system

Abstract

The system according to the embodiment aims to verbalize the behavior and physical condition of a pet and provide the verbalized information to the user. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a verbalization unit, a provision unit, and a detection unit. The collection unit includes a voice sensor and a motion sensor. The analysis unit analyzes data collected by the collection unit. The verbalization unit verbalizes the data analyzed by the analysis unit. The provision unit provides the language generated by the verbalization unit to a user. The detection unit detects abnormalities in physical condition based on the data collected by the collection unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have presented challenges such as difficulty in accurately understanding pets' behavior and physical condition, and limited communication with pets.

[0005] The system according to the embodiment aims to verbalize the behavior and physical condition of a pet and provide the verbalized information to the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a verbalization unit, a provision unit, and a detection unit. The collection unit includes a voice sensor and a motion sensor. The analysis unit analyzes the data collected by the collection unit. The verbalization unit verbalizes the data analyzed by the analysis unit. The provision unit provides the language generated by the verbalization unit to the user. The detection unit detects abnormalities in physical condition based on the data collected by the collection unit. [Effects of the Invention]

[0007] The system according to the embodiment can verbalize the behavior and physical condition of a pet and provide it to the user. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The cat language system according to an embodiment of the present invention is a system that uses a generative AI to translate cat language into language. This system allows the cat to "talk" to the user and engage in conversation. It can also be used as a tool for managing the cat's health. By applying this technology, a foreign language version can be used for English language learning, and it can be linked with a smartphone app to allow communication even when the user is away from home. Furthermore, it is possible to develop versions for other animals and create a generative AI zoo. Specifically, it consists of the following steps. First, the cat's meows and behavior are collected by a voice sensor and a motion sensor, and the generative AI analyzes this data and translates it into language. Next, the generated language is provided to the user, enabling conversation with the cat. For example, if the cat says "I'm hungry," the user can respond with "I'll give you some food." This system can also be used for managing the cat's health. For example, it can detect abnormalities in the cat's health from its meows and behavior and notify the user. This allows for early detection of health problems and appropriate action to be taken. Furthermore, by applying this technology, a foreign language version can be developed and used for English language learning. For example, a cat can talk to users in English, allowing them to practice listening and speaking. By linking it to a smartphone app, users can receive messages from their cat even when they're out. Finally, it's possible to develop other animal versions and create a generative AI zoo. For example, it can verbalize the words of animals like dogs and birds, allowing users to enjoy conversations with those animals. This will enrich communication with animals and provide new ways to enjoy the zoo. This will allow the cat's verbalization system to verbalize cats' words, allowing them to manage their health and converse.

[0029] The cat language system according to this embodiment comprises a collection unit, an analysis unit, a language processing unit, a provision unit, and a detection unit. The collection unit includes an audio sensor and a motion sensor to collect the cat's meows and behavior. For example, the collection unit collects the cat's meows with a high-sensitivity microphone and detects the cat's movements with the motion sensor. The collection unit can also record the cat's movements in detail using, for example, an accelerometer or gyroscope. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit preprocesses the audio data to remove noise. The analysis unit can also analyze the motion data and extract the cat's behavior patterns. For example, the analysis unit uses a machine learning algorithm to analyze the data and extract features of the cat's behavior and meows. The language processing unit translates the data analyzed by the analysis unit into language. For example, the language processing unit uses natural language processing technology to convert the cat's meows and behavior into text. The language generation unit can generate cat language using, for example, a generative AI (such as GPT-4® or Gemini). The provision unit provides the language generated by the language generation unit to the user. For example, the provision unit displays cat language through a user interface. The provision unit can also notify the user of cat language using a notification function. The provision unit can also provide cat language to the user through, for example, a smartphone app. The detection unit detects abnormalities in the cat's physical condition based on the data collected by the collection unit. For example, the detection unit detects abnormalities in the cat's meowing or behavior and notifies the user. The detection unit can also detect abnormalities in the cat's physical condition early using, for example, a generative AI. As a result, the cat language generation system according to this embodiment can translate cat language, enabling health management and conversation.

[0030] The providing unit can provide the language generated by the generation AI to the user. The providing unit provides the language generated by the generation AI (e.g., GPT-4, Gemini, etc.) to the user. For example, the providing unit displays the text generated by the generation AI through a user interface. The providing unit can also provide the language generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the text generated by the generation AI into a speech synthesis engine and outputs it as audio. This allows the user to hear the cat's words aloud. Furthermore, the providing unit can notify the user of the language generated by the generation AI using a notification function. For example, the providing unit notifies the user of the cat's words through a smartphone app. This allows the user to receive the cat's words even when they are out and about. Some or all of the above-described processing in the providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when displaying the text generated by the generation AI on a user interface, the providing unit can display the text without using the generation AI. This improves the accuracy of providing the cat's words to the user by using the generation AI.

[0031] The detection unit can detect abnormalities in the cat's physical condition using the generation AI. The detection unit detects abnormalities in the cat's physical condition using, for example, a generation AI (e.g., GPT-4 or Gemini). For example, the detection unit detects abnormalities in the cat's meows or behavior based on data analyzed by the generation AI. For example, the detection unit can detect abnormal meows by having the generation AI analyze the cat's meow patterns. The detection unit can also detect abnormal movements by having the generation AI analyze the cat's movement data. For example, the detection unit can analyze the cat's movement data and detect abnormal movement patterns. In this way, by using the generation AI, abnormalities in the cat's physical condition can be detected early. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when detecting abnormalities based on data analyzed by the generation AI, the detection unit can also detect abnormalities without using the generation AI. In this way, by using the generation AI, abnormalities in the cat's physical condition can be detected early.

[0032] The analysis unit can analyze the voice data and movement data using a generation AI. The analysis unit analyzes the voice data and movement data using, for example, a generation AI (e.g., GPT-4 or Gemini). For example, the analysis unit preprocesses the voice data and removes noise. The analysis unit can also extract the cat's behavioral patterns by having the generation AI analyze the movement data. For example, the analysis unit analyzes the voice data and extracts characteristics of a cat's meows. The analysis unit can also extract the cat's movement patterns by having the generation AI analyze the movement data. For example, the analysis unit analyzes the cat's movement data and detects specific behavioral patterns. As a result, the use of the generation AI improves the accuracy of the analysis of the voice data and movement data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the voice data and movement data based on the data analyzed by the generation AI without using the generation AI. This will improve the accuracy of analyzing voice data and movement data by using generative AI.

[0033] The verbalization unit can verbalize the data analyzed by the generation AI. The verbalization unit verbalizes the analyzed data, for example, using a generation AI (e.g., GPT-4 or Gemini). For example, the verbalization unit converts a cat's meows and actions into text based on the data analyzed by the generation AI. For example, the verbalization unit analyzes a cat's meow and generates the content as text. The verbalization unit can also analyze cat movement data and generate the content as text. For example, the verbalization unit analyzes cat movement data and generates the meaning of the movement as text. In this way, the use of the generation AI improves the accuracy of verbalizing the data. Some or all of the above-mentioned processing in the verbalization unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the verbalization unit can generate text based on the data analyzed by the generation AI without using the generation AI. In this way, the use of the generation AI improves the accuracy of verbalizing the data.

[0034] The providing unit generates a foreign language version using a generation AI and can use it for English language learning. The providing unit generates a foreign language version using, for example, a generation AI (e.g., GPT-4 or Gemini) and uses it for English language learning. For example, the providing unit displays the English text generated by the generation AI through a user interface. The providing unit can also provide the English text generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the English text generated by the generation AI into a speech synthesis engine and outputs it as audio. This allows the user to practice English listening and conversation. Furthermore, the providing unit can notify the user of the English text generated by the generation AI using a notification function. For example, the providing unit notifies the user of the English text through a smartphone app. This allows the user to receive the English text even when they are out and about. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the service provider can display the English text generated by the generation AI on the user interface without using the generation AI. This allows the system to be used for English language learning by utilizing the generation AI.

[0035] The providing unit can generate other animal versions using the generation AI to create a zoo. The providing unit can generate other animal versions using, for example, a generation AI (e.g., GPT-4 or Gemini) to create a zoo. For example, the providing unit displays animal words, such as dog and bird, generated by the generation AI through a user interface. The providing unit can also provide the animal words generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the animal words generated by the generation AI into a speech synthesis engine and outputs them as audio. This allows users to enjoy conversations with animals, such as dogs and birds. The providing unit can also notify users of the animal words generated by the generation AI using a notification function. For example, the providing unit notifies users of the animal words through a smartphone app. This allows users to receive the animal words even when they are out and about. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when displaying the animal words generated by the generation AI on a user interface, the providing unit can display text without using the generation AI. This makes it possible to create versions of other animals using generative AI and build a zoo.

[0036] The data collection unit can estimate the cat's emotions and adjust the timing of audio and motion data collection based on the estimated emotions. For example, when the cat is relaxed, the data collection unit can activate the audio and motion sensors simultaneously to collect natural behavior. When the cat is excited, the data collection unit can prioritize activating the motion sensor to collect details of intense movements. Furthermore, when the cat is stressed, the data collection unit can prioritize activating the audio sensor to collect details of changes in meowing. By adjusting the collection timing based on the cat's emotions, more natural data can be collected. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can adjust the collection timing based on cat emotion data estimated by generative AI. By adjusting the collection timing based on the cat's emotions, more natural data can be collected.

[0037] The data collection unit can analyze the cat's past behavioral patterns and select the optimal data collection method. For example, if the cat has a tendency to be active during certain time periods in the past, the data collection unit can enhance the motion sensor and collect data during those times. Furthermore, if the cat frequently meows in certain locations in the past, the data collection unit can enhance the sound sensor and collect data at those locations. Additionally, if the cat has repeatedly performed certain behaviors in the past, the data collection unit can activate sensors at the time those behaviors occur. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can select the optimal data collection method based on the cat's past behavioral data analyzed by the generative AI. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns.

[0038] The collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, the collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, if the cat is healthy, the collection unit applies a normal collection method. If the cat is in poor health, the collection unit can increase the sensitivity of the movement sensor to collect abnormal movements in detail. Furthermore, if the cat is in a new environment, the collection unit can increase the sensitivity of the sound sensor to collect environmental sounds in detail. This allows for more accurate data collection by filtering based on the cat's health condition and environment. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can filter based on the cat's health condition and environmental data estimated by the generation AI. This allows for more accurate data collection by filtering based on the cat's health condition and environment.

[0039] The collection unit can estimate the cat's emotions and determine the priority of data to be collected based on the estimated cat emotions. The collection unit, for example, estimates the cat's emotions and determines the priority of data to be collected based on the estimated cat emotions. For example, when the cat is relaxed, the collection unit prioritizes collecting voice data over movement data. Also, when the cat is excited, the collection unit can prioritize collecting movement data over voice data. Furthermore, when the cat is stressed, the collection unit can collect both voice data and movement data equally. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can determine the priority of data to be collected based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially.

[0040] When collecting voice and motion, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the cat. For example, when collecting voice and motion, the collection unit prioritizes collecting highly relevant data by taking into account the geographical location information of the cat. For example, when the cat is inside the house, the collection unit can prioritize collecting motion sensors. Also, when the cat is outside, the collection unit can prioritize collecting voice sensors. Furthermore, when the cat is in a specific location, the collection unit can prioritize collecting behavioral patterns in that location. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI, for example. For example, the collection unit can prioritize collecting highly relevant data based on the geographical location information of the cat estimated by the generation AI. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information.

