system

Abstract

The system according to this embodiment aims to analyze the facial expressions and voices of pets and notify their owners. [Solution] The system according to the embodiment comprises a facial expression analysis unit, a voice analysis unit, a tracking unit, and a notification unit. The facial expression analysis unit analyzes the pet's facial expressions. The voice analysis unit analyzes the pet's voice. The tracking unit tracks the pet's movements. The notification unit notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, analyzing the expressions and voices of pets and notifying the owner thereof has not been sufficiently performed, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze the expressions and voices of pets and notify the owner thereof.

Means for Solving the Problems

[0006] The system according to the embodiment includes an expression analysis unit, a voice analysis unit, a tracking unit, and a notification unit. The expression analysis unit analyzes the expressions of the pet. The voice analysis unit analyzes the voices of the pet. The tracking unit tracks the movements of the pet. The notification unit notifies the owner of the analysis results obtained by the expression analysis unit and the voice analysis unit.

Advantages of the Invention

[0007] The system according to this embodiment can analyze the pet's facial expressions and voice and notify the owner. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An embodiment of the present invention provides a pet communication system that uses an AI smart camera and a speaker to communicate with and manage the health of pets. This pet communication system analyzes the pet's facial expressions in real time to understand the pet's emotions and condition. Furthermore, it learns the pet's voice and analyzes the sounds the pet makes to understand their meaning. It can also track the pet's movements and detect abnormal movements and behaviors. This enables deeper communication with pets and can be used for health management and training management. For example, the pet communication system uses an AI smart camera to analyze the pet's facial expressions in real time. The AI ​​smart camera captures the pet's facial expressions and analyzes the image data. The analysis results are used to understand the pet's emotions and condition. Next, the pet communication system uses an AI speaker to learn the pet's voice. The AI ​​speaker records the pet's voice and analyzes the audio data. The analysis results are used to understand the meaning of the sounds the pet makes. Furthermore, the pet communication system uses a tracking unit to track the pet's movements. The tracking unit tracks the pet's movements in real time and detects abnormal movements and behaviors. For example, if a pet makes an unusual movement, the tracking unit detects the movement and notifies the owner. This allows the owner to be assured of the pet's health and safety. Thus, the pet communication system enables deeper communication and health management with pets.

[0029] The pet communication system according to this embodiment comprises a facial expression analysis unit, a voice analysis unit, a tracking unit, and a notification unit. The facial expression analysis unit analyzes the pet's facial expressions. The facial expression analysis unit analyzes the pet's facial expressions using, for example, image processing technology. The facial expression analysis unit can also estimate the pet's emotions using machine learning algorithms. The facial expression analysis unit analyzes the pet's facial expressions in real time to understand the pet's emotions and state. The voice analysis unit analyzes the pet's voice. The voice analysis unit analyzes the pet's voice using, for example, speech recognition technology. The voice analysis unit can also extract features of the pet's voice using frequency analysis. The voice analysis unit learns the pet's voice and analyzes the sounds the pet makes to understand their meaning. The tracking unit tracks the pet's movements. The tracking unit tracks the pet's movements using, for example, camera tracking technology. The tracking unit can also detect the pet's movements using sensor data analysis. The tracking unit tracks the pet's movements in real time to detect abnormal movements and behaviors. The notification unit notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. The notification unit notifies the owner, for example, using smartphone notifications. The notification unit can also notify the owner using voice notifications. The notification unit notifies the owner, for example, of the pet's emotions and condition. As a result, the pet communication system according to this embodiment analyzes the pet's facial expressions, voice, and movements and notifies the owner, enabling deeper communication with the pet and health management.

[0030] The facial expression analysis unit analyzes the pet's facial expressions. For example, it uses image processing technology to analyze the pet's expressions. Specifically, it uses a camera to capture the pet's face and processes the image data in real time. Image processing technology includes face detection algorithms and feature point extraction algorithms, which allow for accurate capture of features such as the pet's eyes, nose, and mouth. Furthermore, it can also estimate the pet's emotions using machine learning algorithms. For example, it can train an emotion recognition model using deep learning to accurately estimate emotions such as joy, sadness, anger, and surprise from the pet's facial expressions. The facial expression analysis unit analyzes the pet's facial expressions in real time, understanding the pet's emotions and state. This allows owners to instantly know about changes in their pet's emotions and take appropriate action. Additionally, the facial expression analysis unit can accumulate past facial expression data and analyze long-term emotional trends. This allows for continuous monitoring of the pet's health and stress levels, enabling early detection of abnormalities. For example, if a pet frequently displays sad expressions, this can be interpreted as a sign of stress or health problems, allowing for early intervention.

[0031] The voice analysis unit analyzes pets' voices. For example, it uses speech recognition technology to analyze pets' voices. Specifically, it collects pets' voices using a microphone and processes the audio data in real time. Speech recognition technology includes speech signal processing algorithms and feature extraction algorithms, which allow for accurate capture of characteristics such as frequency components, volume, and duration of the pet's voice. Furthermore, it can extract features of the pet's voice using frequency analysis. For example, it uses Fourier transform to decompose the audio signal into frequency components and analyze the energy distribution in a specific frequency band. This allows for a detailed understanding of the pet's voice characteristics and the estimation of specific emotions or states. The voice analysis unit learns from pets' voices and analyzes the sounds they make to understand their meaning. For example, it uses machine learning algorithms to learn patterns in pets' voices and estimate what specific sounds mean. This makes it easier for owners to understand their pets' needs and emotions from their voices. Additionally, the voice analysis unit can detect abnormal voice patterns, enabling early detection of health problems or signs of stress. For example, if your pet frequently makes unusual noises, it could be a sign of a health problem, so it is recommended to consult a veterinarian as soon as possible.

[0032] The tracking unit tracks the pet's movements. For example, it uses camera tracking technology to track the pet's movements. Specifically, it uses a camera to capture the pet's movements and processes the video data in real time. Camera tracking technology includes object detection algorithms and tracking algorithms, which allow for accurate capture of the pet's position and movements. Furthermore, it can also detect the pet's movements using sensor data analysis. For example, it can detect the pet's movements using acceleration sensors and gyroscopes, and analyze this data to detect patterns and abnormal movements. The tracking unit tracks the pet's movements in real time and detects abnormal movements and behaviors. This allows pet owners to immediately know of changes in their pet's movements and take appropriate action. Additionally, the tracking unit can accumulate past movement data and analyze long-term movement trends. This allows for continuous monitoring of the pet's health and activity level, enabling early detection of abnormalities. For example, if a pet's activity level is lower than normal, it can be interpreted as a sign of health problems or stress, allowing for early intervention.

[0033] The notification unit notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. The notification unit notifies the owner, for example, using smartphone notifications. Specifically, it notifies the owner in real time about information regarding the pet's emotions and condition through a smartphone app. The notification content includes the results of the pet's facial expression analysis, voice analysis, and movement analysis results from the tracking unit, allowing the owner to understand the pet's condition in detail. The notification unit can also notify the owner using voice notifications. For example, it notifies the owner of information regarding the pet's condition by voice through a smart speaker. This allows the owner to check the pet's condition without using their hands. The notification unit notifies the owner of the pet's emotions and condition. This allows the owner to immediately know about changes in the pet's emotions and health condition and take appropriate action. Furthermore, the notification unit can also accumulate past notification history and analyze long-term trends. This allows for continuous monitoring of changes in the pet's emotions and health condition and early detection of abnormalities. For example, if a pet is frequently stressed, the cause can be identified and countermeasures can be taken early.

[0034] The pet communication system includes a health monitoring unit that monitors the pet's health status. The health monitoring unit can, for example, measure body temperature. The health monitoring unit can also measure heart rate. For example, the health monitoring unit can measure the pet's body temperature in real time and detect abnormalities. The health monitoring unit can also measure heart rate in real time and detect abnormalities. This allows for early detection of abnormalities and appropriate action by monitoring the pet's health status. Some or all of the above-described processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input the pet's body temperature data into a generating AI and have the generating AI perform abnormality detection from the body temperature data.

[0035] The pet communication system includes a training support unit to assist in training management. The training support unit performs, for example, behavioral analysis. The training support unit can also perform training using a reward system. The training support unit analyzes the pet's behavior in real time and evaluates the effectiveness of training. The training support unit can also reinforce the pet's behavior using a reward system. As a result, by including the training support unit, pet training management can be performed efficiently. Some or all of the above-described processes in the training support unit may be performed using, for example, AI, or without AI. For example, the training support unit can input pet behavioral data into a generating AI and have the generating AI perform a process to evaluate the effectiveness of training from the behavioral data.

[0036] The facial expression analysis unit can analyze a pet's facial expressions in real time and understand the pet's emotions and state. The facial expression analysis unit can, for example, use image processing technology to analyze the pet's facial expressions in real time. The facial expression analysis unit can also estimate the pet's emotions using machine learning algorithms. The facial expression analysis unit can, for example, analyze the pet's facial expressions in real time and instantly understand the pet's emotions and state. This allows for instant understanding of the pet's emotions and state by analyzing the pet's facial expressions in real time. Some or all of the above-described processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's facial expression data into a generating AI and have the generating AI perform the estimation of emotions and state from the facial expression data.

[0037] The voice analysis unit can learn the pet's voice and analyze the sounds the pet makes to understand their meaning. The voice analysis unit can learn the pet's voice, for example, using speech recognition technology. The voice analysis unit can also extract the characteristics of the pet's voice using frequency analysis. The voice analysis unit can learn the pet's voice and analyze the sounds the pet makes to understand their meaning. As a result, by learning the pet's voice and analyzing the sounds, it is possible to understand the pet's intentions and emotions. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's voice data into a generating AI and have the generating AI perform meaning comprehension from the voice data.

