unit may be performed using AI, for example, or may be performed without using AI. For example, the first collection unit can input the past behavior history data of the pet to the generation AI and cause the generation AI to select the optimal collection method.

[0106] The first collection unit can perform filtering based on the pet's current health condition and environment when collecting behavioral data. For example, the first collection unit monitors the pet's health condition with a sensor and collects behavioral data when the pet's health condition is good. For example, the first collection unit measures the pet's body temperature and heart rate with a sensor and evaluates the health condition. The first collection unit can also monitor the pet's environment with a sensor and collect behavioral data when the environment is stable. For example, the first collection unit measures the temperature and humidity of the pet's living space with a sensor and evaluates the stability of the environment. This makes it possible to collect only important data based on the pet's health condition and environment. A part or all of the above-mentioned processing in the first collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the first collection unit can input the pet's health condition and environmental data to the generation AI and cause the generation AI to perform filtering.

[0107] The first collection unit can estimate the pet's emotion and determine the priority of the behavioral data to be collected based on the estimated pet's emotion. For example, the first collection unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first collection unit calculates an emotion score based on the change in facial expression. The first collection unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first collection unit analyzes the tone and speed of the voice and calculates the emotion score. The first collection unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first collection unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the behavioral data to be collected according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the first collection unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0108] The first collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the pet when collecting behavioral data. For example, the first collection unit acquires the geographical location information of the pet by a GPS device, and preferentially collects highly relevant data. For example, when the pet is in a specific location, the first collection unit preferentially collects behavioral data at the location. In addition, when the pet is moving, the first collection unit can also preferentially collect behavioral data during movement. For example, when the pet is in a specific location, the first collection unit preferentially collects behavioral data at the location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the pet. A part or all of the above-mentioned processing in the first collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the first collection unit can input the geographical location information data of the pet to the generation AI, and cause the generation AI to execute the priority order of highly relevant data.

[0109] The first collection unit can analyze the social media activity of the pet owner when collecting the behavioral data, and collect related data. For example, the first collection unit analyzes photos and videos of the pet posted by the pet owner on social media, and collects related behavioral data. For example, the first collection unit analyzes comments on the pet's behavior posted by the owner on social media, and collects related behavioral data. The first collection unit can also analyze information on the pet's behavior posted by the owner on social media, and collect related behavioral data. For example, the first collection unit analyzes information on the pet's behavior posted by the owner on social media, and collects related behavioral data. This makes it possible to collect related data based on the owner's social media activity. A part or all of the above-mentioned processing in the first collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the first collection unit can input the owner's social media activity data to the generation AI, and cause the generation AI to execute collection of related data.

[0110] The first learning unit can estimate the pet's emotion and adjust the behavior pattern learning method based on the estimated pet's emotion. For example, the first learning unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first learning unit calculates an emotion score based on the change in facial expression. The first learning unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first learning unit analyzes the tone and speed of the voice and calculates the emotion score. The first learning unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first learning unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to adjust the behavior pattern learning method according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0111] The first learning unit can adjust the level of detail of the learning based on the importance of the pet's behavior during learning. The first learning unit, for example, evaluates the importance of the pet's behavior and learns important behavior patterns in detail. For example, the first learning unit evaluates the importance of the behavior based on the frequency and impact of the pet's behavior. The first learning unit can also simply learn behavior patterns with low importance. For example, the first learning unit adjusts the level of detail of the learning based on the importance of the pet's behavior. This makes it possible to adjust the level of detail of the learning based on the importance of the pet's behavior. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit can input the pet's behavior data to the generation AI and cause the generation AI to evaluate the importance of the behavior and adjust the level of detail of the learning.

[0112] The first learning unit can apply different learning algorithms depending on the type and age of the pet during learning. The first learning unit applies different learning algorithms depending on, for example, the type of pet. For example, the first learning unit applies optimal learning algorithms to different types of pets such as dogs and cats. The first learning unit can also apply different learning algorithms depending on the age of the pet. For example, the first learning unit applies optimal learning algorithms to young pets and old pets. This makes it possible to apply optimal learning algorithms depending on the type and age of the pet. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit can input data on the type and age of the pet to the generation AI and cause the generation AI to apply the optimal learning algorithm.

[0113] The first learning unit can estimate the pet's emotion and determine the learning priority based on the estimated pet's emotion. For example, the first learning unit captures the pet's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first learning unit calculates an emotion score based on the change in facial expression. The first learning unit can also record the pet's voice and estimate the emotion using a voice analysis technique. For example, the first learning unit analyzes the tone and speed of the voice and calculates the emotion score. The first learning unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first learning unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the learning priority according to the pet's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the first learning unit may input image data of a pet taken by a camera to the generation AI and cause the generation AI to estimate the pet's emotions.

[0114] The first learning unit can weight the learning based on the collection time of the pet's behavior data during learning. The first learning unit, for example, acquires the collection time of the pet's behavior data from a database and analyzes it using AI. For example, the first learning unit weights the learning based on the collection time of the pet's behavior data. For example, the first learning unit weights the learning based on the collection time of the pet's behavior data. This allows the learning to be weighted based on the collection time of the pet's behavior data. A part or all of the above-mentioned processing in the first learning unit may be performed using AI, for example, or may be performed without using AI. For example, the first learning unit can input collection time data of the pet's behavior data to the generation AI and cause the generation AI to perform the weighting of the learning.

[0115] The first learning unit can improve the accuracy of learning by referring to pet-related literature during learning. The first learning unit, for example, acquires pet-related literature from a database and analyzes it using AI. For example, the first learning unit improves the accuracy of learning by referring to pet-related literature. For example, the first learning unit improves the accuracy of learning by referring to pet-related literature. As a result, the accuracy of learning can be improved by referring to pet-related literature. A part or all of the above-mentioned processing in the first learning unit may be performed using AI, for example, or may be performed without using AI. For example, the first learning unit can input pet-related literature data to the generation AI and cause the generation AI to execute improvement of the accuracy of learning.