[0041] The collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, the collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, if the cat is engaging in a behavior that is popular on social media, the collection unit can prioritize collecting that behavior. Also, if the cat is in a location that is trending on social media, the collection unit can prioritize collecting behavior in that location. Furthermore, if the cat is making a specific meow on social media, the collection unit can prioritize collecting that meow. In this way, related data can be collected by analyzing social media activity. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the collection unit can collect related data based on the cat's social media activity data analyzed by the generation AI. In this way, related data can be collected by analyzing social media activity.

[0042] The analysis unit can estimate the cat's emotions and adjust the analysis algorithm based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the analysis algorithm based on the estimated cat emotions. For example, the analysis unit applies a normal analysis algorithm when the cat is relaxed. Furthermore, the analysis unit can apply an algorithm that enhances analysis of movement data when the cat is excited. Furthermore, the analysis unit can apply an algorithm that enhances analysis of audio data when the cat is stressed. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the analysis algorithm based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved.

[0043] The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis. The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis, for example. For example, if a cat's meows and movement match, the analysis unit prioritizes the analysis of that data. The analysis unit can also analyze a cat's meows and movement that do not match as abnormal behavior. Furthermore, the analysis unit can analyze the patterns of a cat's meows and movement and take the correlation into account during analysis. This improves the accuracy of the analysis by taking the correlation between voice and movement into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can analyze the correlation based on the voice data and movement data analyzed by the generation AI. This improves the accuracy of the analysis by taking the correlation between voice and movement into account.

[0044] The analysis unit can perform the analysis taking into account the cat's attribute information. For example, the analysis unit performs the analysis taking into account the cat's attribute information. For example, the analysis unit selects an appropriate analysis algorithm based on the cat's age. The analysis unit can also perform the analysis taking into account specific behavioral patterns based on the cat's breed. Furthermore, the analysis unit can perform analysis to detect abnormal behavior based on the cat's health condition. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can perform the analysis based on the cat's attribute information analyzed by the generation AI. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved.

[0045] The analysis unit can estimate the cat's emotions and adjust the display method of the analysis results based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the display method of the analysis results based on the estimated cat emotions. For example, the analysis unit displays detailed analysis results when the cat is relaxed. The analysis unit can also display concise analysis results when the cat is excited. Furthermore, the analysis unit can highlight abnormal behavior when the cat is stressed. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the display method of the analysis results based on the cat's emotion data estimated by the generation AI. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand.

[0046] The analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, the analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, if a cat frequently meows in a specific location, the analysis unit can prioritize the analysis of data from that location. Also, if a cat performs a specific movement in a specific location, the analysis unit can prioritize the analysis of data from that movement. Furthermore, the analysis unit can analyze the patterns of sounds and movements of the cat when it moves and analyze them while taking into account the geographical distribution. In this way, taking the geographical distribution into account improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can perform the analysis while taking into account the geographical distribution based on the sound data and movement data analyzed by the generation AI. In this way, taking the geographical distribution into account improves the accuracy of the analysis.

[0047] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis, for example. For example, the analysis unit can refer to the latest research on cat behavior and adjust the analysis algorithm. The analysis unit can also improve the accuracy of analyzing audio data by referring to literature on cat meows. Furthermore, the analysis unit can improve the accuracy of detecting abnormal behavior by referring to literature on cat health conditions. In this way, by referring to related literature, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI, for example. For example, the analysis unit can adjust the analysis algorithm based on the related literature referred to by the generation AI. In this way, by referring to related literature, the analysis accuracy is improved.

[0048] The language processing unit can estimate the cat's emotions and adjust the language processing method based on the estimated emotions. For example, if the cat is relaxed, the language processing unit will use calm language. If the cat is excited, the language processing unit can use lively language. Furthermore, if the cat is stressed, the language processing unit can use cautious language. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not. For example, the language processing unit can adjust the language processing method based on the cat's emotion data estimated by the generative AI. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible.

[0049] The language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can perform detailed language processing for important data. The language processing unit can also perform concise language processing for general data. Furthermore, the language processing unit can perform language processing that includes detailed explanations for anomalous data. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data evaluated by the generative AI. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail.

[0050] The linguistic unit can apply different linguistic algorithms depending on the data category during linguisticization. For example, the linguistic unit applies different linguistic algorithms depending on the data category during linguisticization. For example, in the case of health data, the linguistic unit performs linguisticization including medical terms. In addition, in the case of behavioral data, the linguistic unit can perform linguisticization using general terms. Furthermore, in the case of emotional data, the linguistic unit can perform linguisticization including emotional expressions. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression. Some or all of the above-mentioned processing in the linguistic unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the linguistic unit can apply different linguistic algorithms based on the data category classified by the generation AI. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression.

[0051] The verbalization unit can estimate the cat's emotions and adjust the length of the verbalization based on the estimated cat emotions. The verbalization unit, for example, estimates the cat's emotions and adjusts the length of the verbalization based on the estimated cat emotions. For example, the verbalization unit performs longer verbalizations when the cat is relaxed. Furthermore, the verbalization unit can also perform shorter verbalizations when the cat is excited. Furthermore, the verbalization unit can also perform verbalizations of an appropriate length when the cat is stressed. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length. Some or all of the above-described processing in the verbalization unit may be performed using, or without, a generation AI, for example. For example, the verbalization unit can adjust the length of the verbalizations based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length.

[0052] The language processing unit can determine the priority of language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing of the most recent data. The language processing unit can also prioritize the language processing of past data. Furthermore, the language processing unit can prioritize the language processing of data where the submission timing is important. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the language processing unit can determine the priority of language processing based on the data submission timing evaluated by the generative AI. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially.

[0053] The language processing unit can adjust the order of language processing based on the relevance of the data during the language processing process. For example, the language processing unit can prioritize the language processing of highly relevant data. It can also postpone the language processing of less relevant data. Furthermore, the language processing unit can dynamically adjust the order of language processing based on the relevance of the data. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the order of language processing based on the relevance of the data evaluated by the generative AI. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data.

[0054] The providing unit can estimate the cat's emotions and adjust the manner of linguistic expression to be provided based on the estimated cat's emotions. The providing unit, for example, estimates the cat's emotions and adjusts the manner of linguistic expression to be provided based on the estimated cat's emotions. For example, if the cat is relaxed, the providing unit can provide language using calm expressions. Furthermore, if the cat is excited, the providing unit can provide language using lively expressions. Furthermore, if the cat is stressed, the providing unit can provide language using cautious expressions. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible. Some or all of the above-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can adjust the manner of linguistic expression to be provided based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible.

[0055] The providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can prioritize and provide expressions that the user has previously preferred. The providing unit can also provide expressions that the user has previously avoided. Furthermore, the providing unit can analyze the user's past responses and select the optimal expression method. In this way, the optimal providing method can be selected by analyzing the user's past responses. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal providing method based on the user's past response data analyzed by the generation AI. In this way, the optimal providing method can be selected by analyzing the user's past responses.

[0056] The service provider can customize the content offered based on the user's current situation at the time of delivery. For example, the service provider can customize the content offered based on the user's current situation at the time of delivery. For example, if the user is relaxed, the service provider can offer calm content. Also, if the user is busy, the service provider can offer concise content. Furthermore, if the user is excited, the service provider can offer lively content. By customizing the content offered based on the user's current situation, more appropriate information can be provided. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not. For example, the service provider can customize the content offered based on the user's current situation data evaluated by the generative AI. By customizing the content offered based on the user's current situation, more appropriate information can be provided.

[0057] The service provider can estimate the cat's emotions and determine the priority of the languages ​​to be provided based on the estimated emotions. For example, if the cat is relaxed, the service provider will prioritize providing calm languages. If the cat is excited, the service provider may also prioritize providing lively languages. Furthermore, if the cat is stressed, the service provider may also prioritize providing cautious languages. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions. Some or all of the above processing in the service provider may be performed using, for example, generative AI, or not using generative AI. For example, the service provider can determine the priority of languages ​​to be provided based on cat emotion data estimated by generative AI. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions.

[0058] The providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit selects the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit can provide detailed content when the user is at home. Furthermore, the providing unit can provide concise content when the user is out. Furthermore, the providing unit can provide content related to a specific location when the user is in that location. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal delivery method based on the user's geographical location information evaluated by the generation AI. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information.

[0059] The providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can prioritize and provide content in which the user has shown interest on social media. The providing unit can also provide content that the user has avoided on social media. Furthermore, the providing unit can analyze the user's social media activity and provide optimal content. In this way, optimal content to be provided can be selected by analyzing the user's social media activity. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the providing unit can adjust the content to be provided based on the user's social media activity data analyzed by the generation AI. In this way, optimal content to be provided can be selected by analyzing the user's social media activity.

[0060] The detection unit can estimate the cat's emotions and adjust the method for detecting abnormal physical conditions based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and adjusts the method for detecting abnormal physical conditions based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit applies a normal abnormality detection method. Furthermore, when the cat is excited, the detection unit can also prioritize detecting abnormalities in the movement data. Furthermore, when the cat is stressed, the detection unit can also prioritize detecting abnormalities in the voice data. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI, for example. For example, the detection unit can adjust the method for detecting abnormal physical conditions based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible.

[0061] The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection. The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection, for example. For example, the detection unit detects abnormal behavior based on the cat's past health data. The detection unit can also detect abnormal meows by referring to the cat's past health data. Furthermore, the detection unit can analyze the cat's past health data and adjust the anomaly detection algorithm. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data. Some or all of the above-described processing in the detection unit can be performed using, or without, a generation AI, for example. For example, the detection unit can improve the accuracy of anomaly detection based on the cat's past health data analyzed by the generation AI. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data.

[0062] The detection unit can customize the anomaly detection method based on the cat's current living environment during detection. For example, the detection unit customizes the anomaly detection method based on the cat's current living environment during detection. For example, when the cat is indoors, the detection unit applies a normal anomaly detection method. Furthermore, when the cat is outside, the detection unit can prioritize detecting anomalies in motion data. Furthermore, when the cat is in a new environment, the detection unit can prioritize detecting anomalies in audio data. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI. For example, the detection unit can customize the anomaly detection method based on the cat's current living environment data evaluated by the generation AI. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment.

[0063] The detection unit can estimate the cat's emotions and determine the priority of anomaly detection based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and determines the priority of anomaly detection based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit performs normal anomaly detection. Furthermore, when the cat is excited, the detection unit can prioritize detecting anomalies in the movement data. Furthermore, when the cat is stressed, the detection unit can prioritize detecting anomalies in the voice data. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can determine the priority of anomaly detection based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies.

[0064] The detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, the detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, if the cat is inside the house, the detection unit can apply the normal anomaly detection method. Also, if the cat is outside, the detection unit can prioritize detecting anomalies in the motion data. Furthermore, if the cat is in a specific location, the detection unit can prioritize detecting anomalies related to that location. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can select the optimal anomaly detection method based on the cat's geographical location information evaluated by the generative AI. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information.

[0065] The detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can adjust the anomaly detection algorithm by referring to the latest research on cat health. The detection unit can also improve the accuracy of anomaly detection of motion data by referring to literature on cat behavior. Furthermore, the detection unit can improve the accuracy of anomaly detection of sound data by referring to literature on cat meows. In this way, the accuracy of anomaly detection is improved by referring to relevant literature. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can adjust the anomaly detection algorithm based on the relevant literature referred to by the generative AI. In this way, the accuracy of anomaly detection is improved by referring to relevant literature.