[0038] The tracking unit can track the pet's movements and detect abnormal movements or behaviors. The tracking unit can track the pet's movements using, for example, camera tracking technology. The tracking unit can also detect the pet's movements using sensor data analysis. The tracking unit can, for example, track the pet's movements in real time and detect abnormal movements or behaviors. This ensures the pet's health and safety by tracking its movements and detecting abnormal behaviors. Some or all of the above-described processes in the tracking unit may be performed using, for example, AI, or without AI. For example, the tracking unit can input pet movement data into a generating AI and have the generating AI perform anomaly detection from the movement data.

[0039] The facial expression analysis unit can estimate the pet's emotions and adjust the content of notifications to the owner based on the estimated emotions. The facial expression analysis unit can estimate the pet's emotions using, for example, a facial expression recognition algorithm. The facial expression analysis unit can also estimate the pet's emotions using a voice analysis algorithm. The facial expression analysis unit can, for example, estimate the pet's emotions and adjust the content of notifications to the owner based on the estimated emotions. This allows the unit to provide appropriate advice to the owner by adjusting the notification content based on the pet's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, AI, or not using AI. For example, the facial expression analysis unit can input the pet's facial expression data into a generative AI and have the generative AI perform emotion estimation from the facial expression data.

[0040] The facial expression analysis unit can improve its analysis accuracy by referring to the pet's past facial expression data during facial expression analysis. For example, the facial expression analysis unit can learn specific emotional patterns of the pet based on past facial expression data to improve analysis accuracy. The facial expression analysis unit can also compare past facial expression data with current facial expressions to detect abnormal changes. The facial expression analysis unit can also analyze changes in the pet's emotions over time using past facial expression data. This improves analysis accuracy by referring to past facial expression data, allowing for a more accurate understanding of the pet's emotions. Some or all of the above processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's past facial expression data into a generating AI and have the generating AI perform a process to analyze the current facial expression based on the past data.

[0041] The facial expression analysis unit can apply different analysis algorithms depending on the type and age of the pet during facial expression analysis. For example, the facial expression analysis unit can apply different facial expression analysis algorithms to dogs and cats to improve analysis accuracy. The facial expression analysis unit can also apply different analysis algorithms to young pets and elderly pets to accurately grasp changes in emotion. The facial expression analysis unit can also apply analysis algorithms specialized for specific breeds to improve analysis accuracy. In this way, analysis accuracy is improved by applying analysis algorithms appropriate to the type and age of the pet. Some or all of the above processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate analysis algorithm.

[0042] The facial expression analysis unit can estimate the pet's emotions and predict the pet's behavior based on the estimated emotions. For example, if the pet is feeling anxious, the facial expression analysis unit may predict that it may run away. If the pet is excited, the facial expression analysis unit may also predict that it will want to play. If the pet is tired, the facial expression analysis unit may also predict that it will rest. This allows pet owners to anticipate their pet's behavior by predicting it based on its emotions. Some or all of the above processing in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's emotional data into a generating AI and have the generating AI predict behavior from the emotional data.

[0043] The facial expression analysis unit can improve the accuracy of its analysis by using biometric information such as the pet's body temperature and heart rate during facial expression analysis. For example, the facial expression analysis unit may analyze that a high body temperature indicates stress or excitement. It can also analyze that an elevated heart rate indicates excitement or a post-exercise state. The facial expression analysis unit can also combine changes in the pet's body temperature and heart rate to more accurately analyze changes in emotion. As a result, the accuracy of the analysis is improved by using biometric information, allowing for a more accurate understanding of the pet's emotions. Some or all of the above-described processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's body temperature and heart rate data into a generating AI and have the generating AI perform an emotional analysis based on the biometric information.

[0044] The facial expression analysis unit can perform facial expression analysis while considering the pet's living environment (room temperature, humidity, etc.). For example, if the room temperature is high, the facial expression analysis unit may analyze that the pet may be feeling hot. If the humidity is low, the facial expression analysis unit may analyze that the pet may be feeling dry. The facial expression analysis unit can also analyze changes in the pet's emotions by considering changes in the living environment. This allows for a more accurate analysis of changes in the pet's emotions by considering the living environment. Some or all of the above processing in the facial expression analysis unit may be performed using AI, for example, or without using AI. For example, the facial expression analysis unit can input pet living environment data into a generating AI and have the generating AI perform emotional analysis based on the environmental data.

[0045] The voice analysis unit can estimate the pet's emotions and notify the owner of the voice analysis results based on the estimated emotions. For example, if the pet is feeling anxious, the voice analysis unit can notify the owner with advice on how to calm the pet down. If the pet is excited, the voice analysis unit can also notify the owner with ways to calm the pet down. If the pet is tired, the voice analysis unit can also notify the owner with suggestions for resting. In this way, by notifying the owner of the voice analysis results based on the pet's emotions, appropriate advice can be provided to the owner. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's voice data into a generating AI and have the generating AI perform the process of notifying the owner of the analysis results based on the emotion data.

[0046] The voice analysis unit can improve its analysis accuracy by referring to the pet's past voice data during voice analysis. For example, the voice analysis unit can learn specific emotional patterns of the pet based on past voice data to improve analysis accuracy. The voice analysis unit can also compare past voice data with the current voice to detect abnormal changes. The voice analysis unit can also analyze changes in the pet's emotions over time using past voice data. This improves analysis accuracy by referring to past voice data, allowing for a more accurate understanding of the pet's emotions. Some or all of the above processes in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's past voice data into a generating AI and have the generating AI perform the process of analyzing the current voice based on the past data.

[0047] The voice analysis unit can apply different analysis algorithms depending on the type and age of the pet during voice analysis. For example, the voice analysis unit can apply different voice analysis algorithms to dogs and cats to improve analysis accuracy. The voice analysis unit can also apply different analysis algorithms to young and elderly pets to accurately grasp changes in their emotions. The voice analysis unit can also apply analysis algorithms specialized for specific breeds to improve analysis accuracy. In this way, analysis accuracy is improved by applying analysis algorithms appropriate to the type and age of the pet. Some or all of the above processes in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate analysis algorithm.

[0048] The voice analysis unit can estimate the pet's emotions and predict the pet's behavior based on the estimated emotions. For example, if the pet is feeling anxious, the voice analysis unit may predict that it may run away. If the pet is excited, the voice analysis unit may also predict that it will want to play. If the pet is tired, the voice analysis unit may also predict that it will rest. This allows pet owners to anticipate their pet's behavior by predicting it based on its emotions. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's emotional data into a generating AI and have the generating AI predict behavior from the emotional data.

[0049] The voice analysis unit can improve the accuracy of its voice analysis by using the pet's physical condition and health status in conjunction with the voice analysis. For example, if the pet is unwell, the voice analysis unit can analyze changes in its voice to understand its health status. If the pet is in good health, the voice analysis unit can also analyze changes in its voice to understand changes in its emotions. The voice analysis unit can also combine the pet's physical condition and changes in its voice to more accurately analyze changes in its emotions. As a result, by using physical condition and health status in conjunction with the voice analysis unit, the accuracy of the analysis is improved, and the pet's emotions can be understood more accurately. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's physical condition data into a generating AI and have the generating AI perform voice analysis based on the physical condition data.

[0050] The voice analysis unit can perform voice analysis while considering the pet's living environment (such as noise levels). For example, if the noise level is high, the voice analysis unit may analyze that the pet is experiencing stress. If the noise level is low, the voice analysis unit may analyze that the pet is relaxed. The voice analysis unit can also analyze changes in the pet's emotions by considering changes in the living environment. This allows for a more accurate analysis of changes in the pet's emotions by considering the living environment. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input pet living environment data into a generating AI and have the generating AI perform voice analysis based on the environmental data.

[0051] The tracking unit can estimate the pet's emotions and adjust its tracking method based on the estimated emotions. For example, if the pet is feeling anxious, the tracking unit can shorten the tracking distance to reassure it. If the pet is excited, the tracking unit can also adjust the tracking speed to ensure its safety. If the pet is tired, the tracking unit can reduce the frequency of tracking to allow it to rest. In this way, the safety and comfort of the pet can be ensured by adjusting the tracking method based on its emotions. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the tracking method based on the emotion data.

[0052] The tracking unit can improve tracking accuracy by referring to the pet's past behavioral data during tracking. For example, the tracking unit can learn specific behavioral patterns of the pet based on past behavioral data to improve tracking accuracy. The tracking unit can also compare past behavioral data with current behavior to detect abnormal changes. The tracking unit can also analyze changes in the pet's behavior over time using past behavioral data. As a result, by referring to past behavioral data, tracking accuracy is improved and the pet's behavior can be accurately understood. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the pet's past behavioral data into a generating AI and have the generating AI perform a process to analyze the current behavior based on the past data.

[0053] The tracking unit can apply different tracking algorithms depending on the type and age of the pet during tracking. For example, the tracking unit can apply different tracking algorithms to dogs and cats to improve tracking accuracy. The tracking unit can also apply different tracking algorithms to young and elderly pets to accurately grasp changes in their behavior. The tracking unit can also apply tracking algorithms specialized for specific breeds to improve tracking accuracy. In this way, tracking accuracy is improved by applying tracking algorithms appropriate to the type and age of the pet. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate tracking algorithm.