[0116] The first reproducing unit can estimate the emotion of the pet and adjust the timing of the action to be reproduced based on the estimated emotion of the pet. For example, the first reproducing unit captures the facial expression of the pet with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first reproducing unit can calculate an emotion score based on the change in facial expression. The first reproducing unit can also record the voice of the pet and estimate the emotion using a voice analysis technology. For example, the first reproducing unit analyzes the tone and speed of the voice and calculates an emotion score. The first reproducing unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first reproducing unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to reproduce the action at an optimal timing according to the emotion of the pet. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the first reproducing unit may input image data of a pet taken by a camera to the generating AI and cause the generating AI to estimate the pet's emotions.

[0117] The first reproducing unit can select the optimal reproduction method by referring to the past behavioral patterns of the pet at the time of reproduction. For example, the first reproducing unit acquires the past behavioral patterns of the pet from a database and analyzes them using AI. For example, the first reproducing unit selects the optimal reproduction method by referring to the past behavioral patterns of the pet. For example, the first reproducing unit selects the optimal reproduction method by referring to the past behavioral patterns of the pet. This makes it possible to select the optimal reproduction method based on the past behavioral patterns of the pet. A part or all of the above-mentioned processing in the first reproducing unit may be performed, for example, using AI, or may be performed without using AI. For example, the first reproducing unit can input the past behavioral pattern data of the pet to the generating AI and cause the generating AI to select the optimal reproduction method.

[0118] The first reproducing unit can customize the operation program based on the pet's current environment at the time of reproduction. The first reproducing unit, for example, monitors the pet's current environment with a sensor and customizes the operation program based on the environmental data. For example, the first reproducing unit measures the temperature and humidity of the pet's living space with a sensor and evaluates the stability of the environment. The first reproducing unit can also monitor the situation around the pet with a sensor and customize the operation program. For example, the first reproducing unit customizes the operation program based on the situation of the pet's living space. This makes it possible to customize the operation program based on the pet's current environment. A part or all of the above-mentioned processing in the first reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the first reproducing unit can input the pet's environmental data to the generating AI and cause the generating AI to execute customization of the operation program.

[0119] The first reproducing unit can estimate the emotion of the pet and determine the priority of the actions to be reproduced based on the estimated emotion of the pet. For example, the first reproducing unit captures the facial expression of the pet with a camera and estimates the emotion using an emotion estimation algorithm. For example, the first reproducing unit calculates an emotion score based on the change in the facial expression. The first reproducing unit can also record the voice of the pet and estimate the emotion using a voice analysis technology. For example, the first reproducing unit analyzes the tone and speed of the voice and calculates the emotion score. The first reproducing unit can also collect the pet's biological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the first reproducing unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the actions to be reproduced according to the emotion of the pet. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the first reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the first reproducing unit may input image data of a pet taken by a camera to the generating AI and cause the generating AI to estimate the pet's emotions.

[0120] The first reproducing unit can select an optimal reproduction method in consideration of the geographical location information of the pet at the time of reproduction. For example, the first reproducing unit acquires the geographical location information of the pet by a GPS device and preferentially collects highly relevant data. For example, when the pet is in a specific location, the first reproducing unit preferentially collects behavioral data at that location. Also, when the pet is moving, the first reproducing unit can preferentially collect behavioral data during the movement. For example, when the pet is in a specific location, the first reproducing unit preferentially collects behavioral data at that location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the pet. A part or all of the above-mentioned processing in the first reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the first reproducing unit can input the geographical location information data of the pet to the generating AI and cause the generating AI to execute the priority order of highly relevant data.

[0121] At the time of reproduction, the first reproduction unit can analyze the social media activity of the pet owner and suggest a means of reproduction. For example, the first reproduction unit analyzes photos and videos of the pet posted by the pet owner on social media and collects related behavioral data. For example, the first reproduction unit analyzes comments on the pet's behavior posted by the owner on social media and collects related behavioral data. The first reproduction unit can also analyze information on the pet's behavior posted by the owner on social media and collect related behavioral data. For example, the first reproduction unit analyzes information on the pet's behavior posted by the owner on social media and collects related behavioral data. This makes it possible to collect related data based on the owner's social media activity. A part or all of the above-mentioned processing in the first reproduction unit may be performed, for example, using AI or may be performed without using AI. For example, the first reproduction unit can input the owner's social media activity data to the generation AI and cause the generation AI to collect related data.

[0122] The second collection unit can estimate the spouse's emotion and adjust the timing of collecting conversation data based on the estimated spouse's emotion. For example, the second collection unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second collection unit calculates an emotion score based on the change in facial expression. The second collection unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second collection unit analyzes the tone and speed of the voice and calculates an emotion score. The second collection unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second collection unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to collect conversation data at an optimal timing according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the second collection unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's feelings.

[0123] The second collection unit can analyze the spouse's past conversation history and select the optimal collection method. For example, the second collection unit acquires the spouse's past conversation history from a database and analyzes it using AI. For example, the second collection unit determines the priority of data to be collected based on conversations that the spouse frequently had in the past. The second collection unit can also analyze the spouse's past conversation patterns and select the optimal method for collecting a specific conversation. For example, the second collection unit selects data to be collected in a specific time period from the spouse's past conversation history. This makes it possible to select the optimal collection method based on the spouse's past conversation history. A part or all of the above-mentioned processing in the second collection unit may be performed using AI, for example, or may be performed without using AI. For example, the second collection unit can input the spouse's past conversation history data to the generation AI and cause the generation AI to select the optimal collection method.