[0066] The providing unit generates a foreign language version using a generation AI and can use it for English language learning. The providing unit generates a foreign language version using, for example, a generation AI (e.g., GPT-4 or Gemini) and uses it for English language learning. For example, the providing unit displays the English text generated by the generation AI through a user interface. The providing unit can also provide the English text generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the English text generated by the generation AI into a speech synthesis engine and outputs it as audio. This allows the user to practice English listening and conversation. Furthermore, the providing unit can notify the user of the English text generated by the generation AI using a notification function. For example, the providing unit notifies the user of the English text through a smartphone app. This allows the user to receive the English text even when they are out and about. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the service provider can display the English text generated by the generation AI on the user interface without using the generation AI. This allows the system to be used for English language learning by utilizing the generation AI.

[0067] The providing unit can generate other animal versions using the generation AI to create a zoo. The providing unit can generate other animal versions using, for example, a generation AI (e.g., GPT-4 or Gemini) to create a zoo. For example, the providing unit displays animal words, such as dog and bird, generated by the generation AI through a user interface. The providing unit can also provide the animal words generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the animal words generated by the generation AI into a speech synthesis engine and outputs them as audio. This allows users to enjoy conversations with animals, such as dogs and birds. The providing unit can also notify users of the animal words generated by the generation AI using a notification function. For example, the providing unit notifies users of the animal words through a smartphone app. This allows users to receive the animal words even when they are out and about. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when displaying the animal words generated by the generation AI on a user interface, the providing unit can display text without using the generation AI. This makes it possible to create versions of other animals using generative AI and build a zoo.

[0068] The data collection unit can estimate the cat's emotions and adjust the timing of audio and motion data collection based on the estimated emotions. For example, when the cat is relaxed, the data collection unit can activate the audio and motion sensors simultaneously to collect natural behavior. When the cat is excited, the data collection unit can prioritize activating the motion sensor to collect details of intense movements. Furthermore, when the cat is stressed, the data collection unit can prioritize activating the audio sensor to collect details of changes in meowing. By adjusting the collection timing based on the cat's emotions, more natural data can be collected. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can adjust the collection timing based on cat emotion data estimated by generative AI. By adjusting the collection timing based on the cat's emotions, more natural data can be collected.

[0069] The data collection unit can analyze the cat's past behavioral patterns and select the optimal data collection method. For example, if the cat has a tendency to be active during certain time periods in the past, the data collection unit can enhance the motion sensor and collect data during those times. Furthermore, if the cat frequently meows in certain locations in the past, the data collection unit can enhance the sound sensor and collect data at those locations. Additionally, if the cat has repeatedly performed certain behaviors in the past, the data collection unit can activate sensors at the time those behaviors occur. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can select the optimal data collection method based on the cat's past behavioral data analyzed by the generative AI. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns.

[0070] The collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, the collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, if the cat is healthy, the collection unit applies a normal collection method. If the cat is in poor health, the collection unit can increase the sensitivity of the movement sensor to collect abnormal movements in detail. Furthermore, if the cat is in a new environment, the collection unit can increase the sensitivity of the sound sensor to collect environmental sounds in detail. This allows for more accurate data collection by filtering based on the cat's health condition and environment. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can filter based on the cat's health condition and environmental data estimated by the generation AI. This allows for more accurate data collection by filtering based on the cat's health condition and environment.

[0071] The collection unit can estimate the cat's emotions and determine the priority of data to be collected based on the estimated cat emotions. The collection unit, for example, estimates the cat's emotions and determines the priority of data to be collected based on the estimated cat emotions. For example, when the cat is relaxed, the collection unit prioritizes collecting voice data over movement data. Also, when the cat is excited, the collection unit can prioritize collecting movement data over voice data. Furthermore, when the cat is stressed, the collection unit can collect both voice data and movement data equally. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can determine the priority of data to be collected based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially.

[0072] When collecting voice and motion, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the cat. For example, when collecting voice and motion, the collection unit prioritizes collecting highly relevant data by taking into account the geographical location information of the cat. For example, when the cat is inside the house, the collection unit can prioritize collecting motion sensors. Also, when the cat is outside, the collection unit can prioritize collecting voice sensors. Furthermore, when the cat is in a specific location, the collection unit can prioritize collecting behavioral patterns in that location. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI, for example. For example, the collection unit can prioritize collecting highly relevant data based on the geographical location information of the cat estimated by the generation AI. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information.

[0073] The collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, the collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, if the cat is engaging in a behavior that is popular on social media, the collection unit can prioritize collecting that behavior. Also, if the cat is in a location that is trending on social media, the collection unit can prioritize collecting behavior in that location. Furthermore, if the cat is making a specific meow on social media, the collection unit can prioritize collecting that meow. In this way, related data can be collected by analyzing social media activity. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the collection unit can collect related data based on the cat's social media activity data analyzed by the generation AI. In this way, related data can be collected by analyzing social media activity.

[0074] The analysis unit can estimate the cat's emotions and adjust the analysis algorithm based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the analysis algorithm based on the estimated cat emotions. For example, the analysis unit applies a normal analysis algorithm when the cat is relaxed. Furthermore, the analysis unit can apply an algorithm that enhances analysis of movement data when the cat is excited. Furthermore, the analysis unit can apply an algorithm that enhances analysis of audio data when the cat is stressed. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the analysis algorithm based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved.

[0075] The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis. The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis, for example. For example, if a cat's meows and movement match, the analysis unit prioritizes the analysis of that data. The analysis unit can also analyze a cat's meows and movement that do not match as abnormal behavior. Furthermore, the analysis unit can analyze the patterns of a cat's meows and movement and take the correlation into account during analysis. This improves the accuracy of the analysis by taking the correlation between voice and movement into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can analyze the correlation based on the voice data and movement data analyzed by the generation AI. This improves the accuracy of the analysis by taking the correlation between voice and movement into account.

[0076] The analysis unit can perform the analysis taking into account the cat's attribute information. For example, the analysis unit performs the analysis taking into account the cat's attribute information. For example, the analysis unit selects an appropriate analysis algorithm based on the cat's age. The analysis unit can also perform the analysis taking into account specific behavioral patterns based on the cat's breed. Furthermore, the analysis unit can perform analysis to detect abnormal behavior based on the cat's health condition. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can perform the analysis based on the cat's attribute information analyzed by the generation AI. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved.

[0077] The analysis unit can estimate the cat's emotions and adjust the display method of the analysis results based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the display method of the analysis results based on the estimated cat emotions. For example, the analysis unit displays detailed analysis results when the cat is relaxed. The analysis unit can also display concise analysis results when the cat is excited. Furthermore, the analysis unit can highlight abnormal behavior when the cat is stressed. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the display method of the analysis results based on the cat's emotion data estimated by the generation AI. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand.

[0078] The analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, the analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, if a cat frequently meows in a specific location, the analysis unit can prioritize the analysis of data from that location. Also, if a cat performs a specific movement in a specific location, the analysis unit can prioritize the analysis of data from that movement. Furthermore, the analysis unit can analyze the patterns of sounds and movements of the cat when it moves and analyze them while taking into account the geographical distribution. In this way, taking the geographical distribution into account improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can perform the analysis while taking into account the geographical distribution based on the sound data and movement data analyzed by the generation AI. In this way, taking the geographical distribution into account improves the accuracy of the analysis.

[0079] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis, for example. For example, the analysis unit can refer to the latest research on cat behavior and adjust the analysis algorithm. The analysis unit can also improve the accuracy of analyzing audio data by referring to literature on cat meows. Furthermore, the analysis unit can improve the accuracy of detecting abnormal behavior by referring to literature on cat health conditions. In this way, by referring to related literature, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI, for example. For example, the analysis unit can adjust the analysis algorithm based on the related literature referred to by the generation AI. In this way, by referring to related literature, the analysis accuracy is improved.

[0080] The language processing unit can estimate the cat's emotions and adjust the language processing method based on the estimated emotions. For example, if the cat is relaxed, the language processing unit will use calm language. If the cat is excited, the language processing unit can use lively language. Furthermore, if the cat is stressed, the language processing unit can use cautious language. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not. For example, the language processing unit can adjust the language processing method based on the cat's emotion data estimated by the generative AI. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible.

[0081] The language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can perform detailed language processing for important data. The language processing unit can also perform concise language processing for general data. Furthermore, the language processing unit can perform language processing that includes detailed explanations for anomalous data. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data evaluated by the generative AI. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail.

[0082] The linguistic unit can apply different linguistic algorithms depending on the data category during linguisticization. For example, the linguistic unit applies different linguistic algorithms depending on the data category during linguisticization. For example, in the case of health data, the linguistic unit performs linguisticization including medical terms. In addition, in the case of behavioral data, the linguistic unit can perform linguisticization using general terms. Furthermore, in the case of emotional data, the linguistic unit can perform linguisticization including emotional expressions. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression. Some or all of the above-mentioned processing in the linguistic unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the linguistic unit can apply different linguistic algorithms based on the data category classified by the generation AI. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression.

[0083] The verbalization unit can estimate the cat's emotions and adjust the length of the verbalization based on the estimated cat emotions. The verbalization unit, for example, estimates the cat's emotions and adjusts the length of the verbalization based on the estimated cat emotions. For example, the verbalization unit performs longer verbalizations when the cat is relaxed. Furthermore, the verbalization unit can also perform shorter verbalizations when the cat is excited. Furthermore, the verbalization unit can also perform verbalizations of an appropriate length when the cat is stressed. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length. Some or all of the above-described processing in the verbalization unit may be performed using, or without, a generation AI, for example. For example, the verbalization unit can adjust the length of the verbalizations based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length.

[0084] The language processing unit can determine the priority of language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing of the most recent data. The language processing unit can also prioritize the language processing of past data. Furthermore, the language processing unit can prioritize the language processing of data where the submission timing is important. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the language processing unit can determine the priority of language processing based on the data submission timing evaluated by the generative AI. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially.

[0085] The language processing unit can adjust the order of language processing based on the relevance of the data during the language processing process. For example, the language processing unit can prioritize the language processing of highly relevant data. It can also postpone the language processing of less relevant data. Furthermore, the language processing unit can dynamically adjust the order of language processing based on the relevance of the data. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the order of language processing based on the relevance of the data evaluated by the generative AI. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data.

[0086] The providing unit can estimate the cat's emotions and adjust the manner of linguistic expression to be provided based on the estimated cat's emotions. The providing unit, for example, estimates the cat's emotions and adjusts the manner of linguistic expression to be provided based on the estimated cat's emotions. For example, if the cat is relaxed, the providing unit can provide language using calm expressions. Furthermore, if the cat is excited, the providing unit can provide language using lively expressions. Furthermore, if the cat is stressed, the providing unit can provide language using cautious expressions. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible. Some or all of the above-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can adjust the manner of linguistic expression to be provided based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible.

[0087] The providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can prioritize and provide expressions that the user has previously preferred. The providing unit can also provide expressions that the user has previously avoided. Furthermore, the providing unit can analyze the user's past responses and select the optimal expression method. In this way, the optimal providing method can be selected by analyzing the user's past responses. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal providing method based on the user's past response data analyzed by the generation AI. In this way, the optimal providing method can be selected by analyzing the user's past responses.

[0088] The service provider can customize the content offered based on the user's current situation at the time of delivery. For example, the service provider can customize the content offered based on the user's current situation at the time of delivery. For example, if the user is relaxed, the service provider can offer calm content. Also, if the user is busy, the service provider can offer concise content. Furthermore, if the user is excited, the service provider can offer lively content. By customizing the content offered based on the user's current situation, more appropriate information can be provided. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not. For example, the service provider can customize the content offered based on the user's current situation data evaluated by the generative AI. By customizing the content offered based on the user's current situation, more appropriate information can be provided.