[0054] The tracking unit can estimate the pet's emotions and detect abnormal behavior based on the estimated emotions. For example, if the pet is feeling anxious, the tracking unit can detect abnormal behavior and notify the owner. If the pet is excited, the tracking unit can also detect dangerous behavior and notify the owner. If the pet is tired, the tracking unit can also detect abnormal resting behavior and notify the owner. This allows for rapid notification to the owner by detecting abnormal behavior based on the pet's emotions. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet emotion data into a generating AI and have the generating AI perform the process of detecting abnormal behavior based on the emotion data.

[0055] The tracking unit can improve tracking accuracy by using the pet's physical condition and health status during tracking. For example, if the pet is unwell, the tracking unit will increase the tracking frequency to monitor its health. If the pet is in good health, the tracking unit can also reduce the tracking frequency to reduce stress. The tracking unit can also improve tracking accuracy by combining changes in the pet's physical condition and behavior. As a result, by using physical condition and health status in combination, tracking accuracy is improved and the pet's behavior can be understood more accurately. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet physical condition data into a generating AI and have the generating AI perform processing to improve tracking accuracy based on the physical condition data.

[0056] The tracking unit can perform tracking while considering the pet's living environment (such as the room layout). For example, the tracking unit can track the pet along a route that is easy for the pet to move along, taking the room layout into consideration. The tracking unit can also analyze changes in the pet's behavior by considering changes in the living environment. The tracking unit can also track the pet while ensuring its safety by avoiding obstacles in the room. This allows for a more accurate analysis of changes in the pet's behavior by considering the living environment. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet living environment data into a generating AI and have the generating AI perform tracking based on the environmental data.

[0057] The notification unit can estimate the pet's emotions and customize the notification content based on the estimated emotions. For example, if the pet is feeling anxious, the notification unit will notify the owner with advice to reassure them. If the pet is excited, the notification unit can also notify the owner with ways to calm the pet down. If the pet is tired, the notification unit can also notify the owner with suggestions for resting. In this way, by customizing the notification content based on the pet's emotions, the notification unit can provide the owner with appropriate advice. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input pet emotion data into a generating AI and have the generating AI perform the process of customizing the notification content based on the emotion data.

[0058] The notification unit can optimize the notification method by referring to the owner's past response data when sending a notification. For example, the notification unit will prioritize using notification methods (voice, text, etc.) that the owner has preferred in the past. The notification unit can also suggest the optimal notification timing based on the owner's past response data. The notification unit can also analyze the owner's past response data and suggest the most effective notification content. As a result, by referring to past response data, the notification method is optimized, enabling effective notifications to the owner. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the owner's past response data into a generating AI and have the generating AI perform the process of optimizing the notification method based on the response data.

[0059] The notification unit can apply different notification methods depending on the type and age of the pet when it sends a notification. For example, the notification unit can apply different notification methods for dogs and cats to provide the owner with the most appropriate information. The notification unit can also apply different notification methods for young pets and elderly pets to provide the owner with appropriate advice. The notification unit can also apply notification methods specific to particular breeds to provide the owner with the most appropriate information. In this way, by applying notification methods according to the type and age of the pet, the owner can be provided with the most appropriate information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input data according to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate notification method.

[0060] The notification unit can estimate the pet's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the pet is feeling anxious, the notification unit will immediately notify the owner. If the pet is excited, the notification unit can also notify the owner when the pet has calmed down. If the pet is tired, the notification unit can also notify the owner after the pet has rested. By adjusting the timing of notifications based on the pet's emotions, it is possible to notify the owner at an appropriate time. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the timing of notifications based on the emotion data.

[0061] The notification unit can select a notification method when sending a notification, taking into account the owner's current situation (e.g., at home, out). For example, if the owner is at home, the notification unit may prioritize voice notifications. If the owner is out, the notification unit may also prioritize text notifications. The notification unit can also select the most suitable notification method by considering the owner's current situation. This allows the notification unit to select the most suitable notification method by considering the owner's current situation. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input data on the owner's current situation into a generating AI and have the generating AI perform the process of selecting a notification method based on the situation data.

[0062] The notification unit can enrich its notifications by using pet health status and behavioral data in conjunction with them. For example, if a pet's health is poor, the notification unit will notify the owner with detailed health management advice. The notification unit can also notify the owner with appropriate behavioral advice based on the pet's behavioral data. The notification unit can also provide the owner with optimal information by combining the pet's health status and behavioral data. As a result, by using health status and behavioral data in combination, the notification content can be enriched and the owner can be provided with optimal information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input pet health status data and behavioral data into a generating AI and have the generating AI perform processing to enrich the notification content based on the data.

[0063] The health monitoring unit can estimate the pet's emotions and adjust the health monitoring method based on the estimated emotions. For example, if the pet is feeling anxious, the health monitoring unit can increase the frequency of health monitoring to monitor its condition. If the pet is excited, the health monitoring unit can also adjust the health monitoring method to ensure its safety. If the pet is tired, the health monitoring unit can also decrease the frequency of health monitoring to allow it to rest. By adjusting the health monitoring method based on the pet's emotions, the pet's health condition can be understood more accurately. Some or all of the above processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the monitoring method based on the emotion data.

[0064] The health monitoring unit can improve monitoring accuracy by referring to the pet's past health data during health monitoring. For example, the health monitoring unit can learn specific health patterns of the pet based on past health data to improve monitoring accuracy. The health monitoring unit can also compare past health data with the current health status to detect abnormal changes. The health monitoring unit can also analyze changes in the pet's health status over time using past health data. As a result, by referring to past health data, monitoring accuracy is improved and the pet's health status can be accurately understood. Some or all of the above processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input the pet's past health data into a generating AI and have the generating AI perform a process to analyze the current health status based on the past data.

[0065] The health monitoring unit can apply different monitoring algorithms depending on the type and age of the pet during health monitoring. For example, the health monitoring unit can apply different monitoring algorithms to dogs and cats to improve monitoring accuracy. The health monitoring unit can also apply different monitoring algorithms to young pets and elderly pets to accurately grasp changes in their health status. The health monitoring unit can also apply monitoring algorithms specialized for specific breeds to improve monitoring accuracy. In this way, monitoring accuracy is improved by applying monitoring algorithms appropriate to the type and age of the pet. Some or all of the above processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate monitoring algorithm.

[0066] The health monitoring unit can estimate the pet's emotions and detect abnormalities in its health based on the estimated emotions. For example, if the pet is feeling anxious, the health monitoring unit can detect an abnormal health condition and notify the owner. If the pet is excited, the health monitoring unit can also detect a dangerous health condition and notify the owner. If the pet is tired, the health monitoring unit can also detect an abnormal health condition and notify the owner. This allows for rapid notification to the owner by detecting abnormalities in the pet's health based on its emotions. Some or all of the above-described processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input pet emotion data into a generating AI and have the generating AI perform a process to detect abnormalities in the health condition based on the emotion data.

[0067] The health monitoring unit can perform monitoring while taking into account the pet's living environment (room temperature, humidity, etc.). For example, if the room temperature is high, the health monitoring unit will carefully monitor the pet's health. The health monitoring unit can also carefully monitor the pet's health if the humidity is low. The health monitoring unit can also monitor the pet's health while taking into account changes in the living environment. This allows for more accurate monitoring of the pet's health by considering the living environment. Some or all of the above-described processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input pet living environment data into a generating AI and have the generating AI perform the process of monitoring based on the environmental data.

[0068] The training support unit can estimate the pet's emotions and adjust training methods based on the estimated emotions. For example, if the pet is feeling anxious, the training support unit can suggest gentle training methods. If the pet is excited, the training support unit can also suggest training methods to calm the pet. If the pet is tired, the training support unit can also suggest training methods to allow the pet to rest. This allows for appropriate training of the pet by adjusting training methods based on the pet's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the training support unit may be performed using AI, for example, or not using AI. For example, the training support unit can input pet emotion data into a generative AI and have the generative AI perform the process of adjusting training methods based on the emotion data.

[0069] The training support unit can optimize training methods by referring to the pet's past training data during training. For example, the training support unit can learn specific training patterns of pets based on past training data and optimize training methods. The training support unit can also compare past training data with the current training status and propose the optimal training method. The training support unit can also analyze changes in the pet's training over time using past training data. As a result, by referring to past training data, training methods can be optimized, enabling effective training for pets. Some or all of the above processes in the training support unit may be performed using AI, for example, or without AI. For example, the training support unit can input the pet's past training data into a generating AI and have the generating AI perform the process of optimizing the current training method based on the past data.

[0070] The training support unit can apply different training algorithms depending on the type and age of the pet during training. For example, the training support unit can apply different training algorithms to dogs and cats to optimize the training method. The training support unit can also apply different training algorithms to young and elderly pets to accurately understand changes in training. The training support unit can also apply training algorithms specialized for specific breeds to optimize the training method. In this way, the training method is optimized by applying training algorithms that are appropriate for the type and age of the pet. Some or all of the above processes in the training support unit may be performed using AI, for example, or not using AI. For example, the training support unit can input data according to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate training algorithm.

[0071] The training support unit can estimate the pet's emotions and adjust the timing of training based on those emotions. For example, if the pet is feeling anxious, the training support unit can delay training to help the pet feel secure. If the pet is excited, the training support unit can wait until the pet is calm before training. If the pet is tired, the training support unit can wait until the pet has rested before training. By adjusting the timing of training based on the pet's emotions, appropriate training becomes possible. Some or all of the above processes in the training support unit may be performed using AI, for example, or without AI. For example, the training support unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the timing of training based on the emotion data.