[0124] The second collection unit can perform filtering based on the spouse's current living situation and areas of interest when collecting conversation data. For example, the second collection unit monitors the spouse's living situation with a sensor and collects conversation data when the living situation is stable. For example, the second collection unit evaluates the living situation based on the spouse's occupation and daily activities. The second collection unit can also obtain the spouse's areas of interest from a database and filter the conversation data to be collected based on the areas of interest. For example, the second collection unit filters the conversation data to be collected based on the spouse's hobbies and interests. This makes it possible to collect only important data based on the spouse's living situation and areas of interest. A part or all of the above-mentioned processing in the second collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the second collection unit can input the spouse's living situation and areas of interest data to the generation AI and cause the generation AI to perform filtering.

[0125] The second collection unit can estimate the spouse's emotion and determine the priority of the conversation data to be collected based on the estimated spouse's emotion. For example, the second collection unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second collection unit calculates an emotion score based on the change in facial expression. The second collection unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second collection unit analyzes the tone and speed of the voice and calculates the emotion score. The second collection unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second collection unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the conversation data to be collected according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the second collection unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's feelings.

[0126] When collecting conversation data, the second collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the spouse. For example, the second collection unit acquires the geographical location information of the spouse by a GPS device, and preferentially collects highly relevant data. For example, when the spouse is in a specific location, the second collection unit preferentially collects conversation data at that location. In addition, when the spouse is moving, the second collection unit can also preferentially collect conversation data during the movement. For example, when the spouse is in a specific location, the second collection unit preferentially collects conversation data at that location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the spouse. A part or all of the above-mentioned processing in the second collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the second collection unit can input the geographical location information data of the spouse to the generation AI, and cause the generation AI to execute the priority order of highly relevant data.

[0127] The second collection unit can analyze the social media activity of the spouse when collecting the conversation data and collect related data. For example, the second collection unit analyzes the content of the conversation posted by the spouse on social media and collects related conversation data. For example, the second collection unit analyzes comments on hobbies and interests posted by the spouse on social media and collects related conversation data. The second collection unit can also analyze information on the conversation posted by the spouse on social media and collect related conversation data. For example, the second collection unit analyzes information on the conversation posted by the spouse on social media and collects related conversation data. This makes it possible to collect related data based on the social media activity of the spouse. A part or all of the above-mentioned processing in the second collection unit may be performed, for example, using AI or may be performed without using AI. For example, the second collection unit can input the social media activity data of the spouse to the generation AI and cause the generation AI to execute collection of related data.

[0128] The second learning unit can estimate the spouse's emotion and adjust the learning method of the conversation pattern based on the estimated spouse's emotion. For example, the second learning unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second learning unit calculates an emotion score based on the change in facial expression. The second learning unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second learning unit analyzes the tone and speed of the voice and calculates the emotion score. The second learning unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second learning unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to adjust the learning method of the conversation pattern according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the second learning unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's emotions.

[0129] The second learning unit can adjust the level of detail of the learning based on the importance of the spouse's conversation during learning. The second learning unit, for example, evaluates the importance of the spouse's conversation and learns important conversation patterns in detail. For example, the second learning unit evaluates the importance of the conversation based on the frequency of the spouse's conversation and the importance of the content. The second learning unit can also simply learn conversation patterns with low importance. For example, the second learning unit adjusts the level of detail of the learning based on the importance of the spouse's conversation. This makes it possible to adjust the level of detail of the learning based on the importance of the spouse's conversation. A part or all of the above-mentioned processing in the second learning unit may be performed, for example, using AI or may be performed without using AI. For example, the second learning unit can input spouse's conversation data to the generation AI and cause the generation AI to evaluate the importance of the conversation and adjust the level of detail of the learning.

[0130] The second learning unit can apply different learning algorithms depending on the hobbies and interests of the spouse during learning. The second learning unit applies different learning algorithms depending on, for example, the hobbies of the spouse. For example, the second learning unit applies an optimal learning algorithm depending on the hobbies and interests of the spouse. This makes it possible to apply an optimal learning algorithm depending on the hobbies and interests of the spouse. A part or all of the above-mentioned processing in the second learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the second learning unit can input the hobby and interest data of the spouse to the generation AI and cause the generation AI to apply the optimal learning algorithm.

[0131] The second learning unit can estimate the spouse's emotion and determine the learning priority based on the spouse's estimated emotion. For example, the second learning unit captures the spouse's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second learning unit calculates an emotion score based on the change in facial expression. The second learning unit can also record the spouse's voice and estimate the emotion using a voice analysis technique. For example, the second learning unit analyzes the tone and speed of the voice and calculates the emotion score. The second learning unit can also collect the spouse's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second learning unit calculates the emotion score based on the heart rate fluctuation. This makes it possible to determine the learning priority according to the spouse's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the second learning unit may input image data of the spouse taken by a camera to the generation AI and cause the generation AI to estimate the spouse's emotions.

[0132] The second learning unit can weight the learning based on the collection time of the spouse's conversation data during learning. The second learning unit, for example, acquires the collection time of the spouse's conversation data from a database and analyzes it using AI. For example, the second learning unit weights the learning based on the collection time of the spouse's conversation data. For example, the second learning unit weights the learning based on the collection time of the spouse's conversation data. This makes it possible to weight the learning based on the collection time of the spouse's conversation data. A part or all of the above-mentioned processing in the second learning unit may be performed using AI, for example, or may be performed without using AI. For example, the second learning unit can input collection time data of the spouse's conversation data to the generation AI and cause the generation AI to perform the weighting of the learning.