[0089] The service provider can estimate the cat's emotions and determine the priority of the languages ​​to be provided based on the estimated emotions. For example, if the cat is relaxed, the service provider will prioritize providing calm languages. If the cat is excited, the service provider may also prioritize providing lively languages. Furthermore, if the cat is stressed, the service provider may also prioritize providing cautious languages. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions. Some or all of the above processing in the service provider may be performed using, for example, generative AI, or not using generative AI. For example, the service provider can determine the priority of languages ​​to be provided based on cat emotion data estimated by generative AI. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions.

[0090] The providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit selects the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit can provide detailed content when the user is at home. Furthermore, the providing unit can provide concise content when the user is out. Furthermore, the providing unit can provide content related to a specific location when the user is in that location. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal delivery method based on the user's geographical location information evaluated by the generation AI. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information.

[0091] The providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can prioritize and provide content in which the user has shown interest on social media. The providing unit can also provide content that the user has avoided on social media. Furthermore, the providing unit can analyze the user's social media activity and provide optimal content. In this way, optimal content to be provided can be selected by analyzing the user's social media activity. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the providing unit can adjust the content to be provided based on the user's social media activity data analyzed by the generation AI. In this way, optimal content to be provided can be selected by analyzing the user's social media activity.

[0092] The detection unit can estimate the cat's emotions and adjust the method for detecting abnormal physical conditions based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and adjusts the method for detecting abnormal physical conditions based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit applies a normal abnormality detection method. Furthermore, when the cat is excited, the detection unit can also prioritize detecting abnormalities in the movement data. Furthermore, when the cat is stressed, the detection unit can also prioritize detecting abnormalities in the voice data. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI, for example. For example, the detection unit can adjust the method for detecting abnormal physical conditions based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible.

[0093] The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection. The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection, for example. For example, the detection unit detects abnormal behavior based on the cat's past health data. The detection unit can also detect abnormal meows by referring to the cat's past health data. Furthermore, the detection unit can analyze the cat's past health data and adjust the anomaly detection algorithm. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data. Some or all of the above-described processing in the detection unit can be performed using, or without, a generation AI, for example. For example, the detection unit can improve the accuracy of anomaly detection based on the cat's past health data analyzed by the generation AI. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data.

[0094] The detection unit can customize the anomaly detection method based on the cat's current living environment during detection. For example, the detection unit customizes the anomaly detection method based on the cat's current living environment during detection. For example, when the cat is indoors, the detection unit applies a normal anomaly detection method. Furthermore, when the cat is outside, the detection unit can prioritize detecting anomalies in motion data. Furthermore, when the cat is in a new environment, the detection unit can prioritize detecting anomalies in audio data. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI. For example, the detection unit can customize the anomaly detection method based on the cat's current living environment data evaluated by the generation AI. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment.

[0095] The detection unit can estimate the cat's emotions and determine the priority of anomaly detection based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and determines the priority of anomaly detection based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit performs normal anomaly detection. Furthermore, when the cat is excited, the detection unit can prioritize detecting anomalies in the movement data. Furthermore, when the cat is stressed, the detection unit can prioritize detecting anomalies in the voice data. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can determine the priority of anomaly detection based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies.

[0096] The detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, the detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, if the cat is inside the house, the detection unit can apply the normal anomaly detection method. Also, if the cat is outside, the detection unit can prioritize detecting anomalies in the motion data. Furthermore, if the cat is in a specific location, the detection unit can prioritize detecting anomalies related to that location. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can select the optimal anomaly detection method based on the cat's geographical location information evaluated by the generative AI. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information.

[0097] The detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can adjust the anomaly detection algorithm by referring to the latest research on cat health. The detection unit can also improve the accuracy of anomaly detection of motion data by referring to literature on cat behavior. Furthermore, the detection unit can improve the accuracy of anomaly detection of sound data by referring to literature on cat meows. In this way, the accuracy of anomaly detection is improved by referring to relevant literature. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can adjust the anomaly detection algorithm based on the relevant literature referred to by the generative AI. In this way, the accuracy of anomaly detection is improved by referring to relevant literature.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The cat verbalization system can further include a monitoring unit that monitors the cat's behavior in real time and detects abnormal behavior. The monitoring unit issues an alert, for example, if the cat behaves in a way that is different from normal. The monitoring unit can also issue an alert if the cat stays in a particular place for a long time or makes an abnormal sound. Furthermore, the monitoring unit can learn the cat's behavioral patterns and detect abnormal behavior early. This allows for more detailed monitoring of the cat's health and early detection of abnormalities.

[0100] When analyzing cat behavior data, the analysis unit can adjust the analysis algorithm based on the cat's age and breed. For example, for young cats, the analysis can focus on active behavior patterns. For older cats, the analysis can also focus on changes in health. Furthermore, the analysis can take into account behavior patterns unique to specific breeds. This enables appropriate analysis according to the cat's age and breed, improving the accuracy of the analysis.

[0101] The providing unit can analyze the user's past reactions and select the optimal providing method. For example, it can provide the expression methods that the user has preferred in the past with priority. It can also provide the expression methods that the user has avoided in the past by avoiding them. Furthermore, it can analyze the user's past reactions and select the optimal expression method. In this way, the optimal providing method can be selected by analyzing the user's past reactions.

[0102] The collection unit can prioritize collection of highly relevant data by taking into account the geographical location information of the cat. For example, if the cat is inside the house, it can prioritize collection of motion sensors. Also, if the cat is outside, it can prioritize collection of audio sensors. Furthermore, if the cat is in a specific location, it can prioritize collection of behavioral patterns in that location. In this way, by taking into account the geographical location information, it is possible to prioritize collection of highly relevant data.

[0103] The providing unit can customize the content to be provided based on the user's current situation. For example, if the user is relaxed, calm content can be provided. If the user is busy, concise content can be provided. Furthermore, if the user is excited, lively content can be provided. In this way, by customizing the content to be provided based on the user's current situation, more appropriate information can be provided.

[0104] The collection unit can analyze the social media activity of the cat and collect related data. For example, if the cat is engaging in a behavior that is popular on social media, the collection unit can prioritize collecting that behavior. Also, if the cat is in a location that is trending on social media, the collection unit can prioritize collecting behavior in that location. Furthermore, if the cat is making a specific sound on social media, the collection unit can prioritize collecting that sound. In this way, related data can be collected by analyzing social media activity.

[0105] The processing flow of the first embodiment will be briefly explained below.

[0106] Step 1: The collection unit is equipped with an audio sensor and a motion sensor to collect the cat's meows and behavior. For example, the collection unit collects the cat's meows with a highly sensitive microphone and records the cat's movements in detail using an accelerometer and gyroscope. Step 2: The analysis unit analyzes the data collected by the collection unit. For example, it preprocesses and removes noise from the audio data and analyzes the movement data to extract the cat's behavioral patterns. It then uses machine learning algorithms to analyze the data and extract the characteristics of the cat's behavior and meows. Step 3: The verbalization unit verbalizes the data analyzed by the analysis unit. For example, it uses natural language processing technology to convert the cat's meows and behavior into text, and uses generation AI to generate cat words. Step 4: The providing unit provides the language generated by the language generator to the user. For example, the providing unit displays cat words through a user interface and notifies the user using a notification function. The cat words can also be provided through a smartphone app. Step 5: The detection unit detects abnormalities in the cat's physical condition based on the data collected by the collection unit. For example, it detects abnormalities in the cat's meows or behavior and notifies the user. Generative AI can also be used to detect abnormalities in the cat's physical condition early on.

[0107] (Example 2) The cat language system according to an embodiment of the present invention is a system that uses a generative AI to translate cat language into language. This system allows the cat to "talk" to the user and engage in conversation. It can also be used as a tool for managing the cat's health. By applying this technology, a foreign language version can be used for English language learning, and it can be linked with a smartphone app to allow communication even when the user is away from home. Furthermore, it is possible to develop versions for other animals and create a generative AI zoo. Specifically, it consists of the following steps. First, the cat's meows and behavior are collected by a voice sensor and a motion sensor, and the generative AI analyzes this data and translates it into language. Next, the generated language is provided to the user, enabling conversation with the cat. For example, if the cat says "I'm hungry," the user can respond with "I'll give you some food." This system can also be used for managing the cat's health. For example, it can detect abnormalities in the cat's health from its meows and behavior and notify the user. This allows for early detection of health problems and appropriate action to be taken. Furthermore, by applying this technology, a foreign language version can be developed and used for English language learning. For example, a cat can talk to users in English, allowing them to practice listening and speaking. By linking it to a smartphone app, users can receive messages from their cat even when they're out. Finally, it's possible to develop other animal versions and create a generative AI zoo. For example, it can verbalize the words of animals like dogs and birds, allowing users to enjoy conversations with those animals. This will enrich communication with animals and provide new ways to enjoy the zoo. This will allow the cat's verbalization system to verbalize cats' words, allowing them to manage their health and converse.

[0108] The cat language system according to this embodiment comprises a collection unit, an analysis unit, a language processing unit, a provision unit, and a detection unit. The collection unit includes an audio sensor and a motion sensor to collect the cat's meows and behavior. For example, the collection unit collects the cat's meows with a high-sensitivity microphone and detects the cat's movements with the motion sensor. The collection unit can also record the cat's movements in detail using, for example, an accelerometer or gyroscope. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit preprocesses the audio data to remove noise. The analysis unit can also analyze the motion data and extract the cat's behavior patterns. The analysis unit analyzes the data using, for example, a machine learning algorithm to extract the characteristics of the cat's behavior and meows. The language processing unit translates the data analyzed by the analysis unit into language. For example, the language processing unit uses natural language processing technology to convert the cat's meows and behavior into text. The language processing unit can also generate cat language using, for example, a generative AI (such as GPT-4 or Gemini). The providing unit provides the user with the language generated by the language generation unit. For example, the providing unit displays cat language through the user interface. The providing unit can also notify the user of cat language using a notification function. The providing unit can also provide cat language to the user, for example, through a smartphone app. The detection unit detects abnormalities in the cat's health based on the data collected by the collection unit. For example, the detection unit detects abnormalities in the cat's meowing or behavior and notifies the user. The detection unit can also detect abnormalities in the cat's health early, for example, using a generative AI. As a result, the cat language generation system according to this embodiment can translate cat language, enabling health management and conversation.

[0109] The providing unit can provide the language generated by the generation AI to the user. The providing unit provides the language generated by the generation AI (e.g., GPT-4, Gemini, etc.) to the user. For example, the providing unit displays the text generated by the generation AI through a user interface. The providing unit can also provide the language generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the text generated by the generation AI into a speech synthesis engine and outputs it as audio. This allows the user to hear the cat's words aloud. Furthermore, the providing unit can notify the user of the language generated by the generation AI using a notification function. For example, the providing unit notifies the user of the cat's words through a smartphone app. This allows the user to receive the cat's words even when they are out and about. Some or all of the above-described processing in the providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when displaying the text generated by the generation AI on a user interface, the providing unit can display the text without using the generation AI. This improves the accuracy of providing the cat's words to the user by using the generation AI.