[0072] The training support department can select a training method while considering the pet's living environment (such as the room layout) during training support. For example, the training support department can create an environment that is conducive to training by considering the room layout. The training support department can also select the optimal training method by considering changes in the living environment. The training support department can also create an environment where the pet can be safely trained by avoiding obstacles in the room. In this way, the optimal training method for the pet can be selected by considering the living environment. Some or all of the above processes in the training support department may be performed using AI, for example, or without using AI. For example, the training support department can input pet living environment data into a generating AI and have the generating AI perform the process of selecting a training method based on the environmental data.

[0073] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0074] The pet communication system may include a meal management unit to assist with pet diet management. The meal management unit monitors the pet's food intake and nutritional balance, and provides an appropriate meal plan. For example, the meal management unit can calculate the appropriate food intake based on the pet's weight and activity level. It can also record the pet's dietary history and evaluate its nutritional balance. Furthermore, the meal management unit can suggest a meal plan to supplement specific nutrients according to the pet's health condition. This helps maintain the pet's health and enables proper nutritional management. Some or all of the above processes in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input pet dietary data into a generating AI, which can then execute an appropriate meal plan based on that data.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The facial expression analysis unit analyzes the pet's facial expressions. For example, it uses image processing technology and machine learning algorithms to understand the pet's emotions and state in real time. Step 2: The voice analysis unit analyzes the pet's voice. For example, it uses speech recognition technology and frequency analysis to extract the characteristics of the pet's voice and analyzes the sounds the pet makes to understand their meaning. Step 3: The tracking unit tracks the pet's movements. For example, it uses camera tracking technology or sensor data analysis to track the pet's movements in real time and detect abnormal movements or behaviors. Step 4: The notification unit notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. For example, it notifies the owner of the pet's emotions and condition using smartphone notifications or voice notifications.

[0077] (Example of form 2) An embodiment of the present invention provides a pet communication system that uses an AI smart camera and a speaker to communicate with and manage the health of pets. This pet communication system analyzes the pet's facial expressions in real time to understand the pet's emotions and condition. Furthermore, it learns the pet's voice and analyzes the sounds the pet makes to understand their meaning. It can also track the pet's movements and detect abnormal movements and behaviors. This enables deeper communication with pets and can be used for health management and training management. For example, the pet communication system uses an AI smart camera to analyze the pet's facial expressions in real time. The AI ​​smart camera captures the pet's facial expressions and analyzes the image data. The analysis results are used to understand the pet's emotions and condition. Next, the pet communication system uses an AI speaker to learn the pet's voice. The AI ​​speaker records the pet's voice and analyzes the audio data. The analysis results are used to understand the meaning of the sounds the pet makes. Furthermore, the pet communication system uses a tracking unit to track the pet's movements. The tracking unit tracks the pet's movements in real time and detects abnormal movements and behaviors. For example, if a pet makes an unusual movement, the tracking unit detects the movement and notifies the owner. This allows the owner to be assured of the pet's health and safety. Thus, the pet communication system enables deeper communication and health management with pets.

[0078] The pet communication system according to this embodiment comprises a facial expression analysis unit, a voice analysis unit, a tracking unit, and a notification unit. The facial expression analysis unit analyzes the pet's facial expressions. The facial expression analysis unit analyzes the pet's facial expressions using, for example, image processing technology. The facial expression analysis unit can also estimate the pet's emotions using machine learning algorithms. The facial expression analysis unit analyzes the pet's facial expressions in real time to understand the pet's emotions and state. The voice analysis unit analyzes the pet's voice. The voice analysis unit analyzes the pet's voice using, for example, speech recognition technology. The voice analysis unit can also extract features of the pet's voice using frequency analysis. The voice analysis unit learns the pet's voice and analyzes the sounds the pet makes to understand their meaning. The tracking unit tracks the pet's movements. The tracking unit tracks the pet's movements using, for example, camera tracking technology. The tracking unit can also detect the pet's movements using sensor data analysis. The tracking unit tracks the pet's movements in real time to detect abnormal movements and behaviors. The notification unit notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. The notification unit notifies the owner, for example, using smartphone notifications. The notification unit can also notify the owner using voice notifications. The notification unit notifies the owner, for example, of the pet's emotions and condition. As a result, the pet communication system according to this embodiment analyzes the pet's facial expressions, voice, and movements and notifies the owner, enabling deeper communication with the pet and health management.

[0079] The facial expression analysis unit analyzes the pet's facial expressions. For example, it uses image processing technology to analyze the pet's expressions. Specifically, it uses a camera to capture the pet's face and processes the image data in real time. Image processing technology includes face detection algorithms and feature point extraction algorithms, which allow for accurate capture of features such as the pet's eyes, nose, and mouth. Furthermore, it can also estimate the pet's emotions using machine learning algorithms. For example, it can train an emotion recognition model using deep learning to accurately estimate emotions such as joy, sadness, anger, and surprise from the pet's facial expressions. The facial expression analysis unit analyzes the pet's facial expressions in real time, understanding the pet's emotions and state. This allows owners to instantly know about changes in their pet's emotions and take appropriate action. Additionally, the facial expression analysis unit can accumulate past facial expression data and analyze long-term emotional trends. This allows for continuous monitoring of the pet's health and stress levels, enabling early detection of abnormalities. For example, if a pet frequently displays sad expressions, this can be interpreted as a sign of stress or health problems, allowing for early intervention.

[0080] The voice analysis unit analyzes pets' voices. For example, it uses speech recognition technology to analyze pets' voices. Specifically, it collects pets' voices using a microphone and processes the audio data in real time. Speech recognition technology includes speech signal processing algorithms and feature extraction algorithms, which allow for accurate capture of characteristics such as frequency components, volume, and duration of the pet's voice. Furthermore, it can extract features of the pet's voice using frequency analysis. For example, it uses Fourier transform to decompose the audio signal into frequency components and analyze the energy distribution in a specific frequency band. This allows for a detailed understanding of the pet's voice characteristics and the estimation of specific emotions or states. The voice analysis unit learns from pets' voices and analyzes the sounds they make to understand their meaning. For example, it uses machine learning algorithms to learn patterns in pets' voices and estimate what specific sounds mean. This makes it easier for owners to understand their pets' needs and emotions from their voices. Additionally, the voice analysis unit can detect abnormal voice patterns, enabling early detection of health problems or signs of stress. For example, if your pet frequently makes unusual noises, it could be a sign of a health problem, so it is recommended to consult a veterinarian as soon as possible.

[0081] The tracking unit tracks the pet's movements. For example, it uses camera tracking technology to track the pet's movements. Specifically, it uses a camera to capture the pet's movements and processes the video data in real time. Camera tracking technology includes object detection algorithms and tracking algorithms, which allow for accurate capture of the pet's position and movements. Furthermore, it can also detect the pet's movements using sensor data analysis. For example, it can detect the pet's movements using acceleration sensors and gyroscopes, and analyze this data to detect patterns and abnormal movements. The tracking unit tracks the pet's movements in real time and detects abnormal movements and behaviors. This allows pet owners to immediately know of changes in their pet's movements and take appropriate action. Additionally, the tracking unit can accumulate past movement data and analyze long-term movement trends. This allows for continuous monitoring of the pet's health and activity level, enabling early detection of abnormalities. For example, if a pet's activity level is lower than normal, it can be interpreted as a sign of health problems or stress, allowing for early intervention.

[0082] The notification unit notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. The notification unit notifies the owner, for example, using smartphone notifications. Specifically, it notifies the owner in real time about information regarding the pet's emotions and condition through a smartphone app. The notification content includes the results of the pet's facial expression analysis, voice analysis, and movement analysis results from the tracking unit, allowing the owner to understand the pet's condition in detail. The notification unit can also notify the owner using voice notifications. For example, it notifies the owner of information regarding the pet's condition by voice through a smart speaker. This allows the owner to check the pet's condition without using their hands. The notification unit notifies the owner of the pet's emotions and condition. This allows the owner to immediately know about changes in the pet's emotions and health condition and take appropriate action. Furthermore, the notification unit can also accumulate past notification history and analyze long-term trends. This allows for continuous monitoring of changes in the pet's emotions and health condition and early detection of abnormalities. For example, if a pet is frequently stressed, the cause can be identified and countermeasures can be taken early.

[0083] The pet communication system includes a health monitoring unit that monitors the pet's health status. The health monitoring unit can, for example, measure body temperature. The health monitoring unit can also measure heart rate. For example, the health monitoring unit can measure the pet's body temperature in real time and detect abnormalities. The health monitoring unit can also measure heart rate in real time and detect abnormalities. This allows for early detection of abnormalities and appropriate action by monitoring the pet's health status. Some or all of the above-described processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input the pet's body temperature data into a generating AI and have the generating AI perform abnormality detection from the body temperature data.

[0084] The pet communication system includes a training support unit to assist in training management. The training support unit performs, for example, behavioral analysis. The training support unit can also perform training using a reward system. The training support unit analyzes the pet's behavior in real time and evaluates the effectiveness of training. The training support unit can also reinforce the pet's behavior using a reward system. As a result, by including the training support unit, pet training management can be performed efficiently. Some or all of the above-described processes in the training support unit may be performed using, for example, AI, or without AI. For example, the training support unit can input pet behavioral data into a generating AI and have the generating AI perform a process to evaluate the effectiveness of training from the behavioral data.