[0133] The second learning unit can improve the accuracy of the learning by referring to the spouse's related literature during learning. The second learning unit, for example, acquires the spouse's related literature from a database and analyzes it using AI. For example, the second learning unit improves the accuracy of the learning by referring to the spouse's related literature. For example, the second learning unit improves the accuracy of the learning by referring to the spouse's related literature. As a result, the accuracy of the learning can be improved by referring to the spouse's related literature. A part or all of the above-mentioned processing in the second learning unit may be performed using AI, for example, or may be performed without using AI. For example, the second learning unit can input the spouse's related literature data to the generation AI and cause the generation AI to execute the improvement of the learning accuracy.

[0134] The second reproducing unit can estimate the emotion of the spouse and adjust the timing of the conversation to be reproduced based on the estimated emotion of the spouse. For example, the second reproducing unit captures the facial expression of the spouse with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second reproducing unit calculates an emotion score based on the change in the facial expression. The second reproducing unit can also record the voice of the spouse and estimate the emotion using a voice analysis technique. For example, the second reproducing unit analyzes the tone and speed of the voice and calculates an emotion score. The second reproducing unit can also collect the biological data of the spouse (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second reproducing unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to reproduce the conversation at an optimal timing according to the emotion of the spouse. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the second reproducing unit may input image data of the spouse taken by a camera to the generating AI, and cause the generating AI to estimate the spouse's emotions.

[0135] The second reproducing unit can select the optimal reproduction method by referring to the spouse's past conversation patterns at the time of reproduction. The second reproducing unit, for example, acquires the spouse's past conversation patterns from a database and analyzes them using AI. For example, the second reproducing unit selects the optimal reproduction method by referring to the spouse's past conversation patterns. For example, the second reproducing unit selects the optimal reproduction method by referring to the spouse's past conversation patterns. This makes it possible to select the optimal reproduction method based on the spouse's past conversation patterns. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI, or may be performed without using AI. For example, the second reproducing unit can input the spouse's past conversation pattern data to the generating AI and cause the generating AI to select the optimal reproduction method.

[0136] The second reproducing unit can customize the conversation program based on the spouse's current living situation at the time of reproduction. The second reproducing unit, for example, monitors the spouse's current living situation with a sensor and customizes the conversation program based on the living situation data. For example, the second reproducing unit evaluates the living situation based on the spouse's occupation and daily activities. The second reproducing unit can also monitor the spouse's surroundings with a sensor and customize the conversation program. For example, the second reproducing unit customizes the conversation program based on the situation of the spouse's living space. This makes it possible to customize the conversation program based on the spouse's current living situation. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the second reproducing unit can input the spouse's living situation data to the generating AI and cause the generating AI to customize the conversation program.

[0137] The second reproducing unit can estimate the emotion of the spouse and determine the priority of the conversation to be reproduced based on the estimated emotion of the spouse. For example, the second reproducing unit captures the facial expression of the spouse with a camera and estimates the emotion using an emotion estimation algorithm. For example, the second reproducing unit can calculate an emotion score based on the change in the facial expression. The second reproducing unit can also record the voice of the spouse and estimate the emotion using a voice analysis technique. For example, the second reproducing unit analyzes the tone and speed of the voice and calculates an emotion score. The second reproducing unit can also collect the biological data of the spouse (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the second reproducing unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the conversation to be reproduced according to the emotion of the spouse. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the second reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the second reproducing unit may input image data of the spouse taken by a camera to the generating AI, and cause the generating AI to estimate the spouse's emotions.

[0138] The second reproducing unit can select an optimal reproduction method in consideration of the geographical location information of the spouse at the time of reproduction. For example, the second reproducing unit acquires the geographical location information of the spouse by a GPS device and preferentially collects highly relevant data. For example, when the spouse is in a specific location, the second reproducing unit preferentially collects conversation data at that location. In addition, when the spouse is moving, the second reproducing unit can also preferentially collect conversation data during the movement. For example, when the spouse is in a specific location, the second reproducing unit preferentially collects conversation data at that location. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the spouse. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the second reproducing unit can input the geographical location information data of the spouse to the generating AI and cause the generating AI to execute the priority order of highly relevant data.

[0139] The second reproducing unit can analyze the spouse's social media activity at the time of reproduction and suggest a means of reproduction. The second reproducing unit, for example, analyzes the content of the conversation posted by the spouse on social media and collects related conversation data. For example, the second reproducing unit analyzes comments on hobbies and interests posted by the spouse on social media and collects related conversation data. The second reproducing unit can also analyze information on the conversation posted by the spouse on social media and collect related conversation data. For example, the second reproducing unit analyzes information on the conversation posted by the spouse on social media and collects related conversation data. This makes it possible to collect related data based on the spouse's social media activity. A part or all of the above-mentioned processing in the second reproducing unit may be performed, for example, using AI or may be performed without using AI. For example, the second reproducing unit can input the spouse's social media activity data to the generating AI and cause the generating AI to collect related data.

[0140] The communication unit can estimate the user's emotion and adjust the timing of contact based on the estimated user's emotion. The communication unit, for example, captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the communication unit calculates an emotion score based on the change in facial expression. The communication unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the communication unit analyzes the tone and speed of the voice and calculates the emotion score. The communication unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the communication unit calculates the emotion score based on the fluctuation of the heart rate. This allows the user to contact the user at the optimal timing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0141] The contact unit can select the optimal contact method by referring to the user's past contact history at the time of contact. The contact unit, for example, acquires the user's past contact history from a database and analyzes it using AI. For example, the contact unit selects the optimal contact method by referring to the user's past contact history. For example, the contact unit selects a specific contact method based on the user's past contact history. This makes it possible to select the optimal contact method based on the user's past contact history. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI, or may be performed without using AI. For example, the contact unit can input the user's past contact history data to the generation AI and cause the generation AI to select the optimal contact method.