[0110] The detection unit can detect abnormalities in the cat's physical condition using the generation AI. The detection unit detects abnormalities in the cat's physical condition using, for example, a generation AI (e.g., GPT-4 or Gemini). For example, the detection unit detects abnormalities in the cat's meows or behavior based on data analyzed by the generation AI. For example, the detection unit can detect abnormal meows by having the generation AI analyze the cat's meow patterns. The detection unit can also detect abnormal movements by having the generation AI analyze the cat's movement data. For example, the detection unit can analyze the cat's movement data and detect abnormal movement patterns. In this way, by using the generation AI, abnormalities in the cat's physical condition can be detected early. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when detecting abnormalities based on data analyzed by the generation AI, the detection unit can also detect abnormalities without using the generation AI. In this way, by using the generation AI, abnormalities in the cat's physical condition can be detected early.

[0111] The analysis unit can analyze the voice data and movement data using a generation AI. The analysis unit analyzes the voice data and movement data using, for example, a generation AI (e.g., GPT-4 or Gemini). For example, the analysis unit preprocesses the voice data and removes noise. The analysis unit can also extract the cat's behavioral patterns by having the generation AI analyze the movement data. For example, the analysis unit analyzes the voice data and extracts characteristics of a cat's meows. The analysis unit can also extract the cat's movement patterns by having the generation AI analyze the movement data. For example, the analysis unit analyzes the cat's movement data and detects specific behavioral patterns. As a result, the use of the generation AI improves the accuracy of the analysis of the voice data and movement data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the voice data and movement data based on the data analyzed by the generation AI without using the generation AI. This will improve the accuracy of analyzing voice data and movement data by using generative AI.

[0112] The verbalization unit can verbalize the data analyzed by the generation AI. The verbalization unit verbalizes the analyzed data, for example, using a generation AI (e.g., GPT-4 or Gemini). For example, the verbalization unit converts a cat's meows and actions into text based on the data analyzed by the generation AI. For example, the verbalization unit analyzes a cat's meow and generates the content as text. The verbalization unit can also analyze cat movement data and generate the content as text. For example, the verbalization unit analyzes cat movement data and generates the meaning of the movement as text. In this way, the use of the generation AI improves the accuracy of verbalizing the data. Some or all of the above-mentioned processing in the verbalization unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the verbalization unit can generate text based on the data analyzed by the generation AI without using the generation AI. In this way, the use of the generation AI improves the accuracy of verbalizing the data.

[0113] The providing unit generates a foreign language version using a generation AI and can use it for English language learning. The providing unit generates a foreign language version using, for example, a generation AI (e.g., GPT-4 or Gemini) and uses it for English language learning. For example, the providing unit displays the English text generated by the generation AI through a user interface. The providing unit can also provide the English text generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the English text generated by the generation AI into a speech synthesis engine and outputs it as audio. This allows the user to practice English listening and conversation. Furthermore, the providing unit can notify the user of the English text generated by the generation AI using a notification function. For example, the providing unit notifies the user of the English text through a smartphone app. This allows the user to receive the English text even when they are out and about. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the service provider can display the English text generated by the generation AI on the user interface without using the generation AI. This allows the system to be used for English language learning by utilizing the generation AI.

[0114] The providing unit can generate other animal versions using the generation AI to create a zoo. The providing unit can generate other animal versions using, for example, a generation AI (e.g., GPT-4 or Gemini) to create a zoo. For example, the providing unit displays animal words, such as dog and bird, generated by the generation AI through a user interface. The providing unit can also provide the animal words generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the animal words generated by the generation AI into a speech synthesis engine and outputs them as audio. This allows users to enjoy conversations with animals, such as dogs and birds. The providing unit can also notify users of the animal words generated by the generation AI using a notification function. For example, the providing unit notifies users of the animal words through a smartphone app. This allows users to receive the animal words even when they are out and about. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when displaying the animal words generated by the generation AI on a user interface, the providing unit can display text without using the generation AI. This makes it possible to create versions of other animals using generative AI and build a zoo.

[0115] The data collection unit can estimate the cat's emotions and adjust the timing of audio and motion data collection based on the estimated emotions. For example, when the cat is relaxed, the data collection unit can activate the audio and motion sensors simultaneously to collect natural behavior. When the cat is excited, the data collection unit can prioritize activating the motion sensor to collect details of intense movements. Furthermore, when the cat is stressed, the data collection unit can prioritize activating the audio sensor to collect details of changes in meowing. By adjusting the collection timing based on the cat's emotions, more natural data can be collected. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can adjust the collection timing based on cat emotion data estimated by generative AI. By adjusting the collection timing based on the cat's emotions, more natural data can be collected.

[0116] The data collection unit can analyze the cat's past behavioral patterns and select the optimal data collection method. For example, if the cat has a tendency to be active during certain time periods in the past, the data collection unit can enhance the motion sensor and collect data during those times. Furthermore, if the cat frequently meows in certain locations in the past, the data collection unit can enhance the sound sensor and collect data at those locations. Additionally, if the cat has repeatedly performed certain behaviors in the past, the data collection unit can activate sensors at the time those behaviors occur. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can select the optimal data collection method based on the cat's past behavioral data analyzed by the generative AI. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns.

[0117] The collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, the collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, if the cat is healthy, the collection unit applies a normal collection method. If the cat is in poor health, the collection unit can increase the sensitivity of the movement sensor to collect abnormal movements in detail. Furthermore, if the cat is in a new environment, the collection unit can increase the sensitivity of the sound sensor to collect environmental sounds in detail. This allows for more accurate data collection by filtering based on the cat's health condition and environment. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can filter based on the cat's health condition and environmental data estimated by the generation AI. This allows for more accurate data collection by filtering based on the cat's health condition and environment.

[0118] The collection unit can estimate the cat's emotions and determine the priority of data to be collected based on the estimated cat emotions. The collection unit, for example, estimates the cat's emotions and determines the priority of data to be collected based on the estimated cat emotions. For example, when the cat is relaxed, the collection unit prioritizes collecting voice data over movement data. Also, when the cat is excited, the collection unit can prioritize collecting movement data over voice data. Furthermore, when the cat is stressed, the collection unit can collect both voice data and movement data equally. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can determine the priority of data to be collected based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially.

[0119] When collecting voice and motion, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the cat. For example, when collecting voice and motion, the collection unit prioritizes collecting highly relevant data by taking into account the geographical location information of the cat. For example, when the cat is inside the house, the collection unit can prioritize collecting motion sensors. Also, when the cat is outside, the collection unit can prioritize collecting voice sensors. Furthermore, when the cat is in a specific location, the collection unit can prioritize collecting behavioral patterns in that location. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI, for example. For example, the collection unit can prioritize collecting highly relevant data based on the geographical location information of the cat estimated by the generation AI. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information.

[0120] The collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, the collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, if the cat is engaging in a behavior that is popular on social media, the collection unit can prioritize collecting that behavior. Also, if the cat is in a location that is trending on social media, the collection unit can prioritize collecting behavior in that location. Furthermore, if the cat is making a specific meow on social media, the collection unit can prioritize collecting that meow. In this way, related data can be collected by analyzing social media activity. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the collection unit can collect related data based on the cat's social media activity data analyzed by the generation AI. In this way, related data can be collected by analyzing social media activity.

[0121] The analysis unit can estimate the cat's emotions and adjust the analysis algorithm based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the analysis algorithm based on the estimated cat emotions. For example, the analysis unit applies a normal analysis algorithm when the cat is relaxed. Furthermore, the analysis unit can apply an algorithm that enhances analysis of movement data when the cat is excited. Furthermore, the analysis unit can apply an algorithm that enhances analysis of audio data when the cat is stressed. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the analysis algorithm based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved.

[0122] The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis. The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis, for example. For example, if a cat's meows and movement match, the analysis unit prioritizes the analysis of that data. The analysis unit can also analyze a cat's meows and movement that do not match as abnormal behavior. Furthermore, the analysis unit can analyze the patterns of a cat's meows and movement and take the correlation into account during analysis. This improves the accuracy of the analysis by taking the correlation between voice and movement into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can analyze the correlation based on the voice data and movement data analyzed by the generation AI. This improves the accuracy of the analysis by taking the correlation between voice and movement into account.

[0123] The analysis unit can perform the analysis taking into account the cat's attribute information. For example, the analysis unit performs the analysis taking into account the cat's attribute information. For example, the analysis unit selects an appropriate analysis algorithm based on the cat's age. The analysis unit can also perform the analysis taking into account specific behavioral patterns based on the cat's breed. Furthermore, the analysis unit can perform analysis to detect abnormal behavior based on the cat's health condition. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can perform the analysis based on the cat's attribute information analyzed by the generation AI. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved.

[0124] The analysis unit can estimate the cat's emotions and adjust the display method of the analysis results based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the display method of the analysis results based on the estimated cat emotions. For example, the analysis unit displays detailed analysis results when the cat is relaxed. The analysis unit can also display concise analysis results when the cat is excited. Furthermore, the analysis unit can highlight abnormal behavior when the cat is stressed. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the display method of the analysis results based on the cat's emotion data estimated by the generation AI. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand.

[0125] The analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, the analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, if a cat frequently meows in a specific location, the analysis unit can prioritize the analysis of data from that location. Also, if a cat performs a specific movement in a specific location, the analysis unit can prioritize the analysis of data from that movement. Furthermore, the analysis unit can analyze the patterns of sounds and movements of the cat when it moves and analyze them while taking into account the geographical distribution. In this way, taking the geographical distribution into account improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can perform the analysis while taking into account the geographical distribution based on the sound data and movement data analyzed by the generation AI. In this way, taking the geographical distribution into account improves the accuracy of the analysis.

[0126] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis, for example. For example, the analysis unit can refer to the latest research on cat behavior and adjust the analysis algorithm. The analysis unit can also improve the accuracy of analyzing audio data by referring to literature on cat meows. Furthermore, the analysis unit can improve the accuracy of detecting abnormal behavior by referring to literature on cat health conditions. In this way, by referring to related literature, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI, for example. For example, the analysis unit can adjust the analysis algorithm based on the related literature referred to by the generation AI. In this way, by referring to related literature, the analysis accuracy is improved.

[0127] The language processing unit can estimate the cat's emotions and adjust the language processing method based on the estimated emotions. For example, if the cat is relaxed, the language processing unit will use calm language. If the cat is excited, the language processing unit can use lively language. Furthermore, if the cat is stressed, the language processing unit can use cautious language. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not. For example, the language processing unit can adjust the language processing method based on the cat's emotion data estimated by the generative AI. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible.

[0128] The language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can perform detailed language processing for important data. The language processing unit can also perform concise language processing for general data. Furthermore, the language processing unit can perform language processing that includes detailed explanations for anomalous data. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data evaluated by the generative AI. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail.

[0129] The linguistic unit can apply different linguistic algorithms depending on the data category during linguisticization. For example, the linguistic unit applies different linguistic algorithms depending on the data category during linguisticization. For example, in the case of health data, the linguistic unit performs linguisticization including medical terms. In addition, in the case of behavioral data, the linguistic unit can perform linguisticization using general terms. Furthermore, in the case of emotional data, the linguistic unit can perform linguisticization including emotional expressions. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression. Some or all of the above-mentioned processing in the linguistic unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the linguistic unit can apply different linguistic algorithms based on the data category classified by the generation AI. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression.

[0130] The verbalization unit can estimate the cat's emotions and adjust the length of the verbalization based on the estimated cat emotions. The verbalization unit, for example, estimates the cat's emotions and adjusts the length of the verbalization based on the estimated cat emotions. For example, the verbalization unit performs longer verbalizations when the cat is relaxed. Furthermore, the verbalization unit can also perform shorter verbalizations when the cat is excited. Furthermore, the verbalization unit can also perform verbalizations of an appropriate length when the cat is stressed. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length. Some or all of the above-described processing in the verbalization unit may be performed using, or without, a generation AI, for example. For example, the verbalization unit can adjust the length of the verbalizations based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length.