[0085] The facial expression analysis unit can analyze a pet's facial expressions in real time and understand the pet's emotions and state. The facial expression analysis unit can, for example, use image processing technology to analyze the pet's facial expressions in real time. The facial expression analysis unit can also estimate the pet's emotions using machine learning algorithms. The facial expression analysis unit can, for example, analyze the pet's facial expressions in real time and instantly understand the pet's emotions and state. This allows for instant understanding of the pet's emotions and state by analyzing the pet's facial expressions in real time. Some or all of the above-described processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's facial expression data into a generating AI and have the generating AI perform the estimation of emotions and state from the facial expression data.

[0086] The voice analysis unit can learn the pet's voice and analyze the sounds the pet makes to understand their meaning. The voice analysis unit can learn the pet's voice, for example, using speech recognition technology. The voice analysis unit can also extract the characteristics of the pet's voice using frequency analysis. The voice analysis unit can learn the pet's voice and analyze the sounds the pet makes to understand their meaning. As a result, by learning the pet's voice and analyzing the sounds, it is possible to understand the pet's intentions and emotions. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's voice data into a generating AI and have the generating AI perform meaning comprehension from the voice data.

[0087] The tracking unit can track the pet's movements and detect abnormal movements or behaviors. The tracking unit can track the pet's movements using, for example, camera tracking technology. The tracking unit can also detect the pet's movements using sensor data analysis. The tracking unit can, for example, track the pet's movements in real time and detect abnormal movements or behaviors. This ensures the pet's health and safety by tracking its movements and detecting abnormal behaviors. Some or all of the above-described processes in the tracking unit may be performed using, for example, AI, or without AI. For example, the tracking unit can input pet movement data into a generating AI and have the generating AI perform anomaly detection from the movement data.

[0088] The facial expression analysis unit can estimate the pet's emotions and adjust the content of notifications to the owner based on the estimated emotions. The facial expression analysis unit can estimate the pet's emotions using, for example, a facial expression recognition algorithm. The facial expression analysis unit can also estimate the pet's emotions using a voice analysis algorithm. The facial expression analysis unit can, for example, estimate the pet's emotions and adjust the content of notifications to the owner based on the estimated emotions. This allows the unit to provide appropriate advice to the owner by adjusting the notification content based on the pet's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, AI, or not using AI. For example, the facial expression analysis unit can input the pet's facial expression data into a generative AI and have the generative AI perform emotion estimation from the facial expression data.

[0089] The facial expression analysis unit can improve its analysis accuracy by referring to the pet's past facial expression data during facial expression analysis. For example, the facial expression analysis unit can learn specific emotional patterns of the pet based on past facial expression data to improve analysis accuracy. The facial expression analysis unit can also compare past facial expression data with current facial expressions to detect abnormal changes. The facial expression analysis unit can also analyze changes in the pet's emotions over time using past facial expression data. This improves analysis accuracy by referring to past facial expression data, allowing for a more accurate understanding of the pet's emotions. Some or all of the above processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's past facial expression data into a generating AI and have the generating AI perform a process to analyze the current facial expression based on the past data.

[0090] The facial expression analysis unit can apply different analysis algorithms depending on the type and age of the pet during facial expression analysis. For example, the facial expression analysis unit can apply different facial expression analysis algorithms to dogs and cats to improve analysis accuracy. The facial expression analysis unit can also apply different analysis algorithms to young pets and elderly pets to accurately grasp changes in emotion. The facial expression analysis unit can also apply analysis algorithms specialized for specific breeds to improve analysis accuracy. In this way, analysis accuracy is improved by applying analysis algorithms appropriate to the type and age of the pet. Some or all of the above processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate analysis algorithm.

[0091] The facial expression analysis unit can estimate the pet's emotions and predict the pet's behavior based on the estimated emotions. For example, if the pet is feeling anxious, the facial expression analysis unit may predict that it may run away. If the pet is excited, the facial expression analysis unit may also predict that it will want to play. If the pet is tired, the facial expression analysis unit may also predict that it will rest. This allows pet owners to anticipate their pet's behavior by predicting it based on its emotions. Some or all of the above processing in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's emotional data into a generating AI and have the generating AI predict behavior from the emotional data.

[0092] The facial expression analysis unit can improve the accuracy of its analysis by using biometric information such as the pet's body temperature and heart rate during facial expression analysis. For example, the facial expression analysis unit may analyze that a high body temperature indicates stress or excitement. It can also analyze that an elevated heart rate indicates excitement or a post-exercise state. The facial expression analysis unit can also combine changes in the pet's body temperature and heart rate to more accurately analyze changes in emotion. As a result, the accuracy of the analysis is improved by using biometric information, allowing for a more accurate understanding of the pet's emotions. Some or all of the above-described processes in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the pet's body temperature and heart rate data into a generating AI and have the generating AI perform an emotional analysis based on the biometric information.

[0093] The facial expression analysis unit can perform facial expression analysis while considering the pet's living environment (room temperature, humidity, etc.). For example, if the room temperature is high, the facial expression analysis unit may analyze that the pet may be feeling hot. If the humidity is low, the facial expression analysis unit may analyze that the pet may be feeling dry. The facial expression analysis unit can also analyze changes in the pet's emotions by considering changes in the living environment. This allows for a more accurate analysis of changes in the pet's emotions by considering the living environment. Some or all of the above processing in the facial expression analysis unit may be performed using AI, for example, or without using AI. For example, the facial expression analysis unit can input pet living environment data into a generating AI and have the generating AI perform emotional analysis based on the environmental data.

[0094] The voice analysis unit can estimate the pet's emotions and notify the owner of the voice analysis results based on the estimated emotions. For example, if the pet is feeling anxious, the voice analysis unit can notify the owner with advice on how to calm the pet down. If the pet is excited, the voice analysis unit can also notify the owner with ways to calm the pet down. If the pet is tired, the voice analysis unit can also notify the owner with suggestions for resting. In this way, by notifying the owner of the voice analysis results based on the pet's emotions, appropriate advice can be provided to the owner. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's voice data into a generating AI and have the generating AI perform the process of notifying the owner of the analysis results based on the emotion data.

[0095] The voice analysis unit can improve its analysis accuracy by referring to the pet's past voice data during voice analysis. For example, the voice analysis unit can learn specific emotional patterns of the pet based on past voice data to improve analysis accuracy. The voice analysis unit can also compare past voice data with the current voice to detect abnormal changes. The voice analysis unit can also analyze changes in the pet's emotions over time using past voice data. This improves analysis accuracy by referring to past voice data, allowing for a more accurate understanding of the pet's emotions. Some or all of the above processes in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's past voice data into a generating AI and have the generating AI perform the process of analyzing the current voice based on the past data.

[0096] The voice analysis unit can apply different analysis algorithms depending on the type and age of the pet during voice analysis. For example, the voice analysis unit can apply different voice analysis algorithms to dogs and cats to improve analysis accuracy. The voice analysis unit can also apply different analysis algorithms to young and elderly pets to accurately grasp changes in their emotions. The voice analysis unit can also apply analysis algorithms specialized for specific breeds to improve analysis accuracy. In this way, analysis accuracy is improved by applying analysis algorithms appropriate to the type and age of the pet. Some or all of the above processes in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate analysis algorithm.

[0097] The voice analysis unit can estimate the pet's emotions and predict the pet's behavior based on the estimated emotions. For example, if the pet is feeling anxious, the voice analysis unit may predict that it may run away. If the pet is excited, the voice analysis unit may also predict that it will want to play. If the pet is tired, the voice analysis unit may also predict that it will rest. This allows pet owners to anticipate their pet's behavior by predicting it based on its emotions. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's emotional data into a generating AI and have the generating AI predict behavior from the emotional data.

[0098] The voice analysis unit can improve the accuracy of its voice analysis by using the pet's physical condition and health status in conjunction with the voice analysis. For example, if the pet is unwell, the voice analysis unit can analyze changes in its voice to understand its health status. If the pet is in good health, the voice analysis unit can also analyze changes in its voice to understand changes in its emotions. The voice analysis unit can also combine the pet's physical condition and changes in its voice to more accurately analyze changes in its emotions. As a result, by using physical condition and health status in conjunction with the voice analysis unit, the accuracy of the analysis is improved, and the pet's emotions can be understood more accurately. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input the pet's physical condition data into a generating AI and have the generating AI perform voice analysis based on the physical condition data.

[0099] The voice analysis unit can perform voice analysis while considering the pet's living environment (such as noise levels). For example, if the noise level is high, the voice analysis unit may analyze that the pet is experiencing stress. If the noise level is low, the voice analysis unit may analyze that the pet is relaxed. The voice analysis unit can also analyze changes in the pet's emotions by considering changes in the living environment. This allows for a more accurate analysis of changes in the pet's emotions by considering the living environment. Some or all of the above processing in the voice analysis unit may be performed using AI, for example, or without AI. For example, the voice analysis unit can input pet living environment data into a generating AI and have the generating AI perform voice analysis based on the environmental data.

[0100] The tracking unit can estimate the pet's emotions and adjust its tracking method based on the estimated emotions. For example, if the pet is feeling anxious, the tracking unit can shorten the tracking distance to reassure it. If the pet is excited, the tracking unit can also adjust the tracking speed to ensure its safety. If the pet is tired, the tracking unit can reduce the frequency of tracking to allow it to rest. In this way, the safety and comfort of the pet can be ensured by adjusting the tracking method based on its emotions. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the tracking method based on the emotion data.