[0142] The communication unit can estimate the user's emotion and determine the priority of the contact based on the estimated user's emotion. The communication unit, for example, captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the communication unit calculates an emotion score based on the change in the facial expression. The communication unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the communication unit analyzes the tone and speed of the voice and calculates the emotion score. The communication unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the communication unit calculates the emotion score based on the fluctuation of the heart rate. This makes it possible to determine the priority of the contact according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0143] The contact unit can select the optimal contact method in consideration of the geographical location information of the user at the time of contact. For example, the contact unit acquires the geographical location information of the user using a GPS device, and preferentially collects highly relevant data. For example, when the user is in a specific location, the contact unit preferentially selects a contact method at that location. In addition, when the user is moving, the contact unit can also preferentially select a contact method during movement. For example, when the user is in a specific location, the contact unit preferentially selects a contact method at that location. This makes it possible to select a highly relevant contact method based on the geographical location information of the user. Part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI, or may be performed without using AI. For example, the contact unit can input the geographical location information data of the user to the generation AI, and cause the generation AI to select a highly relevant contact method.

[0144] The contact unit can select the optimal contact method by analyzing the user's social media activity at the time of contact. The contact unit, for example, analyzes the content posted by the user on social media and selects a related contact method. For example, the contact unit analyzes comments on hobbies and interests posted by the user on social media and selects a related contact method. The contact unit can also analyze information posted by the user on social media and select a related contact method. For example, the contact unit analyzes information posted by the user on social media and selects a related contact method. This makes it possible to select a related contact method based on the user's social media activity. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI or may be performed without using AI. For example, the contact unit can input the user's social media activity data to the generation AI and cause the generation AI to select a related contact method.

[0145] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0146] When collecting the behavioral data of the pet, the first collection unit can monitor the health condition of the pet and collect data when the health condition is good. For example, the pet's body temperature and heart rate are measured by a sensor to evaluate the health condition. The pet's environment can also be monitored by a sensor and behavioral data can be collected when the environment is stable. This makes it possible to collect only important data based on the pet's health condition and environment. Furthermore, the first collection unit can also preferentially collect highly relevant data in consideration of the geographical location information of the pet. For example, when the pet is in a specific location, behavioral data at that location can be preferentially collected. Also, when the pet is moving, behavioral data during the movement can be preferentially collected. This makes it possible to preferentially collect highly relevant data based on the geographical location information of the pet.

[0147] When learning the behavioral patterns of a pet, the first learning unit can apply different learning algorithms depending on the type and age of the pet. For example, the optimal learning algorithm is applied to different types of pets such as dogs and cats. Also, the optimal learning algorithm can be applied to young pets and old pets. This makes it possible to apply the optimal learning algorithm depending on the type and age of the pet. Furthermore, the first learning unit can adjust the level of detail of the learning based on the importance of the pet's behavior. For example, the importance of the behavior is evaluated based on the frequency and impact of the pet's behavior, and important behavioral patterns are learned in detail. Also, it is possible to simply learn behavioral patterns with low importance. This makes it possible to adjust the level of detail of the learning based on the importance of the pet's behavior.

[0148] The first reproducing unit can customize the operation program based on the pet's current environment when reproducing the pet's gestures, characteristics, and habits. For example, the temperature and humidity of the pet's living space are measured by a sensor to evaluate the stability of the environment. The operation program can also be customized by monitoring the pet's surroundings with a sensor. This allows the operation program to be customized based on the pet's current environment. Furthermore, the first reproducing unit can also select the optimal reproduction method by referring to the pet's past behavioral patterns. For example, the pet's past behavioral patterns are obtained from a database and analyzed using AI. This allows the optimal reproduction method to be selected based on the pet's past behavioral patterns.

[0149] When collecting conversation data with a spouse, the second collection unit can filter the conversation data based on the spouse's living situation and areas of interest. For example, the living situation is evaluated based on the spouse's occupation and daily activities, and conversation data is collected when the living situation is stable. The conversation data to be collected can also be filtered based on the spouse's hobbies and interests. This makes it possible to collect only important data based on the spouse's living situation and areas of interest. Furthermore, the second collection unit can preferentially collect highly relevant data in consideration of the spouse's geographical location information. For example, when the spouse is in a specific location, conversation data at that location can be preferentially collected. Also, when the spouse is on the move, conversation data during the move can be preferentially collected. This makes it possible to preferentially collect highly relevant data based on the spouse's geographical location information.

[0150] The second learning unit can estimate the spouse's emotions when learning the spouse's conversation patterns and hobbies and preferences, and adjust the learning method based on the estimated emotions. For example, the spouse's facial expression is photographed with a camera, and emotions are estimated using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and learning priorities are determined according to the emotions. The spouse's voice can also be recorded, and emotions can be estimated using voice analysis technology. The tone and speed of the voice are analyzed, and an emotion score is calculated. Furthermore, the spouse's biometric data (heart rate and electrodermal activity) can be collected with a sensor, and emotions can be estimated using an emotion estimation algorithm. This makes it possible to adjust the learning method of the conversation pattern according to the spouse's emotions.

[0151] When reproducing the spouse, the second reproducing unit can estimate the spouse's emotions and adjust the timing of the conversation to be reproduced based on the estimated emotions. For example, the spouse's facial expression is photographed by a camera, and the emotions are estimated using an emotion estimation algorithm. An emotion score is calculated based on the change in facial expression, and the conversation is reproduced at the optimal timing according to the emotions. The second reproducing unit can also record the spouse's voice and estimate the emotions using voice analysis technology. The tone and speed of the voice are analyzed to calculate the emotion score. Furthermore, the spouse's biometric data (heart rate and electrodermal activity) can be collected by a sensor, and the emotions can be estimated using an emotion estimation algorithm. This makes it possible to reproduce the conversation at the optimal timing according to the spouse's emotions.