[0131] The language processing unit can determine the priority of language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing of the most recent data. The language processing unit can also prioritize the language processing of past data. Furthermore, the language processing unit can prioritize the language processing of data where the submission timing is important. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the language processing unit can determine the priority of language processing based on the data submission timing evaluated by the generative AI. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially.

[0132] The language processing unit can adjust the order of language processing based on the relevance of the data during the language processing process. For example, the language processing unit can prioritize the language processing of highly relevant data. It can also postpone the language processing of less relevant data. Furthermore, the language processing unit can dynamically adjust the order of language processing based on the relevance of the data. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the order of language processing based on the relevance of the data evaluated by the generative AI. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data.

[0133] The providing unit can estimate the cat's emotions and adjust the manner of linguistic expression to be provided based on the estimated cat's emotions. The providing unit, for example, estimates the cat's emotions and adjusts the manner of linguistic expression to be provided based on the estimated cat's emotions. For example, if the cat is relaxed, the providing unit can provide language using calm expressions. Furthermore, if the cat is excited, the providing unit can provide language using lively expressions. Furthermore, if the cat is stressed, the providing unit can provide language using cautious expressions. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible. Some or all of the above-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can adjust the manner of linguistic expression to be provided based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible.

[0134] The providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can prioritize and provide expressions that the user has previously preferred. The providing unit can also provide expressions that the user has previously avoided. Furthermore, the providing unit can analyze the user's past responses and select the optimal expression method. In this way, the optimal providing method can be selected by analyzing the user's past responses. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal providing method based on the user's past response data analyzed by the generation AI. In this way, the optimal providing method can be selected by analyzing the user's past responses.

[0135] The service provider can customize the content offered based on the user's current situation at the time of delivery. For example, the service provider can customize the content offered based on the user's current situation at the time of delivery. For example, if the user is relaxed, the service provider can offer calm content. Also, if the user is busy, the service provider can offer concise content. Furthermore, if the user is excited, the service provider can offer lively content. By customizing the content offered based on the user's current situation, more appropriate information can be provided. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not. For example, the service provider can customize the content offered based on the user's current situation data evaluated by the generative AI. By customizing the content offered based on the user's current situation, more appropriate information can be provided.

[0136] The service provider can estimate the cat's emotions and determine the priority of the languages ​​to be provided based on the estimated emotions. For example, if the cat is relaxed, the service provider will prioritize providing calm languages. If the cat is excited, the service provider may also prioritize providing lively languages. Furthermore, if the cat is stressed, the service provider may also prioritize providing cautious languages. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions. Some or all of the above processing in the service provider may be performed using, for example, generative AI, or not using generative AI. For example, the service provider can determine the priority of languages ​​to be provided based on cat emotion data estimated by generative AI. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions.

[0137] The providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit selects the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit can provide detailed content when the user is at home. Furthermore, the providing unit can provide concise content when the user is out. Furthermore, the providing unit can provide content related to a specific location when the user is in that location. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal delivery method based on the user's geographical location information evaluated by the generation AI. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information.

[0138] The providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can prioritize and provide content in which the user has shown interest on social media. The providing unit can also provide content that the user has avoided on social media. Furthermore, the providing unit can analyze the user's social media activity and provide optimal content. In this way, optimal content to be provided can be selected by analyzing the user's social media activity. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the providing unit can adjust the content to be provided based on the user's social media activity data analyzed by the generation AI. In this way, optimal content to be provided can be selected by analyzing the user's social media activity.

[0139] The detection unit can estimate the cat's emotions and adjust the method for detecting abnormal physical conditions based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and adjusts the method for detecting abnormal physical conditions based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit applies a normal abnormality detection method. Furthermore, when the cat is excited, the detection unit can also prioritize detecting abnormalities in the movement data. Furthermore, when the cat is stressed, the detection unit can also prioritize detecting abnormalities in the voice data. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI, for example. For example, the detection unit can adjust the method for detecting abnormal physical conditions based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible.

[0140] The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection. The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection, for example. For example, the detection unit detects abnormal behavior based on the cat's past health data. The detection unit can also detect abnormal meows by referring to the cat's past health data. Furthermore, the detection unit can analyze the cat's past health data and adjust the anomaly detection algorithm. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data. Some or all of the above-described processing in the detection unit can be performed using, or without, a generation AI, for example. For example, the detection unit can improve the accuracy of anomaly detection based on the cat's past health data analyzed by the generation AI. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data.

[0141] The detection unit can customize the anomaly detection method based on the cat's current living environment during detection. For example, the detection unit customizes the anomaly detection method based on the cat's current living environment during detection. For example, when the cat is indoors, the detection unit applies a normal anomaly detection method. Furthermore, when the cat is outside, the detection unit can prioritize detecting anomalies in motion data. Furthermore, when the cat is in a new environment, the detection unit can prioritize detecting anomalies in audio data. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI. For example, the detection unit can customize the anomaly detection method based on the cat's current living environment data evaluated by the generation AI. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment.

[0142] The detection unit can estimate the cat's emotions and determine the priority of anomaly detection based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and determines the priority of anomaly detection based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit performs normal anomaly detection. Furthermore, when the cat is excited, the detection unit can prioritize detecting anomalies in the movement data. Furthermore, when the cat is stressed, the detection unit can prioritize detecting anomalies in the voice data. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can determine the priority of anomaly detection based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies.

[0143] The detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, the detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, if the cat is inside the house, the detection unit can apply the normal anomaly detection method. Also, if the cat is outside, the detection unit can prioritize detecting anomalies in the motion data. Furthermore, if the cat is in a specific location, the detection unit can prioritize detecting anomalies related to that location. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can select the optimal anomaly detection method based on the cat's geographical location information evaluated by the generative AI. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information.

[0144] The detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can adjust the anomaly detection algorithm by referring to the latest research on cat health. The detection unit can also improve the accuracy of anomaly detection of motion data by referring to literature on cat behavior. Furthermore, the detection unit can improve the accuracy of anomaly detection of sound data by referring to literature on cat meows. In this way, the accuracy of anomaly detection is improved by referring to relevant literature. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can adjust the anomaly detection algorithm based on the relevant literature referred to by the generative AI. In this way, the accuracy of anomaly detection is improved by referring to relevant literature.

[0145] The providing unit generates a foreign language version using a generation AI and can use it for English language learning. The providing unit generates a foreign language version using, for example, a generation AI (e.g., GPT-4 or Gemini) and uses it for English language learning. For example, the providing unit displays the English text generated by the generation AI through a user interface. The providing unit can also provide the English text generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the English text generated by the generation AI into a speech synthesis engine and outputs it as audio. This allows the user to practice English listening and conversation. Furthermore, the providing unit can notify the user of the English text generated by the generation AI using a notification function. For example, the providing unit notifies the user of the English text through a smartphone app. This allows the user to receive the English text even when they are out and about. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the service provider can display the English text generated by the generation AI on the user interface without using the generation AI. This allows the system to be used for English language learning by utilizing the generation AI.

[0146] The providing unit can generate other animal versions using the generation AI to create a zoo. The providing unit can generate other animal versions using, for example, a generation AI (e.g., GPT-4 or Gemini) to create a zoo. For example, the providing unit displays animal words, such as dog and bird, generated by the generation AI through a user interface. The providing unit can also provide the animal words generated by the generation AI as audio using speech synthesis technology. For example, the providing unit inputs the animal words generated by the generation AI into a speech synthesis engine and outputs them as audio. This allows users to enjoy conversations with animals, such as dogs and birds. The providing unit can also notify users of the animal words generated by the generation AI using a notification function. For example, the providing unit notifies users of the animal words through a smartphone app. This allows users to receive the animal words even when they are out and about. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when displaying the animal words generated by the generation AI on a user interface, the providing unit can display text without using the generation AI. This makes it possible to create versions of other animals using generative AI and build a zoo.

[0147] The data collection unit can estimate the cat's emotions and adjust the timing of audio and motion data collection based on the estimated emotions. For example, when the cat is relaxed, the data collection unit can activate the audio and motion sensors simultaneously to collect natural behavior. When the cat is excited, the data collection unit can prioritize activating the motion sensor to collect details of intense movements. Furthermore, when the cat is stressed, the data collection unit can prioritize activating the audio sensor to collect details of changes in meowing. By adjusting the collection timing based on the cat's emotions, more natural data can be collected. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can adjust the collection timing based on cat emotion data estimated by generative AI. By adjusting the collection timing based on the cat's emotions, more natural data can be collected.

[0148] The data collection unit can analyze the cat's past behavioral patterns and select the optimal data collection method. For example, if the cat has a tendency to be active during certain time periods in the past, the data collection unit can enhance the motion sensor and collect data during those times. Furthermore, if the cat frequently meows in certain locations in the past, the data collection unit can enhance the sound sensor and collect data at those locations. Additionally, if the cat has repeatedly performed certain behaviors in the past, the data collection unit can activate sensors at the time those behaviors occur. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or without generative AI. For example, the data collection unit can select the optimal data collection method based on the cat's past behavioral data analyzed by the generative AI. This allows for the selection of the optimal data collection method by analyzing past behavioral patterns.

[0149] The collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, the collection unit can filter the voice and movement data based on the cat's current health condition and environment when collecting the voice and movement data. For example, if the cat is healthy, the collection unit applies a normal collection method. If the cat is in poor health, the collection unit can increase the sensitivity of the movement sensor to collect abnormal movements in detail. Furthermore, if the cat is in a new environment, the collection unit can increase the sensitivity of the sound sensor to collect environmental sounds in detail. This allows for more accurate data collection by filtering based on the cat's health condition and environment. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can filter based on the cat's health condition and environmental data estimated by the generation AI. This allows for more accurate data collection by filtering based on the cat's health condition and environment.

[0150] The collection unit can estimate the cat's emotions and determine the priority of data to be collected based on the estimated cat emotions. The collection unit, for example, estimates the cat's emotions and determines the priority of data to be collected based on the estimated cat emotions. For example, when the cat is relaxed, the collection unit prioritizes collecting voice data over movement data. Also, when the cat is excited, the collection unit can prioritize collecting movement data over voice data. Furthermore, when the cat is stressed, the collection unit can collect both voice data and movement data equally. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can determine the priority of data to be collected based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of data based on the cat's emotions, important data can be collected preferentially.

[0151] When collecting voice and motion, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the cat. For example, when collecting voice and motion, the collection unit prioritizes collecting highly relevant data by taking into account the geographical location information of the cat. For example, when the cat is inside the house, the collection unit can prioritize collecting motion sensors. Also, when the cat is outside, the collection unit can prioritize collecting voice sensors. Furthermore, when the cat is in a specific location, the collection unit can prioritize collecting behavioral patterns in that location. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI, for example. For example, the collection unit can prioritize collecting highly relevant data based on the geographical location information of the cat estimated by the generation AI. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information.

[0152] The collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, the collection unit can analyze the cat's social media activity when collecting the voice and movement, and collect related data. For example, if the cat is engaging in a behavior that is popular on social media, the collection unit can prioritize collecting that behavior. Also, if the cat is in a location that is trending on social media, the collection unit can prioritize collecting behavior in that location. Furthermore, if the cat is making a specific meow on social media, the collection unit can prioritize collecting that meow. In this way, related data can be collected by analyzing social media activity. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the collection unit can collect related data based on the cat's social media activity data analyzed by the generation AI. In this way, related data can be collected by analyzing social media activity.