[0101] The tracking unit can improve tracking accuracy by referring to the pet's past behavioral data during tracking. For example, the tracking unit can learn specific behavioral patterns of the pet based on past behavioral data to improve tracking accuracy. The tracking unit can also compare past behavioral data with current behavior to detect abnormal changes. The tracking unit can also analyze changes in the pet's behavior over time using past behavioral data. As a result, by referring to past behavioral data, tracking accuracy is improved and the pet's behavior can be accurately understood. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the pet's past behavioral data into a generating AI and have the generating AI perform a process to analyze the current behavior based on the past data.

[0102] The tracking unit can apply different tracking algorithms depending on the type and age of the pet during tracking. For example, the tracking unit can apply different tracking algorithms to dogs and cats to improve tracking accuracy. The tracking unit can also apply different tracking algorithms to young and elderly pets to accurately grasp changes in their behavior. The tracking unit can also apply tracking algorithms specialized for specific breeds to improve tracking accuracy. In this way, tracking accuracy is improved by applying tracking algorithms appropriate to the type and age of the pet. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate tracking algorithm.

[0103] The tracking unit can estimate the pet's emotions and detect abnormal behavior based on the estimated emotions. For example, if the pet is feeling anxious, the tracking unit can detect abnormal behavior and notify the owner. If the pet is excited, the tracking unit can also detect dangerous behavior and notify the owner. If the pet is tired, the tracking unit can also detect abnormal resting behavior and notify the owner. This allows for rapid notification to the owner by detecting abnormal behavior based on the pet's emotions. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet emotion data into a generating AI and have the generating AI perform the process of detecting abnormal behavior based on the emotion data.

[0104] The tracking unit can improve tracking accuracy by using the pet's physical condition and health status during tracking. For example, if the pet is unwell, the tracking unit will increase the tracking frequency to monitor its health. If the pet is in good health, the tracking unit can also reduce the tracking frequency to reduce stress. The tracking unit can also improve tracking accuracy by combining changes in the pet's physical condition and behavior. As a result, by using physical condition and health status in combination, tracking accuracy is improved and the pet's behavior can be understood more accurately. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet physical condition data into a generating AI and have the generating AI perform processing to improve tracking accuracy based on the physical condition data.

[0105] The tracking unit can perform tracking while considering the pet's living environment (such as the room layout). For example, the tracking unit can track the pet along a route that is easy for the pet to move along, taking the room layout into consideration. The tracking unit can also analyze changes in the pet's behavior by considering changes in the living environment. The tracking unit can also track the pet while ensuring its safety by avoiding obstacles in the room. This allows for a more accurate analysis of changes in the pet's behavior by considering the living environment. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input pet living environment data into a generating AI and have the generating AI perform tracking based on the environmental data.

[0106] The notification unit can estimate the pet's emotions and customize the notification content based on the estimated emotions. For example, if the pet is feeling anxious, the notification unit will notify the owner with advice to reassure them. If the pet is excited, the notification unit can also notify the owner with ways to calm the pet down. If the pet is tired, the notification unit can also notify the owner with suggestions for resting. In this way, by customizing the notification content based on the pet's emotions, the notification unit can provide the owner with appropriate advice. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input pet emotion data into a generating AI and have the generating AI perform the process of customizing the notification content based on the emotion data.

[0107] The notification unit can optimize the notification method by referring to the owner's past response data when sending a notification. For example, the notification unit will prioritize using notification methods (voice, text, etc.) that the owner has preferred in the past. The notification unit can also suggest the optimal notification timing based on the owner's past response data. The notification unit can also analyze the owner's past response data and suggest the most effective notification content. As a result, by referring to past response data, the notification method is optimized, enabling effective notifications to the owner. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the owner's past response data into a generating AI and have the generating AI perform the process of optimizing the notification method based on the response data.

[0108] The notification unit can apply different notification methods depending on the type and age of the pet when it sends a notification. For example, the notification unit can apply different notification methods for dogs and cats to provide the owner with the most appropriate information. The notification unit can also apply different notification methods for young pets and elderly pets to provide the owner with appropriate advice. The notification unit can also apply notification methods specific to particular breeds to provide the owner with the most appropriate information. In this way, by applying notification methods according to the type and age of the pet, the owner can be provided with the most appropriate information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input data according to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate notification method.

[0109] The notification unit can estimate the pet's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the pet is feeling anxious, the notification unit will immediately notify the owner. If the pet is excited, the notification unit can also notify the owner when the pet has calmed down. If the pet is tired, the notification unit can also notify the owner after the pet has rested. By adjusting the timing of notifications based on the pet's emotions, it is possible to notify the owner at an appropriate time. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the timing of notifications based on the emotion data.

[0110] The notification unit can select a notification method when sending a notification, taking into account the owner's current situation (e.g., at home, out). For example, if the owner is at home, the notification unit may prioritize voice notifications. If the owner is out, the notification unit may also prioritize text notifications. The notification unit can also select the most suitable notification method by considering the owner's current situation. This allows the notification unit to select the most suitable notification method by considering the owner's current situation. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input data on the owner's current situation into a generating AI and have the generating AI perform the process of selecting a notification method based on the situation data.

[0111] The notification unit can enrich its notifications by using pet health status and behavioral data in conjunction with them. For example, if a pet's health is poor, the notification unit will notify the owner with detailed health management advice. The notification unit can also notify the owner with appropriate behavioral advice based on the pet's behavioral data. The notification unit can also provide the owner with optimal information by combining the pet's health status and behavioral data. As a result, by using health status and behavioral data in combination, the notification content can be enriched and the owner can be provided with optimal information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input pet health status data and behavioral data into a generating AI and have the generating AI perform processing to enrich the notification content based on the data.

[0112] The health monitoring unit can estimate the pet's emotions and adjust the health monitoring method based on the estimated emotions. For example, if the pet is feeling anxious, the health monitoring unit can increase the frequency of health monitoring to monitor its condition. If the pet is excited, the health monitoring unit can also adjust the health monitoring method to ensure its safety. If the pet is tired, the health monitoring unit can also decrease the frequency of health monitoring to allow it to rest. By adjusting the health monitoring method based on the pet's emotions, the pet's health condition can be understood more accurately. Some or all of the above processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the monitoring method based on the emotion data.

[0113] The health monitoring unit can improve monitoring accuracy by referring to the pet's past health data during health monitoring. For example, the health monitoring unit can learn specific health patterns of the pet based on past health data to improve monitoring accuracy. The health monitoring unit can also compare past health data with the current health status to detect abnormal changes. The health monitoring unit can also analyze changes in the pet's health status over time using past health data. As a result, by referring to past health data, monitoring accuracy is improved and the pet's health status can be accurately understood. Some or all of the above processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input the pet's past health data into a generating AI and have the generating AI perform a process to analyze the current health status based on the past data.

[0114] The health monitoring unit can apply different monitoring algorithms depending on the type and age of the pet during health monitoring. For example, the health monitoring unit can apply different monitoring algorithms to dogs and cats to improve monitoring accuracy. The health monitoring unit can also apply different monitoring algorithms to young pets and elderly pets to accurately grasp changes in their health status. The health monitoring unit can also apply monitoring algorithms specialized for specific breeds to improve monitoring accuracy. In this way, monitoring accuracy is improved by applying monitoring algorithms appropriate to the type and age of the pet. Some or all of the above processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input data appropriate to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate monitoring algorithm.

[0115] The health monitoring unit can estimate the pet's emotions and detect abnormalities in its health based on the estimated emotions. For example, if the pet is feeling anxious, the health monitoring unit can detect an abnormal health condition and notify the owner. If the pet is excited, the health monitoring unit can also detect a dangerous health condition and notify the owner. If the pet is tired, the health monitoring unit can also detect an abnormal health condition and notify the owner. This allows for rapid notification to the owner by detecting abnormalities in the pet's health based on its emotions. Some or all of the above-described processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input pet emotion data into a generating AI and have the generating AI perform a process to detect abnormalities in the health condition based on the emotion data.

[0116] The health monitoring unit can perform monitoring while taking into account the pet's living environment (room temperature, humidity, etc.). For example, if the room temperature is high, the health monitoring unit will carefully monitor the pet's health. The health monitoring unit can also carefully monitor the pet's health if the humidity is low. The health monitoring unit can also monitor the pet's health while taking into account changes in the living environment. This allows for more accurate monitoring of the pet's health by considering the living environment. Some or all of the above-described processes in the health monitoring unit may be performed using AI, for example, or without AI. For example, the health monitoring unit can input pet living environment data into a generating AI and have the generating AI perform the process of monitoring based on the environmental data.

[0117] The training support unit can estimate the pet's emotions and adjust training methods based on the estimated emotions. For example, if the pet is feeling anxious, the training support unit can suggest gentle training methods. If the pet is excited, the training support unit can also suggest training methods to calm the pet. If the pet is tired, the training support unit can also suggest training methods to allow the pet to rest. This allows for appropriate training of the pet by adjusting training methods based on the pet's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the training support unit may be performed using AI, for example, or not using AI. For example, the training support unit can input pet emotion data into a generative AI and have the generative AI perform the process of adjusting training methods based on the emotion data.

[0118] The training support unit can optimize training methods by referring to the pet's past training data during training. For example, the training support unit can learn specific training patterns of pets based on past training data and optimize training methods. The training support unit can also compare past training data with the current training status and propose the optimal training method. The training support unit can also analyze changes in the pet's training over time using past training data. As a result, by referring to past training data, training methods can be optimized, enabling effective training for pets. Some or all of the above processes in the training support unit may be performed using AI, for example, or without AI. For example, the training support unit can input the pet's past training data into a generating AI and have the generating AI perform the process of optimizing the current training method based on the past data.