[0152] The first collection unit can estimate the pet's emotion and adjust the timing of collecting behavioral data based on the estimated emotion. For example, the pet's facial expression is photographed with a camera, and the emotion is estimated using an emotion estimation algorithm. An emotion score is calculated based on the change in facial expression, and behavioral data is collected at the optimal timing according to the emotion. The pet's voice can also be recorded and the emotion can be estimated using voice analysis technology. The tone and speed of the voice are analyzed to calculate the emotion score. Furthermore, the pet's biological data (heart rate and electrodermal activity) can be collected with a sensor, and the emotion can be estimated using an emotion estimation algorithm. This makes it possible to collect behavioral data at the optimal timing according to the pet's emotion.

[0153] The first learning unit can estimate the pet's emotions and adjust the behavior pattern learning method based on the estimated emotions. For example, the pet's facial expression is photographed with a camera, and the emotions are estimated using an emotion estimation algorithm. An emotion score is calculated based on the change in facial expression, and learning priorities are determined according to the emotions. The first learning unit can also record the pet's voice and estimate emotions using voice analysis technology. The tone and speed of the voice are analyzed to calculate an emotion score. Furthermore, the pet's biological data (heart rate and electrodermal activity) can be collected with a sensor, and emotions can be estimated using an emotion estimation algorithm. This makes it possible to adjust the behavior pattern learning method according to the pet's emotions.

[0154] The first reproducing unit can estimate the pet's emotion and adjust the timing of the action to be reproduced based on the estimated emotion. For example, the pet's facial expression is photographed with a camera, and the emotion is estimated using an emotion estimation algorithm. An emotion score is calculated based on the change in the facial expression, and the action is reproduced at the optimal timing according to the emotion. The pet's voice can also be recorded and the emotion can be estimated using voice analysis technology. The tone and speed of the voice are analyzed and the emotion score is calculated. Furthermore, the pet's biological data (heart rate and electrodermal activity) can be collected with a sensor, and the emotion can be estimated using an emotion estimation algorithm. This makes it possible to reproduce the action at the optimal timing according to the pet's emotion.

[0155] The second collection unit can estimate the spouse's emotions and adjust the timing of collecting conversation data based on the estimated emotions. For example, the spouse's facial expression is photographed with a camera, and the emotions are estimated using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expression, and conversation data is collected at the optimal timing according to the emotions. The spouse's voice can also be recorded, and emotions can be estimated using voice analysis technology. The tone and speed of the voice are analyzed, and an emotion score is calculated. Furthermore, the spouse's biometric data (heart rate and electrodermal activity) can be collected with a sensor, and emotions can be estimated using an emotion estimation algorithm. This makes it possible to collect conversation data at the optimal timing according to the spouse's emotions.

[0156] The process flow of the second embodiment will be briefly described below.

[0157] Step 1: The first collection unit collects behavioral data of the pet. The behavioral data of the pet includes, but is not limited to, movements, cries, and eating patterns. The first collection unit collects the behavioral data of the pet using, for example, a camera and a microphone. The camera captures the movements of the pet with high resolution, and the microphone records the cries of the pet with high sensitivity. Step 2: The first learning unit uses AI to analyze the collected pet behavior data and learn the pet's behavior patterns. The AI ​​efficiently learns the pet's behavior patterns using technologies such as deep learning and neural networks. For example, the first learning unit learns the timing and sequence of actions when the pet makes a specific movement and creates a program to reproduce it. Step 3: The first reproducing unit executes an action program that reproduces the pet's gestures, characteristics, and habits based on the learned data. For example, the first reproducing unit faithfully reproduces the behavior of the pet when it makes a specific movement. This allows you to enjoy the gestures and characteristics of your pet even after it has died. Step 4: The second collection unit collects conversation data with the spouse. The conversation data with the spouse includes, but is not limited to, for example, daily conversations and conversations on specific topics. The second collection unit collects conversation data with the spouse using, for example, a recording device. The recording device records the spouse's conversation with high sensitivity and stores it as digital data. Step 5: The second learning unit uses AI to analyze the collected conversation data of the spouse and learn the spouse's conversation patterns and hobbies and interests. The AI ​​efficiently learns the spouse's conversation patterns and hobbies and interests using technologies such as deep learning and neural networks. For example, the second learning unit learns the conversation patterns of the spouse when talking about a specific topic and creates a program to reproduce them. Step 6: The second reproducing unit executes an operation program for reproducing the spouse based on the learned data. For example, the second reproducing unit faithfully reproduces the conversation of the spouse when talking about a specific topic. This allows the spouse to enjoy the conversation even after the death of the spouse.

[0158] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0159] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0160] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0161] For example, the first collecting unit and the second collecting unit are realized by at least one of the smart device 14 and the data processing device 12. For example, the first collecting unit collects behavioral data of the pet using the camera 42 and the microphone 38B of the smart device 14. The second collecting unit collects conversation data with the spouse using the recording device of the smart device 14. The first learning unit and the second learning unit are realized, for example, by the specific processing unit 290 of the data processing device 12, and analyze the collected data using AI to learn behavioral patterns and conversation patterns. The first reproducing unit and the second reproducing unit are realized, for example, by the control unit 46A of the smart device 14, and reproduce the actions and conversations of the pet and spouse based on the learned data. The correspondence between each unit and the device and the control unit is not limited to the above-mentioned example, and various changes are possible.

[0162] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0163] 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.

[0164] 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, the RAM 30, and the 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.

[0165] 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.

[0166] 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 the voice according to instructions from the processor 46.

[0167] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0168] 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 performed in a secure state.

[0169] Fig. 4 shows an example of 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.

[0170] 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.