[0153] The analysis unit can estimate the cat's emotions and adjust the analysis algorithm based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the analysis algorithm based on the estimated cat emotions. For example, the analysis unit applies a normal analysis algorithm when the cat is relaxed. Furthermore, the analysis unit can apply an algorithm that enhances analysis of movement data when the cat is excited. Furthermore, the analysis unit can apply an algorithm that enhances analysis of audio data when the cat is stressed. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the analysis algorithm based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the analysis algorithm based on the cat's emotions, the analysis accuracy is improved.

[0154] The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis. The analysis unit can improve the accuracy of the analysis by taking into account the correlation between voice and movement during analysis, for example. For example, if a cat's meows and movement match, the analysis unit prioritizes the analysis of that data. The analysis unit can also analyze a cat's meows and movement that do not match as abnormal behavior. Furthermore, the analysis unit can analyze the patterns of a cat's meows and movement and take the correlation into account during analysis. This improves the accuracy of the analysis by taking the correlation between voice and movement into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can analyze the correlation based on the voice data and movement data analyzed by the generation AI. This improves the accuracy of the analysis by taking the correlation between voice and movement into account.

[0155] The analysis unit can perform the analysis taking into account the cat's attribute information. For example, the analysis unit performs the analysis taking into account the cat's attribute information. For example, the analysis unit selects an appropriate analysis algorithm based on the cat's age. The analysis unit can also perform the analysis taking into account specific behavioral patterns based on the cat's breed. Furthermore, the analysis unit can perform analysis to detect abnormal behavior based on the cat's health condition. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can perform the analysis based on the cat's attribute information analyzed by the generation AI. In this way, by taking into account the cat's attribute information, the accuracy of the analysis is improved.

[0156] The analysis unit can estimate the cat's emotions and adjust the display method of the analysis results based on the estimated cat emotions. The analysis unit, for example, estimates the cat's emotions and adjusts the display method of the analysis results based on the estimated cat emotions. For example, the analysis unit displays detailed analysis results when the cat is relaxed. The analysis unit can also display concise analysis results when the cat is excited. Furthermore, the analysis unit can highlight abnormal behavior when the cat is stressed. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the display method of the analysis results based on the cat's emotion data estimated by the generation AI. By adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand.

[0157] The analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, the analysis unit can perform the analysis while taking into account the geographical distribution of sounds and movements. For example, if a cat frequently meows in a specific location, the analysis unit can prioritize the analysis of data from that location. Also, if a cat performs a specific movement in a specific location, the analysis unit can prioritize the analysis of data from that movement. Furthermore, the analysis unit can analyze the patterns of sounds and movements of the cat when it moves and analyze them while taking into account the geographical distribution. In this way, taking the geographical distribution into account improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can perform the analysis while taking into account the geographical distribution based on the sound data and movement data analyzed by the generation AI. In this way, taking the geographical distribution into account improves the accuracy of the analysis.

[0158] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis, for example. For example, the analysis unit can refer to the latest research on cat behavior and adjust the analysis algorithm. The analysis unit can also improve the accuracy of analyzing audio data by referring to literature on cat meows. Furthermore, the analysis unit can improve the accuracy of detecting abnormal behavior by referring to literature on cat health conditions. In this way, by referring to related literature, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI, for example. For example, the analysis unit can adjust the analysis algorithm based on the related literature referred to by the generation AI. In this way, by referring to related literature, the analysis accuracy is improved.

[0159] The language processing unit can estimate the cat's emotions and adjust the language processing method based on the estimated emotions. For example, if the cat is relaxed, the language processing unit will use calm language. If the cat is excited, the language processing unit can use lively language. Furthermore, if the cat is stressed, the language processing unit can use cautious language. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not. For example, the language processing unit can adjust the language processing method based on the cat's emotion data estimated by the generative AI. By adjusting the language processing method based on the cat's emotions, more natural language processing becomes possible.

[0160] The language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data. For example, the language processing unit can perform detailed language processing for important data. The language processing unit can also perform concise language processing for general data. Furthermore, the language processing unit can perform language processing that includes detailed explanations for anomalous data. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the level of detail in the language processing based on the importance of the data evaluated by the generative AI. In this way, by adjusting the level of detail in the language processing based on the importance of the data, important information can be conveyed in detail.

[0161] The linguistic unit can apply different linguistic algorithms depending on the data category during linguisticization. For example, the linguistic unit applies different linguistic algorithms depending on the data category during linguisticization. For example, in the case of health data, the linguistic unit performs linguisticization including medical terms. In addition, in the case of behavioral data, the linguistic unit can perform linguisticization using general terms. Furthermore, in the case of emotional data, the linguistic unit can perform linguisticization including emotional expressions. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression. Some or all of the above-mentioned processing in the linguistic unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the linguistic unit can apply different linguistic algorithms based on the data category classified by the generation AI. In this way, by applying the optimal linguistic algorithm depending on the data category, information can be conveyed in an appropriate expression.

[0162] The verbalization unit can estimate the cat's emotions and adjust the length of the verbalization based on the estimated cat emotions. The verbalization unit, for example, estimates the cat's emotions and adjusts the length of the verbalization based on the estimated cat emotions. For example, the verbalization unit performs longer verbalizations when the cat is relaxed. Furthermore, the verbalization unit can also perform shorter verbalizations when the cat is excited. Furthermore, the verbalization unit can also perform verbalizations of an appropriate length when the cat is stressed. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length. Some or all of the above-described processing in the verbalization unit may be performed using, or without, a generation AI, for example. For example, the verbalization unit can adjust the length of the verbalizations based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the length of the verbalizations based on the cat's emotions, information can be conveyed at an appropriate length.

[0163] The language processing unit can determine the priority of language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing based on the data submission timing during the language processing process. For example, the language processing unit can prioritize the language processing of the most recent data. The language processing unit can also prioritize the language processing of past data. Furthermore, the language processing unit can prioritize the language processing of data where the submission timing is important. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the language processing unit can determine the priority of language processing based on the data submission timing evaluated by the generative AI. In this way, by determining the priority of language processing based on the data submission timing, the latest information can be conveyed preferentially.

[0164] The language processing unit can adjust the order of language processing based on the relevance of the data during the language processing process. For example, the language processing unit can prioritize the language processing of highly relevant data. It can also postpone the language processing of less relevant data. Furthermore, the language processing unit can dynamically adjust the order of language processing based on the relevance of the data. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data. Some or all of the above processing in the language processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the language processing unit can adjust the order of language processing based on the relevance of the data evaluated by the generative AI. This allows for the preferential transmission of highly relevant information by adjusting the order of language processing based on the relevance of the data.

[0165] The providing unit can estimate the cat's emotions and adjust the manner of linguistic expression to be provided based on the estimated cat's emotions. The providing unit, for example, estimates the cat's emotions and adjusts the manner of linguistic expression to be provided based on the estimated cat's emotions. For example, if the cat is relaxed, the providing unit can provide language using calm expressions. Furthermore, if the cat is excited, the providing unit can provide language using lively expressions. Furthermore, if the cat is stressed, the providing unit can provide language using cautious expressions. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible. Some or all of the above-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can adjust the manner of linguistic expression to be provided based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the manner of linguistic expression to be provided based on the cat's emotions, more natural communication is possible.

[0166] The providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can select the optimal providing method by analyzing the user's past responses at the time of providing. For example, the providing unit can prioritize and provide expressions that the user has previously preferred. The providing unit can also provide expressions that the user has previously avoided. Furthermore, the providing unit can analyze the user's past responses and select the optimal expression method. In this way, the optimal providing method can be selected by analyzing the user's past responses. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal providing method based on the user's past response data analyzed by the generation AI. In this way, the optimal providing method can be selected by analyzing the user's past responses.

[0167] The service provider can customize the content offered based on the user's current situation at the time of delivery. For example, the service provider can customize the content offered based on the user's current situation at the time of delivery. For example, if the user is relaxed, the service provider can offer calm content. Also, if the user is busy, the service provider can offer concise content. Furthermore, if the user is excited, the service provider can offer lively content. By customizing the content offered based on the user's current situation, more appropriate information can be provided. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not. For example, the service provider can customize the content offered based on the user's current situation data evaluated by the generative AI. By customizing the content offered based on the user's current situation, more appropriate information can be provided.

[0168] The service provider can estimate the cat's emotions and determine the priority of the languages ​​to be provided based on the estimated emotions. For example, if the cat is relaxed, the service provider will prioritize providing calm languages. If the cat is excited, the service provider may also prioritize providing lively languages. Furthermore, if the cat is stressed, the service provider may also prioritize providing cautious languages. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions. Some or all of the above processing in the service provider may be performed using, for example, generative AI, or not using generative AI. For example, the service provider can determine the priority of languages ​​to be provided based on cat emotion data estimated by generative AI. This allows for the priority of providing important information by determining the priority of languages ​​based on the cat's emotions.

[0169] The providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit selects the optimal delivery method by taking into account the user's geographical location information when providing the information. For example, the providing unit can provide detailed content when the user is at home. Furthermore, the providing unit can provide concise content when the user is out. Furthermore, the providing unit can provide content related to a specific location when the user is in that location. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can select the optimal delivery method based on the user's geographical location information evaluated by the generation AI. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information.

[0170] The providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can adjust the content to be provided by analyzing the user's social media activity at the time of providing the content. For example, the providing unit can prioritize and provide content in which the user has shown interest on social media. The providing unit can also provide content that the user has avoided on social media. Furthermore, the providing unit can analyze the user's social media activity and provide optimal content. In this way, optimal content to be provided can be selected by analyzing the user's social media activity. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the providing unit can adjust the content to be provided based on the user's social media activity data analyzed by the generation AI. In this way, optimal content to be provided can be selected by analyzing the user's social media activity.

[0171] The detection unit can estimate the cat's emotions and adjust the method for detecting abnormal physical conditions based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and adjusts the method for detecting abnormal physical conditions based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit applies a normal abnormality detection method. Furthermore, when the cat is excited, the detection unit can also prioritize detecting abnormalities in the movement data. Furthermore, when the cat is stressed, the detection unit can also prioritize detecting abnormalities in the voice data. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI, for example. For example, the detection unit can adjust the method for detecting abnormal physical conditions based on the cat's emotion data estimated by the generation AI. In this way, by adjusting the method for detecting abnormal physical conditions based on the cat's emotions, more accurate abnormality detection is possible.

[0172] The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection. The detection unit can improve the accuracy of anomaly detection by referring to the cat's past health data during detection, for example. For example, the detection unit detects abnormal behavior based on the cat's past health data. The detection unit can also detect abnormal meows by referring to the cat's past health data. Furthermore, the detection unit can analyze the cat's past health data and adjust the anomaly detection algorithm. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data. Some or all of the above-described processing in the detection unit can be performed using, or without, a generation AI, for example. For example, the detection unit can improve the accuracy of anomaly detection based on the cat's past health data analyzed by the generation AI. In this way, the accuracy of anomaly detection is improved by referring to the cat's past health data.

[0173] The detection unit can customize the anomaly detection method based on the cat's current living environment during detection. For example, the detection unit customizes the anomaly detection method based on the cat's current living environment during detection. For example, when the cat is indoors, the detection unit applies a normal anomaly detection method. Furthermore, when the cat is outside, the detection unit can prioritize detecting anomalies in motion data. Furthermore, when the cat is in a new environment, the detection unit can prioritize detecting anomalies in audio data. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment. Some or all of the above-described processing in the detection unit may be performed using, or without, a generation AI. For example, the detection unit can customize the anomaly detection method based on the cat's current living environment data evaluated by the generation AI. This allows for more appropriate anomaly detection by customizing the anomaly detection method based on the cat's current living environment.