[0119] The training support unit can apply different training algorithms depending on the type and age of the pet during training. For example, the training support unit can apply different training algorithms to dogs and cats to optimize the training method. The training support unit can also apply different training algorithms to young and elderly pets to accurately understand changes in training. The training support unit can also apply training algorithms specialized for specific breeds to optimize the training method. In this way, the training method is optimized by applying training algorithms that are appropriate for the type and age of the pet. Some or all of the above processes in the training support unit may be performed using AI, for example, or not using AI. For example, the training support unit can input data according to the type and age of the pet into a generating AI and have the generating AI perform the process of selecting an appropriate training algorithm.

[0120] The training support unit can estimate the pet's emotions and adjust the timing of training based on those emotions. For example, if the pet is feeling anxious, the training support unit can delay training to help the pet feel secure. If the pet is excited, the training support unit can wait until the pet is calm before training. If the pet is tired, the training support unit can wait until the pet has rested before training. By adjusting the timing of training based on the pet's emotions, appropriate training becomes possible. Some or all of the above processes in the training support unit may be performed using AI, for example, or without AI. For example, the training support unit can input pet emotion data into a generating AI and have the generating AI perform the process of adjusting the timing of training based on the emotion data.

[0121] The training support department can select a training method while considering the pet's living environment (such as the room layout) during training support. For example, the training support department can create an environment that is conducive to training by considering the room layout. The training support department can also select the optimal training method by considering changes in the living environment. The training support department can also create an environment where the pet can be safely trained by avoiding obstacles in the room. In this way, the optimal training method for the pet can be selected by considering the living environment. Some or all of the above processes in the training support department may be performed using AI, for example, or without using AI. For example, the training support department can input pet living environment data into a generating AI and have the generating AI perform the process of selecting a training method based on the environmental data.

[0122] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0123] The pet communication system may include a meal management unit to assist with pet diet management. The meal management unit monitors the pet's food intake and nutritional balance, and provides an appropriate meal plan. For example, the meal management unit can calculate the appropriate food intake based on the pet's weight and activity level. It can also record the pet's dietary history and evaluate its nutritional balance. Furthermore, the meal management unit can suggest a meal plan to supplement specific nutrients according to the pet's health condition. This helps maintain the pet's health and enables proper nutritional management. Some or all of the above processes in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input pet dietary data into a generating AI, which can then execute an appropriate meal plan based on that data.

[0124] The pet communication system may include a play support unit to assist pets in playing. The play support unit suggests games tailored to the pet's preferences and personality, thereby reducing the pet's stress. For example, the play support unit can suggest games the pet enjoys based on the pet's past play data. It can also monitor the pet's activity level and suggest appropriate play frequency and duration. Furthermore, the play support unit can estimate the pet's emotions and evaluate whether the pet is enjoying itself. This helps reduce the pet's stress and supports a healthy life. Some or all of the above-described processes in the play support unit may be performed using AI, for example, or without AI. For example, the play support unit can input pet play data into a generating AI and have the generating AI perform the process of suggesting appropriate games based on the play data.

[0125] The pet communication system may include a sleep management unit to assist in managing the pet's sleep. The sleep management unit monitors the pet's sleep patterns and provides an appropriate sleep environment. For example, the sleep management unit can record the pet's sleep duration and quality and detect abnormal patterns. It can also monitor the pet's sleep environment (temperature, humidity, noise level, etc.) and provide an optimal environment. Furthermore, the sleep management unit can estimate the pet's emotions and assess whether stress or anxiety is affecting their sleep. This can support healthy sleep for pets and improve their overall health. Some or all of the above processes in the sleep management unit may be performed using AI, for example, or without AI. For example, the sleep management unit can input the pet's sleep data into a generating AI and have the generating AI perform the process of suggesting an appropriate sleep environment based on the sleep data.

[0126] The pet communication system may include a socialization support unit to improve the pet's social skills. This unit assists the pet in communicating smoothly with other pets and humans. For example, it can analyze interaction patterns with other pets and humans based on the pet's behavioral data. It can also estimate the pet's emotions and provide advice to promote sociable behavior. Furthermore, it can suggest methods to reduce the pet's stress and anxiety. This helps improve the pet's social skills and support a richer life. Some or all of the above-described processes in the socialization support unit may be performed using AI, for example, or without AI. For instance, the socialization support unit can input the pet's behavioral data into a generating AI and have the generating AI perform the process of suggesting appropriate socialization support methods based on the behavioral data.

[0127] The pet communication system may include an exercise management unit to assist in managing the pet's exercise. The exercise management unit monitors the pet's exercise volume and exercise patterns and provides an appropriate exercise plan. For example, the exercise management unit can record the pet's activity level and calculate an appropriate amount of exercise. It can also evaluate the effects of exercise based on the pet's exercise history. Furthermore, the exercise management unit can estimate the pet's emotions and evaluate whether the exercise is reducing the pet's stress or anxiety. This enables the maintenance of the pet's health and appropriate exercise management. Some or all of the above processing in the exercise management unit may be performed using AI, for example, or without AI. For example, the exercise management unit can input the pet's exercise data into a generating AI and have the generating AI execute an appropriate exercise plan based on the exercise data.

[0128] A pet communication system may include a prediction unit that predicts the pet's health status. The prediction unit predicts the pet's future health status based on the pet's past health and behavioral data. For example, the prediction unit can analyze the pet's past body temperature and heart rate data to predict future health risks. It can also predict the likelihood of abnormal behavior occurring based on the pet's behavioral patterns. Furthermore, the prediction unit can estimate the pet's emotions and evaluate the impact of emotional changes on its health status. This allows for the identification of the pet's health risks in advance and the implementation of appropriate countermeasures. Some or all of the above-described processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the pet's health data into a generating AI and have the generating AI perform the process of predicting the future health status from the health data.

[0129] A pet communication system may include a behavior recording unit that records the pet's behavior. The behavior recording unit records the pet's behavior in detail and provides this information to the owner. For example, the behavior recording unit can record the pet's movement routes and activity times and report them to the owner. It can also record the pet's eating and sleeping patterns to aid in health management. Furthermore, the behavior recording unit can estimate the pet's emotions and record changes in those emotions. This allows for a detailed understanding of the pet's behavior, which can be used for health management and training. Some or all of the above-described processes in the behavior recording unit may be performed using AI, for example, or without AI. For example, the behavior recording unit can input pet behavior data into a generating AI and have the generating AI perform detailed recording from the behavior data.

[0130] The pet communication system may include a health check unit to support pet health checks. The health check unit regularly checks the pet's health and detects abnormalities early. For example, the health check unit can regularly measure the pet's body temperature and heart rate and detect abnormalities. It can also analyze the results of blood and urine tests to evaluate the pet's health. Furthermore, the health check unit can estimate the pet's emotions and assess the impact of stress and anxiety on its health. This allows for regular checks of the pet's health and early detection of abnormalities. Some or all of the above-described processes in the health check unit may be performed using AI, for example, or without AI. For example, the health check unit can input pet health data into a generating AI and have the generating AI perform the process of detecting abnormalities from the health data.

[0131] The pet communication system may include a training support unit to assist in pet training. The training support unit monitors the pet's behavior and proposes appropriate training methods. For example, the training support unit can evaluate the effectiveness of training based on the pet's behavioral data. It can also estimate the pet's emotions and propose training methods that correspond to those emotions. Furthermore, the training support unit can analyze the pet's behavioral patterns and provide advice to correct problematic behaviors. This allows for efficient pet training and correction of problematic behaviors. Some or all of the above-described processes in the training support unit may be performed using AI, for example, or without AI. For example, the training support unit can input pet behavioral data into a generating AI and have the generating AI perform the process of proposing appropriate training methods based on the behavioral data.

[0132] The pet communication system may include a health management unit to support pet health management. The health management unit monitors the pet's health status and provides an appropriate health management plan. For example, the health management unit can measure the pet's body temperature and heart rate in real time and detect abnormalities. It can also propose a health management plan based on data on the pet's diet and exercise. Furthermore, the health management unit can estimate the pet's emotions and evaluate the impact of stress and anxiety on its health. This enables comprehensive management of the pet's health status and appropriate health management. Some or all of the above processes in the health management unit may be performed using AI, for example, or not. For example, the health management unit can input pet health data into a generating AI and have the generating AI execute an appropriate health management plan based on the health data.

[0133] The following briefly describes the processing flow for example form 2.

[0134] Step 1: The facial expression analysis unit analyzes the pet's facial expressions. For example, it uses image processing technology and machine learning algorithms to understand the pet's emotions and state in real time. Step 2: The voice analysis unit analyzes the pet's voice. For example, it uses speech recognition technology and frequency analysis to extract the characteristics of the pet's voice and analyzes the sounds the pet makes to understand their meaning. Step 3: The tracking unit tracks the pet's movements. For example, it uses camera tracking technology or sensor data analysis to track the pet's movements in real time and detect abnormal movements or behaviors. Step 4: The notification unit notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. For example, it notifies the owner of the pet's emotions and condition using smartphone notifications or voice notifications.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0137] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] Each of the multiple elements described above, including the facial expression analysis unit, voice analysis unit, tracking unit, notification unit, health monitoring unit, and training support unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the facial expression analysis unit uses the camera 42 of the smart device 14 to capture the pet's facial expressions, which are then analyzed by the specific processing unit 290 of the data processing unit 12. The voice analysis unit uses the microphone 38B of the smart device 14 to record the pet's voice, which is then analyzed by the specific processing unit 290 of the data processing unit 12. The tracking unit uses the camera 42 of the smart device 14 to track the pet's movements, and the specific processing unit 290 of the data processing unit 12 detects abnormal movements. The notification unit uses the output device 40 of the smart device 14 to notify the owner. The health monitoring unit uses the sensors of the smart device 14 to measure the pet's body temperature and heart rate, and the specific processing unit 290 of the data processing unit 12 detects abnormalities. The training support unit monitors the pet's behavior using the camera 42 and microphone 38B of the smart device 14, and evaluates the effectiveness of the training using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device and control unit is not limited to the example described above and can be modified in various ways.