[0171] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0172] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0173] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0174] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0175] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0176] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0177] For example, the first collecting unit and the second collecting unit are realized by at least one of the smart glasses 214 and the data processing device 12. For example, the first collecting unit collects behavioral data of a pet using the camera 42 and the microphone 238 of the smart glasses 214. The second collecting unit collects conversation data with a spouse using a recording device of the smart glasses 214. The first learning unit and the second learning unit are realized, for example, by the specific processing unit 290 of the data processing device 12, and analyze the collected data using AI to learn behavioral patterns and conversation patterns. The first reproducing unit and the second reproducing unit are realized, for example, by the control unit 46A of the smart glasses 214, and reproduce the actions and conversations of a pet or a spouse based on the learned data. The correspondence between each unit and the device or the control unit is not limited to the above-mentioned example, and various changes are possible.

[0178] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0179] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0180] 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, the RAM 30, and the 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.

[0181] 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.

[0182] 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 the voice according to instructions from the processor 46.

[0183] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0184] 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 performed in a secure state.

[0185] 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.

[0186] 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.

[0187] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0188] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

[0189] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0190] 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 voice indicating a user input for 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.

[0191] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0192] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0193] For example, the first collecting unit and the second collecting unit are realized by at least one of the headset type terminal 314 and the data processing device 12. For example, the first collecting unit collects behavioral data of the pet using the camera 42 and the microphone 238 of the headset type terminal 314. The second collecting unit collects conversation data with the spouse using the recording device of the headset type terminal 314. The first learning unit and the second learning unit are realized by, for example, the specific processing unit 290 of the data processing device 12, and analyze the collected data using AI to learn behavioral patterns and conversation patterns. The first reproducing unit and the second reproducing unit are realized by, for example, the control unit 46A of the headset type terminal 314, and reproduce the actions and conversations of the pet and spouse based on the learned data. The correspondence between each unit and the device and the control unit is not limited to the above-mentioned example, and various changes are possible.

[0194] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0195] 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.

[0196] 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, the RAM 30, and the 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.

[0197] 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.

[0198] 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 the voice according to instructions from the processor 46.

[0199] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0200] 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 performed in a secure state.

[0201] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0202] 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.

[0203] 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.

[0204] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0205] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0206] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0207] 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 a voice indicating a user input for 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.

[0208] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0209] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0210] For example, the first collecting unit and the second collecting unit are realized by at least one of the robot 414 and the data processing device 12. For example, the first collecting unit collects behavioral data of the pet using the camera 42 and the microphone 238 of the robot 414. The second collecting unit collects conversation data with the spouse using the recording device of the robot 414. The first learning unit and the second learning unit are realized, for example, by the specific processing unit 290 of the data processing device 12, and analyze the collected data using AI to learn behavioral patterns and conversation patterns. The first reproducing unit and the second reproducing unit are realized, for example, by the control unit 46A of the robot 414, and reproduce the actions and conversations of the pet and spouse based on the learned data. The correspondence between each unit and the device and the control unit is not limited to the above-mentioned example, and various changes are possible.

[0211] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0212] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0213] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0214] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0215] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0216] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0217] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0218] 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.

[0219] 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 Universal Serial Bus (USB) 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.

[0220] In addition, 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 upon request from the data processing device 12.

[0221] 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.