[0174] The detection unit can estimate the cat's emotions and determine the priority of anomaly detection based on the estimated cat emotions. The detection unit, for example, estimates the cat's emotions and determines the priority of anomaly detection based on the estimated cat emotions. For example, when the cat is relaxed, the detection unit performs normal anomaly detection. Furthermore, when the cat is excited, the detection unit can prioritize detecting anomalies in the movement data. Furthermore, when the cat is stressed, the detection unit can prioritize detecting anomalies in the voice data. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can determine the priority of anomaly detection based on the cat's emotion data estimated by the generation AI. In this way, by determining the priority of anomaly detection based on the cat's emotions, it is possible to prioritize detection of important anomalies.

[0175] The detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, the detection unit can select the optimal anomaly detection method when detecting a cat, taking into account the cat's geographical location information. For example, if the cat is inside the house, the detection unit can apply the normal anomaly detection method. Also, if the cat is outside, the detection unit can prioritize detecting anomalies in the motion data. Furthermore, if the cat is in a specific location, the detection unit can prioritize detecting anomalies related to that location. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can select the optimal anomaly detection method based on the cat's geographical location information evaluated by the generative AI. In this way, the optimal anomaly detection method can be selected by taking into account the cat's geographical location information.

[0176] The detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can improve the accuracy of anomaly detection by referring to relevant literature when detecting an anomaly. For example, the detection unit can adjust the anomaly detection algorithm by referring to the latest research on cat health. The detection unit can also improve the accuracy of anomaly detection of motion data by referring to literature on cat behavior. Furthermore, the detection unit can improve the accuracy of anomaly detection of sound data by referring to literature on cat meows. In this way, the accuracy of anomaly detection is improved by referring to relevant literature. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can adjust the anomaly detection algorithm based on the relevant literature referred to by the generative AI. In this way, the accuracy of anomaly detection is improved by referring to relevant literature. === Hard Collateral 1-1 === Each of the multiple elements described above, including the collection unit, analysis unit, language processing unit, provision unit, and detection unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects the cat's meows and behavior using the smart device 14's high-sensitivity microphone and motion sensors. The analysis unit analyzes the data collected by the identification processing unit 290 of the data processing unit 12 and extracts the cat's behavior patterns. The language processing unit translates the data analyzed by the identification processing unit 290 of the data processing unit 12 into language using natural language processing technology. The provision unit provides the cat's language to the user through the smart device 14's user interface. The detection unit detects abnormalities in the cat's physical condition using the identification processing unit 290 of the data processing unit 12 and notifies the user. === Hard Collateral 1-2 === Each of the multiple elements described above, including the collection unit, analysis unit, language processing unit, provision unit, and detection unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects the cat's meows and behavior using the smart glasses 214's high-sensitivity microphone and motion sensors. The analysis unit analyzes the data collected by the identification processing unit 290 of the data processing unit 12 and extracts the cat's behavior patterns. The language processing unit translates the data analyzed by the identification processing unit 290 of the data processing unit 12 into language using natural language processing technology. The provision unit provides the cat's language to the user through the user interface of the smart glasses 214. The detection unit detects abnormalities in the cat's physical condition using the identification processing unit 290 of the data processing unit 12 and notifies the user. === Hard Collateral 1-3 === Each of the multiple elements described above, including the collection unit, analysis unit, language processing unit, provision unit, and detection unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects the cat's meows and behavior using the headset terminal 314's high-sensitivity microphone and motion sensors. The analysis unit analyzes the data collected by the identification processing unit 290 of the data processing unit 12 and extracts the cat's behavior patterns. The language processing unit translates the data analyzed by the identification processing unit 290 of the data processing unit 12 into language using natural language processing technology. The provision unit provides the cat's language to the user through the user interface of the headset terminal 314. The detection unit detects abnormalities in the cat's physical condition using the identification processing unit 290 of the data processing unit 12 and notifies the user. === Hard Collateral 1-4 === Each of the multiple elements described above, including the collection unit, analysis unit, language processing unit, provision unit, and detection unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects the cat's meows and behavior using the robot 414's high-sensitivity microphone and motion sensors. The analysis unit analyzes the data collected by the identification processing unit 290 of the data processing unit 12 and extracts the cat's behavior patterns. The language processing unit verbalizes the data analyzed by the identification processing unit 290 of the data processing unit 12 using natural language processing technology. The provision unit provides the cat's language to the user through the robot 414's user interface. The detection unit detects abnormalities in the cat's physical condition using the identification processing unit 290 of the data processing unit 12 and notifies the user.

[0177] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0178] The cat verbalization system can further include a monitoring unit that monitors the cat's behavior in real time and detects abnormal behavior. The monitoring unit issues an alert, for example, if the cat behaves in a way that is different from normal. The monitoring unit can also issue an alert if the cat stays in a particular place for a long time or makes an abnormal sound. Furthermore, the monitoring unit can learn the cat's behavioral patterns and detect abnormal behavior early. This allows for more detailed monitoring of the cat's health and early detection of abnormalities.

[0179] The providing unit can estimate the user's emotions and adjust the tone of the language to be provided based on the estimated user's emotions. For example, if the user is relaxed, the language can be provided in a calm tone. If the user is excited, the language can be provided in a lively tone. Furthermore, if the user is stressed, the language can be provided in a cautious tone. This allows for more natural communication by providing language in an appropriate tone according to the user's emotions.

[0180] When analyzing cat behavior data, the analysis unit can adjust the analysis algorithm based on the cat's age and breed. For example, for young cats, the analysis can focus on active behavior patterns. For older cats, the analysis can also focus on changes in health. Furthermore, the analysis can take into account behavior patterns unique to specific breeds. This enables appropriate analysis according to the cat's age and breed, improving the accuracy of the analysis.

[0181] The collection unit can estimate the cat's emotions and select the type of data to collect based on the estimated cat emotions. For example, if the cat is relaxed, voice data can be collected with priority. Also, if the cat is excited, movement data can be collected with priority. Furthermore, if the cat is stressed, both voice data and movement data can be collected equally. In this way, by selecting the type of data to collect based on the cat's emotions, important data can be collected with priority.

[0182] The providing unit can analyze the user's past reactions and select the optimal providing method. For example, it can provide the expression methods that the user has preferred in the past with priority. It can also provide the expression methods that the user has avoided in the past by avoiding them. Furthermore, it can analyze the user's past reactions and select the optimal expression method. In this way, the optimal providing method can be selected by analyzing the user's past reactions.

[0183] The analysis unit can estimate the cat's emotions and adjust the display method of the analysis results based on the estimated cat emotions. For example, if the cat is relaxed, detailed analysis results can be displayed. If the cat is excited, concise analysis results can be displayed. Furthermore, if the cat is stressed, abnormal behavior can be highlighted. In this way, by adjusting the display method of the analysis results based on the cat's emotions, it is possible to display results that are easy for the user to understand.

[0184] The collection unit can prioritize collection of highly relevant data by taking into account the geographical location information of the cat. For example, if the cat is inside the house, it can prioritize collection of motion sensors. Also, if the cat is outside, it can prioritize collection of audio sensors. Furthermore, if the cat is in a specific location, it can prioritize collection of behavioral patterns in that location. In this way, by taking into account the geographical location information, it is possible to prioritize collection of highly relevant data.

[0185] The providing unit can customize the content to be provided based on the user's current situation. For example, if the user is relaxed, calm content can be provided. If the user is busy, concise content can be provided. Furthermore, if the user is excited, lively content can be provided. In this way, by customizing the content to be provided based on the user's current situation, more appropriate information can be provided.

[0186] The analysis unit can estimate the cat's emotions and adjust the analysis algorithm based on the estimated emotions. For example, if the cat is relaxed, the normal analysis algorithm is applied. If the cat is excited, an algorithm that enhances the analysis of behavioral data can be applied. Furthermore, if the cat is stressed, an algorithm that enhances the analysis of vocal data can be applied. By adjusting the analysis algorithm based on the cat's emotions, the accuracy of the analysis is improved.

[0187] The collection unit can analyze the social media activity of the cat and collect related data. For example, if the cat is engaging in a behavior that is popular on social media, the collection unit can prioritize collecting that behavior. Also, if the cat is in a location that is trending on social media, the collection unit can prioritize collecting behavior in that location. Furthermore, if the cat is making a specific sound on social media, the collection unit can prioritize collecting that sound. In this way, related data can be collected by analyzing social media activity.

[0188] The processing flow of the second embodiment will be briefly explained below.

[0189] Step 1: The collection unit is equipped with an audio sensor and a motion sensor to collect the cat's meows and behavior. For example, the collection unit collects the cat's meows with a highly sensitive microphone and records the cat's movements in detail using an accelerometer and gyroscope. Step 2: The analysis unit analyzes the data collected by the collection unit. For example, it preprocesses and removes noise from the audio data and analyzes the movement data to extract the cat's behavioral patterns. It then uses machine learning algorithms to analyze the data and extract the characteristics of the cat's behavior and meows. Step 3: The verbalization unit verbalizes the data analyzed by the analysis unit. For example, it uses natural language processing technology to convert the cat's meows and behavior into text, and uses generation AI to generate cat words. Step 4: The providing unit provides the language generated by the language generator to the user. For example, the providing unit displays cat words through a user interface and notifies the user using a notification function. The cat words can also be provided through a smartphone app. Step 5: The detection unit detects abnormalities in the cat's physical condition based on the data collected by the collection unit. For example, it detects abnormalities in the cat's meows or behavior and notifies the user. Generative AI can also be used to detect abnormalities in the cat's physical condition early on.

[0190] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0191] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0192] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0193] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0194] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0195] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0196] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0197] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0198] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

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

[0200] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0201] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0202] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0203] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0204] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0205] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0206] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0207] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0208] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0209] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0210] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0211] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0212] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0213] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0214] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0215] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0216] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0217] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0218] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0219] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0220] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0221] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0222] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0223] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0224] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0225] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0226] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0227] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0228] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0229] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0230] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0231] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0232] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0233] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0234] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0235] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0236] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0237] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0238] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0239] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0240] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0241] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0242] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0243] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0244] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0245] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0246] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0247] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0248] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0249] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0250] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0251] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0252] 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.

[0253] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0254] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0255] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0256] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0257] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0258] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0259] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0260] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0261] [Explanation of symbols]

[0262] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit including an audio sensor and a motion sensor; an analysis unit that analyzes the data collected by the collection unit; a verbalization unit that verbalizes the data analyzed by the analysis unit; a providing unit that provides the language generated by the language generation unit to a user; A detection unit is provided that detects abnormalities in physical condition based on the data collected by the collection unit. A system characterized by:

2. The providing unit Providing users with language generated by generative AI 2. The system of claim 1.

3. The detection unit Detecting abnormalities in physical condition using generative AI 2. The system of claim 1.

4. The analysis unit Analyze voice and movement data using generative AI 2. The system of claim 1.

5. The verbalization unit Verbalizing data analyzed by generative AI 2. The system of claim 1.

6. The providing unit Generate foreign language versions using generative AI and use them for English learning 2. The system of claim 1.

7. The providing unit Use AI to generate other animal versions and create a zoo.

2. The system of claim 1.

8. The collecting unit Estimate the cat's emotions and adjust the timing of collecting sounds and movements based on the estimated emotions.

2. The system of claim 1.

Images