[0139] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0140] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0141] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0142] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0143] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0145] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0146] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the facial expression analysis unit, voice analysis unit, tracking unit, notification unit, health monitoring unit, and training support unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the facial expression analysis unit uses the camera 42 of the smart glasses 214 to capture the pet's facial expressions, which are then analyzed by the specific processing unit 290 of the data processing unit 12. The voice analysis unit uses the microphone 238 of the smart glasses 214 to record the pet's voice, which is then analyzed by the specific processing unit 290 of the data processing unit 12. The tracking unit uses the camera 42 of the smart glasses 214 to track the pet's movements, and the specific processing unit 290 of the data processing unit 12 detects abnormal movements. The notification unit uses the speaker 240 of the smart glasses 214 to notify the owner. The health monitoring unit uses the sensors of the smart glasses 214 to measure the pet's body temperature and heart rate, and the specific processing unit 290 of the data processing unit 12 detects abnormalities. The training support unit monitors the pet's behavior using the camera 42 and microphone 238 of the smart glasses 214, and the specific processing unit 290 of the data processing unit 12 evaluates the effectiveness of the training. The correspondence between each unit and the device and control unit is not limited to the example described above and can be modified in various ways.

[0155] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0156] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0157] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0158] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0159] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0161] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0162] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0163] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0164] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0165] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0167] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0169] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0170] Each of the multiple elements described above, including the facial expression analysis unit, voice analysis unit, tracking unit, notification unit, health monitoring unit, and training support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the facial expression analysis unit uses the camera 42 of the headset terminal 314 to capture the pet's facial expressions, which are then analyzed by the specific processing unit 290 of the data processing unit 12. The voice analysis unit uses the microphone 238 of the headset terminal 314 to record the pet's voice, which is then analyzed by the specific processing unit 290 of the data processing unit 12. The tracking unit uses the camera 42 of the headset terminal 314 to track the pet's movements, and the specific processing unit 290 of the data processing unit 12 detects abnormal movements. The notification unit uses the speaker 240 of the headset terminal 314 to notify the owner. The health monitoring unit uses the sensors of the headset terminal 314 to measure the pet's body temperature and heart rate, and the specific processing unit 290 of the data processing unit 12 detects abnormalities. The training support unit monitors the pet's behavior using the camera 42 and microphone 238 of the headset terminal 314, and evaluates the effectiveness of the training using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0171] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0172] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0173] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0174] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0175] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0177] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0178] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0179] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0180] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0181] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0182] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0183] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0184] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0185] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0186] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0187] Each of the multiple elements described above, including the facial expression analysis unit, voice analysis unit, tracking unit, notification unit, health monitoring unit, and training support unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the facial expression analysis unit uses the camera 42 of the robot 414 to capture the pet's facial expressions, which are then analyzed by the specific processing unit 290 of the data processing unit 12. The voice analysis unit uses the microphone 238 of the robot 414 to record the pet's voice, which is then analyzed by the specific processing unit 290 of the data processing unit 12. The tracking unit uses the camera 42 of the robot 414 to track the pet's movements, and the specific processing unit 290 of the data processing unit 12 detects any abnormal movements. The notification unit uses the speaker 240 of the robot 414 to notify the owner. The health monitoring unit uses the sensors of the robot 414 to measure the pet's body temperature and heart rate, and the specific processing unit 290 of the data processing unit 12 detects any abnormalities. The training support unit monitors the pet's behavior using the camera 42 and microphone 238 of the robot 414, and the specific processing unit 290 of the data processing unit 12 evaluates the effectiveness of the training. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0188] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0189] Figure 9 shows the emotion map 400, in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0190] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0191] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0192] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0193] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0194] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0195] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0196] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0197] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0198] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0199] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0200] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0201] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0202] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0203] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0204] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0205] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0206] (Note 1) A facial expression analysis unit that analyzes the pet's facial expressions, A voice analysis unit that analyzes the sounds of pets, A tracking unit that tracks the pet's movements, The system includes a notification unit that notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. A system characterized by the following features. (Note 2) It is equipped with a health monitoring unit to monitor the health status of pets. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a training support department to assist with training management. The system described in Appendix 1, characterized by the features described herein. (Note 4) The facial expression analysis unit, Analyze your pet's facial expressions in real time to understand their emotions and condition. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned voice analysis unit, Learns pet sounds and analyzes the sounds pets make to understand their meaning. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned tracking unit is, It tracks the pet's movements and detects abnormal movements and behaviors. The system described in Appendix 1, characterized by the features described herein. (Note 7) The facial expression analysis unit, The system estimates the pet's emotions and adjusts the content of notifications sent to the owner based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The facial expression analysis unit, When analyzing facial expressions, we refer to the pet's past facial expression data to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 9) The facial expression analysis unit, When analyzing facial expressions, different analysis algorithms are applied depending on the type and age of the pet. The system described in Appendix 1, characterized by the features described herein. (Note 10) The facial expression analysis unit, It estimates the pet's emotions and predicts the pet's behavior based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The facial expression analysis unit, To improve the accuracy of facial expression analysis, biometric information such as the pet's body temperature and heart rate is used in conjunction with the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 12) The facial expression analysis unit, When analyzing facial expressions, the analysis takes into account the pet's living environment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned voice analysis unit, It estimates the pet's emotions and notifies the owner of the voice analysis results based on the estimated emotions of the pet. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned voice analysis unit, During voice analysis, we improve the accuracy of the analysis by referring to the pet's past voice data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned voice analysis unit, When analyzing voices, different analysis algorithms are applied depending on the type and age of the pet. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned voice analysis unit, It estimates the pet's emotions and predicts the pet's behavior based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned voice analysis unit, When analyzing voices, consider the pet's physical condition and health status to improve analysis accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned voice analysis unit, When analyzing voices, the analysis takes into account the pet's living environment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned tracking unit is, It estimates the pet's emotions and adjusts the tracking method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned tracking unit is, During tracking, the system improves tracking accuracy by referencing the pet's past behavioral data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned tracking unit is, When tracking, different tracking algorithms are applied depending on the type and age of the pet. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned tracking unit is, It estimates the pet's emotions and detects abnormal behavior based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned tracking unit is, During tracking, the tracking accuracy is improved by using the pet's physical condition and health status in conjunction with the tracking process. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned tracking unit is, When tracking, the tracking process takes into account the pet's living environment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned notification unit, It estimates the pet's emotions and customizes notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned notification unit, When sending notifications, the system optimizes the notification method by referencing the owner's past response data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, When sending notifications, different notification methods will be applied depending on the type and age of the pet. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, It estimates the pet's emotions and adjusts the timing of notifications based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned notification unit, When notifying, the notification method will be selected considering the owner's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, When sending notifications, enrich the content by using pet health status and behavioral data in conjunction with the notifications. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned health monitoring unit, Estimate the pet's emotions and adjust health monitoring methods based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned health monitoring unit, During health monitoring, referencing the pet's past health data improves monitoring accuracy. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned health monitoring unit, During health monitoring, different monitoring algorithms are applied depending on the type and age of the pet. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned health monitoring unit, It estimates the emotions of pets and detects abnormal health conditions based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned health monitoring unit, When conducting health monitoring, the pet's living environment should be taken into consideration. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned training support department, It estimates the pet's emotions and adjusts training methods based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned training support department, When providing training support, we optimize the support method by referring to the pet's past training data. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned training support department, When providing training support, different training algorithms are applied depending on the type and age of the pet. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned training support department, It estimates the pet's emotions and adjusts the timing of training based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned training support department, When providing training support, select training methods while considering the pet's living environment. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0207] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A facial expression analysis unit that analyzes the pet's facial expressions, A voice analysis unit that analyzes the sounds of pets, A tracking unit that tracks the pet's movements, The system includes a notification unit that notifies the owner of the analysis results obtained by the facial expression analysis unit and the voice analysis unit. A system characterized by the following features.

2. It is equipped with a health monitoring unit to monitor the health status of pets. The system according to feature 1.

3. It has a training support department to assist with training management. The system according to feature 1.

4. The facial expression analysis unit, Analyze your pet's facial expressions in real time to understand their emotions and condition. The system according to feature 1.

5. The aforementioned voice analysis unit, Learns pet sounds and analyzes the sounds pets make to understand their meaning. The system according to feature 1.

6. The aforementioned tracking unit is, It tracks the pet's movements and detects abnormal movements and behaviors. The system according to feature 1.

7. The facial expression analysis unit, The system estimates the pet's emotions and adjusts the content of notifications sent to the owner based on the estimated emotions. The system according to feature 1.

8. The facial expression analysis unit, When analyzing facial expressions, we refer to the pet's past facial expression data to improve the accuracy of the analysis. The system according to feature 1.

Images