[0222] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0223] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0224] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0225] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0226] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0227] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0228] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0229] (Appendix 1) A first collection unit that collects behavioral data of a pet; a first learning unit that analyzes the data collected by the first collecting unit and learns the behavioral patterns of the pet; A first reproducing unit that reproduces the pet's behavior and habits based on the data learned by the first learning unit; a second collection unit for collecting conversation data with a spouse; a second learning unit that analyzes the data collected by the second collecting unit and learns the conversation patterns and hobbies and interests of the spouse; A second reproduction unit that reproduces the spouse based on the data learned by the second learning unit. A system characterized by: (Appendix 2) Equipped with a contact section that contacts relevant parties in the event of a user's death 2. The system of claim 1, (Appendix 3) The first collection unit is Collecting behavioral data of said pet using a camera and microphone 2. The system of claim 1, (Appendix 4) The first learning unit is Use AI to learn the pet's behavioral patterns 2. The system of claim 1, (Appendix 5) The first recapitulation part Executing a motion program that replicates the behavior, characteristics, and habits of said pet. 2. The system of claim 1, (Appendix 6) The second collection unit is Collect conversation data with your spouse 2. The system of claim 1, (Appendix 7) The second learning unit is Using AI to learn your spouse's conversation patterns, hobbies, and interests 2. The system of claim 1, (Appendix 8) The second recapitulation part Run a program that recreates your spouse 2. The system of claim 1, (Appendix 9) The first collection unit is Estimate the pet's emotions and adjust the timing of behavioral data collection based on the estimated pet's emotions. 2. The system of claim 1, (Appendix 10) The first collection unit is Analyze your pet's past behavioral history and choose the most appropriate collection method 2. The system of claim 1, (Appendix 11) The first collection unit is Filter behavioral data as it is collected based on your pet's current health and environment 2. The system of claim 1, (Appendix 12) The first collection unit is Estimate the emotions of pets and prioritize the behavioral data to be collected based on the estimated emotions of pets. 2. The system of claim 1, (Appendix 13) The first collection unit is When collecting behavioral data, the geographic location of the pet is taken into account to prioritize the collection of more relevant data. 2. The system of claim 1, (Appendix 14) The first collection unit is When collecting behavioral data, we analyze the social media activity of pet owners to collect relevant data. 2. The system of claim 1, (Appendix 15) The first learning unit is Infer your pet's emotions and adjust how it learns your pet's behavioral patterns based on the emotions you infer 2. The system of claim 1, (Appendix 16) The first learning unit is When learning, adjust the level of detail based on the importance of your pet's actions 2. The system of claim 1, (Appendix 17) The first learning unit is During training, different learning algorithms are applied depending on the type and age of the pet. 2. The system of claim 1, (Appendix 18) The first learning unit is Estimate the pet's emotions and prioritize learning based on the estimated pet's emotions 2. The system of claim 1, (Appendix 19) The first learning unit is During training, the training is weighted based on when the pet behavior data was collected. 2. The system of claim 1, (Appendix 20) The first learning unit is When studying, refer to pet-related literature to improve the accuracy of your learning. 2. The system of claim 1, (Appendix 21) The first recapitulation part Estimate your pet's emotions and adjust the timing of your actions based on the estimated emotions. 2. The system of claim 1, (Appendix 22) The first recapitulation part When recreating, the most appropriate method is selected based on the pet's past behavior patterns. 2. The system of claim 1, (Appendix 23) The first recapitulation part When respawning, customize behavior programs based on your pet's current environment 2. The system of claim 1, (Appendix 24) The first recapitulation part Estimate the pet's emotions and prioritize the actions to be reproduced based on the estimated pet's emotions. 2. The system of claim 1, (Appendix 25) The first recapitulation part When recreating, the best reproduction method is selected taking into account the pet's geographic location information 2. The system of claim 1, (Appendix 26) The first recapitulation part During reenactment, we analyze the social media activity of pet owners to suggest reenactment measures. 2. The system of claim 1, (Appendix 27) The second collection unit is The emotions of the spouse are estimated, and the timing of collection of conversation data is adjusted based on the estimated emotions of the spouse. 2. The system of claim 1, (Appendix 28) The second collection unit is Analyze your spouse's past conversation history and choose the best collection method 2. The system of claim 1, (Appendix 29) The second collection unit is When collecting conversation data, filter it based on the spouse's current living situation and areas of interest. 2. The system of claim 1, (Appendix 30) The second collection unit is Estimating spouse's emotions and prioritizing conversation data to be collected based on the estimated spouse's emotions 2. The system of claim 1, (Appendix 31) The second collection unit is When collecting conversation data, prioritize collection of relevant data by taking into account the spouse's geographic location information 2. The system of claim 1, (Appendix 32) The second collection unit is When collecting conversation data, analyze spouses' social media activity to collect relevant data. 2. The system of claim 1, (Appendix 33) The second learning unit is Estimate the spouse's emotions and adjust the way conversation patterns are learned based on the estimated spouse's emotions 2. The system of claim 1, (Appendix 34) The second learning unit is When studying, adjust the depth of your study based on the importance of your spouse's conversations 2. The system of claim 1, (Appendix 35) The second learning unit is When studying, apply different learning algorithms depending on your spouse's hobbies and interests 2. The system of claim 1, (Appendix 36) The second learning unit is Estimate the spouse's feelings and prioritize learning based on the estimated spouse's feelings 2. The system of claim 1, (Appendix 37) The second learning unit is During training, the training is weighted based on when the spouse's conversation data was collected. 2. The system of claim 1, (Appendix 38) The second learning unit is When studying, refer to the relevant literature of your partner to improve the accuracy of your study. 2. The system of claim 1, (Appendix 39) The second recapitulation part Estimating the spouse's emotions and adjusting the timing of the conversation to be reproduced based on the estimated spouse's emotions 2. The system of claim 1, (Appendix 40) The second recapitulation part When reproducing, the optimal reproduction method is selected by referring to the spouse's past conversation patterns. 2. The system of claim 1, (Appendix 41) The second recapitulation part During replay, customize the conversation program based on the spouse's current living situation 2. The system of claim 1, (Appendix 42) The second recapitulation part Estimate the spouse's emotions and prioritize conversations to be reproduced based on the estimated spouse's emotions 2. The system of claim 1, (Appendix 43) The second recapitulation part When reproducing, the optimal reproduction method is selected taking into account the spouse's geographic location information. 2. The system of claim 1, (Appendix 44) The second recapitulation part During reenactment, analyze spouses' social media activity to suggest means of reenactment. 2. The system of claim 1, (Appendix 45) The communication unit includes: To estimate a user's emotion and adjust a timing of contact based on the estimated user's emotion. 3. The system of claim 2, (Appendix 46) The communication unit includes: When contacting a user, refer to the user's past contact history to determine the best way to contact the user 3. The system of claim 2, (Appendix 47) The communication unit includes: To estimate a user's emotion and determine a priority of contacts based on the estimated user's emotion. 3. The system of claim 2, (Appendix 48) The communication unit includes: When contacting someone, consider their geographic location to find the best way to contact them 3. The system of claim 2, [Explanation of symbols]

[0230] 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 first collection unit that collects behavioral data of a pet; a first learning unit that analyzes the data collected by the first collecting unit and learns the behavioral patterns of the pet; A first reproducing unit that reproduces the gestures and habits of the pet based on the data learned by the first learning unit; a second collection unit for collecting conversation data with a spouse; a second learning unit that analyzes the data collected by the second collecting unit and learns the conversation patterns and hobbies and interests of the spouse; A second reproduction unit that reproduces the spouse based on the data learned by the second learning unit. A system characterized by:

2. Equipped with a contact section that contacts relevant parties in the event of the death of a user 2. The system of claim 1 .

3. The first collection unit is Collecting behavioral data of said pet using a camera and microphone 2. The system of claim 1 .

4. The first learning unit is Use AI to learn the behavioral patterns of the pet 2. The system of claim 1 .

5. The first recapitulation part Executing a motion program that replicates the behavior, characteristics, and habits of said pet.

2. The system of claim 1 .

6. The second recapitulation part Execute an operating program that reproduces the spouse 2. The system of claim 1 .

7. The first collection unit is Estimating the emotion of the pet and adjusting the timing of collecting behavioral data based on the estimated emotion of the pet.

2. The system of claim 1 .

8. The first collection unit is Analyze the past behavioral history of the pet and select the optimal collection method.

2. The system of claim 1 .

Images